Biobased Polymer

This article is licensed under CC-BY 4.
pubs.acs.org/EF Review
Advances, Synergy, and Perspectives of Machine Learning and

Biobased Polymers for Energy, Fuels, and Biochemicals for a
Sustainable Future
Abu Danish Aiman Bin Abu Sofian, Xun Sun, Vijai Kumar Gupta, Aydin Berenjian, Ao Xia,
Zengling Ma,* and Pau Loke Show*
Cite This: Energy Fuels 2024, 38, 1593−1617 Read Online

See https://pubs.acs.org/sharingguidelines for options on how to legitimately share published articles.
ACCESS Metrics & More Article Recommendations

Downloaded via 122.175.161.191 on February 19, 2024 at 05:52:38 (UTC).
ABSTRACT: This review illuminates the pivotal synergy between

machine learning (ML) and biopolymers, spotlighting their
combined potential to reshape sustainable energy, fuels, and
biochemicals. Biobased polymers, derived from renewable sources,
have garnered attention for their roles in sustainable energy and
fuel sectors. These polymers, when integrated with ML techniques,
exhibit enhanced functionalities, optimizing renewable energy
systems, storage, and conversion. Detailed case studies reveal the
potential of biobased polymers in energy applications and the fuel
industry, further showcasing how ML bolsters fuel efficiency and
innovation. The intersection of biobased polymers and ML also
marks advancements in biochemical production, emphasizing
innovations in drug delivery and medical device development.
This review underscores the imperative of harnessing the convergence of ML and biobased polymers for future global sustainability
endeavors in energy, fuels, and biochemicals. The collective evidence presented asserts the immense promise this union holds for
steering a sustainable and innovative trajectory.
1. INTRODUCTION being made.21,22 Table 1 shows the Source and Overview of

In the quest for a sustainable future, numerous challenges have Biobased Polymers. The production and modification of these
been encountered.1,2 Global reliance on nonrenewable energy polymers are currently being refined, contributing to the
sources has exacted a significant toll on the environment.3−5 gradual mitigation of the associated challenges. Despite these
Traditional materials, primarily derived from finite resources, endeavors, optimizing biobased polymers for diverse applica-
exacerbate the environmental burden, contributing to pollution tions remains a significant hurdle.23,24 Parallel efforts are
and resource depletion.6,7 The promise of biobased polymers, observed in the realm of ML where advanced algorithms and
sourced from renewable biomass, is overshadowed by various computational models are being developed to enhance the
obstacles, including their production, modification, and characteristics and applications of biobased polymers.25−27 ML
application in diverse fields.8 ML, a subset of artificial strategies for the improved production and application of
intelligence, involves the development of algorithms and biobased polymers are emerging. These efforts symbolize the
statistical models that enable computers to perform tasks budding synergy between ML and biobased polymers,
without explicit instructions.9−11 Instead, these systems learn showcasing the collective stride toward a sustainable future.
from and make predictions or decisions based on data. This In this comprehensive review, an exhaustive and critical
technology has become increasingly pivotal in various sectors, examination of the advancement and synergy of ML and
including energy, materials, and biotechnology.12−17 The biobased polymers is conducted. Insight into the inherent
integration of ML offers a pioneering approach, potentially
overcoming these barriers by optimizing biopolymer character-
istics and their applications in energy, fuel, and biochemical Received: October 6, 2023
domains.18−20 However, a substantial research gap persists in Revised: December 15, 2023
the comprehensive understanding and effective deployment of Accepted: December 15, 2023
this synergistic relationship. Published: January 16, 2024
In various sectors, initial strides toward integrating biobased
polymers for sustainable energy, fuels, and biochemicals are
© 2024 The Authors. Published by
American Chemical Society https://doi.org/10.1021/acs.energyfuels.3c03842
1593 Energy Fuels 2024, 38, 1593−1617
Energy & Fuels pubs.acs.org/EF Review
Table 1. Source and Overview of Biobased Polymers global research community, highlighting the potential for
enhanced exploration and investment in these areas, pivotal for
source of
biobased driving sustainable advancements and innovations.
polymers biopolymer types potential application reference
Corn starch Polylactic acid (PLA) Biodegradable packaging, 28 2. BIOBASED POLYMERS AND SUSTAINABILITY
agricultural products
Sugar cane Biopolyethylene (bio- Food packaging, cosmetics, 29 A global shift toward sustainability is being witnessed.40−42 An
PE) personal care, automotive essential role in this transformative move is played by biobased
parts, toys, agricultural
and industrial purposes polymers, which are derived from biological sources rather
Microalgae Polyhydroxy alkanoates Medical devices, 30 than petroleum bases.43,44 Derived from biomass, these
(PHA) Biodegradable packaging polymers are considered the more sustainable option, thereby
Cellulose Cellulose acetate Food packaging 31 increasing utilization across various industries.45 In this
Soybeans Polyhydroxyerethane Adhesives and coatings 32 significant transition, biobased polymers’ properties, character-
(PHU) istics, and diverse applications are analyzed, highlighting their
Potatoes Starch-based Biodegradable packaging 33
biopolymers films
impactful role in advancing the sustainable agenda for the
Castor oil Polyamide 11 (PA11), Footwear and automotive 34−36 energy, fuel, and biochemical industries.46 In their essence,
Polyurethane (PU) parts biobased polymers carry properties that address many
Chitin from Chitosan Drug delivery and dressings 37 environmental concerns.47 Being biodegradable, a significant
shrimps
and crabs
reduction in waste pollution is associated with their use.48,49
Whey Whey protein-based Food packaging 38
These polymers exhibit a commendable balance between
films lightness and strength and their flexibility, making them
Macroalgae Alginate, agar, Edible films and lectins 39 adaptable to a wide range of applications.50 Their diverse
carrageenan properties open avenues for customizations suitable for specific
needs, reinforcing their potential and adaptability across
attributes of biobased polymers and their cardinal role in multiple sectors.
bolstering sustainability in diverse applications is offered. The A swift surge in the application of biobased polymers in the
profound influences of ML on the enhancement of biobased energy sector is noted.51,52 The efficiency and durability of
polymers are elucidated. Discussions highlight the prominent renewable energy systems such as solar panels and wind
role of biobased polymers in sustainable fuels and their turbines are being enhanced by integrating biobased
production, alongside the substantial impact of ML on fuel polymers.53,54 These polymers further facilitate the fostering
efficiency and innovation. The notable contributions of both of sustainable energy technologies, emphasizing their signifi-
domains to the advancement of biochemical production are cant role in promoting renewable energy systems and
expounded. A conclusion is presented, summing the findings contributing to the global sustainability movement. A marked
and providing a directional path for future research, solidifying influence of biobased polymers in the fuel industry is
the belief in the continuous collaborative growth of ML and observed.55 The enhancement in the production of biofuels
biobased polymers for a sustainable global future. is ascribed to the effective catalytic properties exhibited by
This compelling review culminates in affirming the these polymers. The efficient conversion of biomass to fuels is
indispensable role played by the convergence of ML and being facilitated, demonstrating their crucial contribution to
biobased polymers in energy, fuels, and biochemicals. This bolstering sustainable fuel production.55,56 This is an essential
review fills a gap in the current literature by providing a unique, step in the global move toward more sustainable and cleaner
integrated perspective on ML and biobased polymers, a energy solutions, further reinforcing the pivotal role played by
combination scarcely addressed in existing studies, offering biobased polymers.
timely insights into emerging interdisciplinary solutions for The realm of biochemicals is not untouched by the extensive
sustainability. The path toward a more sustainable and benefits of biobased polymers. Their use in developing
innovative future is presented by thoroughly exploring the biodegradable and ecofriendly packaging materials is reducing
intersection of these two critical domains. The detailed analysis the environmental load considerably. 57,58 Moreover, a
presented within these pages aims to inform and spur further significant contribution to the production of sustainable
research and development in these vital areas. The criticality of chemicals and materials is made by these polymers, showcasing
this synergy underscores a compelling opportunity for the their extensive and versatile applications.59 In the domain of
Table 2. ML’s Capability in Property Prediction and Optimization Potential for Materials Science and Engineering
property or feature ML’s role in enhancement potential impact references

Material design Guiding innovative design approaches Enhanced material functionality 61, 84
Mechanical properties Predicting and optimizing strength and durability Improved product reliability and lifespan 85, 86
Thermal properties Forecasting and enhancing heat resistance Wider application range 87, 88
Environmental compatibility Assessing and improving biodegradability Increased sustainability 89, 90
Production efficiency Enhancing process parameters for efficient production Reduced production cost and time 91, 92
Performance characteristics Ensuring robust and efficient material properties Enhanced operational efficiency 79, 93
Application specific customization Tailoring polymers for specific applications Improved performance in diverse applications 94, 95
Cost-efficiency Optimizing for low-cost production and material use Economic and competitive advantages 96, 97
Integration in renewable energy systems Customizing materials for energy systems Augmented renewable energy efficiency 98, 99
Integration in energy storage Developing advanced components for energy storage Enhanced energy storage capacity and efficiency 73, 100
1594 https://doi.org/10.1021/acs.energyfuels.3c03842
Energy Fuels 2024, 38, 1593−1617
energy storage and conversion, biobased polymers are making playing a crucial role in enhancing overall energy conversion
substantial contributions.60 High-efficiency batteries and processes and technologies.79
supercapacitors are being developed with these polymers, Further, integrating ML in the realm of biobased polymers
exhibiting advancements in energy storage solutions and fosters innovation in material design and performance. ML’s
contributing to the sustainable energy ecosystem.19,51 capability in property prediction and optimization guides the
The encompassing role of biobased polymers in propelling development of biobased polymers with enhanced features for
global sustainability efforts is emphasized. From the energy diverse energy applications.82,83 The concurrent evolution of
sector to biochemicals, their diverse applications foster both these domains, facilitated by ML, ensures the timely
advancements in sustainable technologies and materials, advancement and integration of efficient and sustainable
leading the path toward a more environmentally conscious biobased polymers in the global energy landscape.
future. The ongoing research and exploration in biobased In summation, the integration of ML in material science,
polymers signify the continuous enhancement and discovery of particularly in enhancing and developing biobased polymers,
their potential, promising a sustainable and innovative future. marks a significant leap toward comprehensive sustainability
and efficiency in energy systems. Ensuring the continued
3. ML: REVOLUTIONIZING MATERIAL SCIENCE collaboration and innovation in these intertwined domains is
In the evolving panorama of material science, the influence of fundamental for the realization of global sustainable energy
ML stands out, predominantly steering the enhancement and objectives, underscoring the essential role of ML in this
development of sustainable materials and biobased poly- endeavor.
mers.61−65 The prospect of designing advanced materials
with precise properties for specific applications is heightened 4. ENERGY AND FUELS
by employing ML algorithms for property prediction and 4.1. Biobased Polymers for Sustainable Energy. The
optimization.11,66,67 A comprehensive analysis of large data sets integration of biobased polymers such as chitosan, lignin,
performed by ML efficiently discerns patterns and correlations polypyrrole, PLA, PHA, and microalgae-derived biopolymers
that might remain unnoticed by conventional methods.68 in the field of sustainable energy reveals significant promise for
Through this, expedited and more informed decisions are enhancing the performance and environmental compatibility of
made in the development of biobased polymers for diverse renewable energy systems, energy storage, and energy
applications. Table 2 shows the ML capability in property conversion.101−104 Within the renewable energy sector, these
prediction and optimization potential for materials science and polymers actively participate in constructing more efficient,
engineering. environmentally friendly solar cells.105 Their application is seen
In the sector of renewable energy systems, a remarkable in organic photovoltaic cells, which serve as the active layer,
enhancement is noticed in the integration of biobased enabling the absorption and conversion of solar energy to
polymers, courtesy of ML interventions.69,70 Renewable energy electricity.106,107 For instance, in the fabrication of organic
apparatuses like solar cells and wind turbines are experiencing photovoltaic cells, chitosan is often employed due to its
a boost in operational efficiency by incorporating ML- excellent film-forming properties and biocompatibility, enhanc-
optimized biobased polymers.71,72 By understanding the ing the cell’s ability to absorb and convert solar energy.108,109
intricate material properties and performance characteristics, Additionally, PLA is another biobased polymer frequently used
ML aids in customizing biobased polymers to complement the in these cells for its environmental sustainability and efficiency
unique requirements of different renewable energy systems.27 in aiding the conversion process from solar to electrical
This cooperation between ML and biobased polymers is energy.110,111
proving to be instrumental in augmenting the sustainability In the realm of energy storage, biobased polymers show
and efficiency of renewable energy systems, contributing significant potential for the development of advanced,
significantly to global sustainable energy goals. sustainable batteries.112 Utilizing biobased polymers for
Shifting the focus to energy storage, ML’s impact in the making electrodes and electrolytes in batteries has witnessed
refinement of biobased polymers for this purpose is notable advancements, contributing to the production of high-
substantial.73 The ML algorithms, proficient in analyzing and performance energy storage devices.22,113 The introduction of
predicting material behaviors, play a crucial role in the these ecofriendly materials in batteries effectively supports the
development of biobased polymer components for advanced reduction of hazardous waste and the overall environmental
batteries and energy storage systems.27,74 The accurate footprint.114 This application stands as a testament to the
prediction capabilities of ML aid in ensuring the robustness beneficial amalgamation of biobased polymers and energy
and efficiency of these storage solutions, further emphasizing storage systems. Additionally, the role of biobased polymers in
ML’s role in promoting the sustainability of energy storage energy conversion is crucial and is gradually gaining attention.
technologies.75,76 Real-time monitoring and predictive main- These materials contribute to the enhancement of fuel cells
tenance, facilitated by ML, enhance the lifespan and reliability and other energy conversion devices, ensuring higher efficiency
of these energy storage systems, showcasing the comprehensive and sustainability. Biobased polymers function as essential
benefits of ML’s integration.77,78 components in the membranes of fuel cells, promoting the
In energy conversion systems, the contribution of ML to the efficient conversion of chemical energy to electrical en-
progress of biobased polymers is crucial.79 The role of ergy.101,115 By replacing conventional, petroleum-based
biobased polymers in fuel cells and other energy conversion materials with biobased alternatives in these applications, the
devices is optimized by employing ML for the precise tailoring industry makes substantial strides toward a more sustainable
of material properties.80,81 The potential of ML in guiding the and ecofriendly future.
development of high-performance, sustainable biobased The infusion of ML with materials further catalyzes these
polymer components for energy conversion is significant. It advancements, providing an avenue for optimized material
ensures the efficiency and sustainability of these systems, thus design and utilization.116 Sophisticated algorithms and models
Energy Fuels 2024, 38, 1593−1617
facilitate the precise tailoring of biobased polymer properties to after 70 days of exposure to ambient conditions. The intricate
meet specific energy-related applications. ML assists in methods employed, including density functional theory
predicting and enhancing the performance, functionality, and calculations, affirmed HS’s passivation of MAPbI3 and TiO2
environmental impact of these polymers within diverse energy surfaces, interacting with undersaturated ions and thereby
systems.117 Through this synergy, the potential for innovation enhancing the overall device performance. Furthermore,
and development in utilizing biobased polymers for sustainable elucidating reduced hysteresis and enhancing device parameter
energy is boundless. consistency post-HS layer addition solidify the findings. The
In conclusion, the amalgamation of biobased polymers with comprehensive assessment, including photoluminescence spec-
sustainable energy applications bolstered by advancements in troscopy and time-resolved PL decay kinetics, reinforced HS’s
ML exemplifies a promising pathway for the future. These critical role in promoting charge transfer, reducing surface
polymers’ incorporation into renewable energy systems, energy charge trapping, and improving film quality by diminishing
storage, and energy conversion technologies demonstrates void density. The evident increase in recombination resistance
tangible benefits for these systems’ efficiency, performance, and from 1345 Ω to 2138 Ω with HS, highlighted in the Nyquist
environmental sustainability. The continued exploration, plots, further supports the assertion of HS’s impactful role in
research, and development in this domain are imperative to enhancing perovskite solar cell performance. In terms of
fully unlock and harness the potential of biobased polymers for stability, the HS interlayer proves crucial. A compelling 90% of
a more sustainable and energy-efficient future. The commit- initial performance is retained after 70 days in a nitrogen
ment to this exploration and innovation will invariably lead to atmosphere, a notable improvement over the reference cell’s
achieving global sustainability goals, ensuring a cleaner, 60% efficiency retention. These robust findings underscore the
greener, and more efficient energy landscape for future HS layer’s crucial role in significantly enhancing perovskite
generations. solar cells’ efficiency and durability.
4.2. Case Studies of Advanced Biobased Polymers for In the work by Rasal et al.,120 a novel and nature-inspired
Energy Applications. Exploring biobased polymers for approach utilizing polydopamine (PDA)-based additives in
energy-related applications holds significant promise in the polysulfide electrolytes was explored to enhance the efficiency
journey toward sustainable energy solutions. Advanced and stability of quantum dot-sensitized solar cells (QDSSCs).
biobased polymers, thoroughly investigated through various The work reports a significant enhancement in the conversion
case studies, unveil opportunities for enhanced ionic efficiencies with P-PDA and Se-PDA electrolytes, yielding
conductivity, increased efficiency and longevity of energy 7.83% and 8.59%, respectively, compared to a 7.62% efficiency
devices, and improvement in other critical parameters, from the reference electrolyte. This improvement is attributed
ultimately contributing to the evolution of green energy to the suppression of electron−hole recombination at the
technologies. TiO2/QDs/electrolyte interface by the PDA-based additives.
The work by Rudhziah et al.118 presented an innovative Moreover, the PDA-based additives greatly contributed to the
exploration into the realm of biopolymer electrolytes, performance stability of QDSSCs, with P-PDA and Se-PDA
specifically focusing on blends of carboxymethyl kappa- devices retaining 91% and 79% of their original performance
carrageenan and carboxymethyl cellulose. The blending was after 60 h, contrasting sharply with the 11% retention of liquid
found to enhance material properties, particularly conductivity. electrolytes. The technical aspects were meticulously detailed
The research reported a remarkable finding of the highest in the work. The Se-PDA showed distinct sharp peaks at
room temperature ionic conductivity, achieving 2.41 × 10−3 S certain degrees, confirming successful Se doping on P-PDA
cm−1 at 30 wt % of ammonium iodides. This result is indicative nanoparticles. Additionally, XPS results suggested that PDA’s
of the impactful role of salt concentration on ionic strong chelating properties may be responsible for the
conductivity. A meticulous evaluation of the polymer-salt interactions between Se ions and P-PDA, a finding crucial
interaction revealed a significant interaction with NH4I salt, for understanding the mechanism underlying the observed
which was instrumental in increasing the O−H band, performance improvements. The study also reported improved
indicating a noteworthy interaction with the biopolymer water dispersibility and homogeneity with PEG-NH2 function-
chain oxygen atoms. This aspect demonstrated the essential alization and Se doping, resolving the issue of partial water
role of NH4I in the enhanced conductivity of the blended solubility of PDA nanoparticles, a critical factor for ensuring
biopolymer electrolyte. It was established that the system’s uniform application and consistent performance of the
conductivity heightened with the increase in temperature, modified electrolytes in QDSSCs. For future work, it would
reaffirming the Vogel−Tammann−Fulcher relation and be imperative to explore the environmental footprint of using
uncovering an activation energy of a low 0.010 eV for the PDA-based additives and Se doping in polysulfide electrolytes.
highest conducting sample. Future research could delve into Further research could also focus on the optimization of the
the potential optimization of the biopolymer blend ratios and PDA and Se concentrations to enhance both the efficiency and
the concentration of NH4I to enhance the electrolyte’s stability of QDSSCs even further.
conductivity and overall efficiency. The work by Yuan et al.121 scrutinizes the development and
In the work by You et al.,119 the utilization of a biopolymer assessment of advanced biobased polythiophenes (PTs) for
heparin sodium (HS) interfacial layer to enhance the efficiency enhancing organic solar cells (OSCs) efficiency. The work
and longevity of methylammonium lead trihalide (MAPbI3) discusses the introduction of new PTs (P5TCN-Fx) with
perovskite solar cells is meticulously analyzed. The HS layer’s cyano-group substitutions and varying fluorination degrees for
application evidently mitigated the traps at the perovskite-TiO2 heightened efficiency in OSCs. The cyano-group awards PTs
cathode interface, resulting in a significant boost in power deep energy levels, and backbone fluorination elicits robust
conversion efficiency from 17.2% to a commendable 20.1%. interchain interaction, leading to a marked polymer crystal-
Remarkably, the HS interfacial layer’s role in retarding device linity improvement. Significantly, several PTs have registered
degradation is clear, with devices maintaining 85% efficiency over 16% efficiency in binary OSCs, with a noteworthy 17.2%
Energy Fuels 2024, 38, 1593−1617
power conversion efficiency (PCE) observed for P5TCN-F25 into understanding the ion dynamics and electrode/electrolyte
via a ternary blend design. This progress is underscored by a interplay could unearth avenues to bolster the electrochemical
comparison of the synthetic complexity (SC) and the number- stability and overall performance of such advanced biobased
average molecular weights (Mn’s) of the polymers. P5TCN-Fx polymers for energy storage applications.
shows a lower SC (49.2%) than other studied polymers and The work by Dannoun et al.124 delves into the use of
Mn’s ranging between 70 and 96 kDa, indicating efficient and plasticized proton conducting polymer composite (PPC) for
stable polymer structures. Despite the decline in solubility after advancing supercapacitors, addressing the inefficiencies
fluorination, all PTs remain adequately soluble for solution associated with polymer-based electrolytes. The exploration
processing from common organic solvents. The study reveals and analysis of a blended methylcellulose and dextran solution
an increase in thermal stability (above 430 °C) and melting impregnated with ammonium thiocyanate and zinc metal
and crystallization temperatures, showcasing the polymers’ complex have yielded notable results. The ionic conductivity of
suitability for long-term OSC operation. However, it is worth the resultant system was recorded at a notable 3.59 × 10−3 S/
noting the decreased homologous orbital (HOMO) energy cm. The study’s methodological approach, involving various
levels with increased fluorination and a discernible aggregation analyses like transference number measurement and electro-
at room temperature, particularly for higher fluorinated chemical impedance spectroscopy, has robustly supported
versions (P5TCN-F35 and F50). These polymers require these findings. Moreover, the glycerol plasticizer shown to
elevated temperatures (55 and 65 °C, respectively) for enhance transport possesses an ionic mobility of 5.77 × 10−5
deaggregation. In terms of future research, exploring the cm2 V−1 s−1 and a diffusion coefficient of 1.48 × 10−6 cm2 s,
nuanced interplay between fluorination degrees and the supporting an overall carrier density of 3.4 × 1020 cm−3.
resultant polymer properties will be crucial. This includes a Additionally, the linear sweep voltammetry results indicate
deeper investigation into the balance between solubility, stability up to 2.05 V, underscoring the material’s suitability for
thermal stability, and energy levels to further optimize PTs energy devices. The absence of Faradaic peaks in the cyclic
for enhanced OSC efficiency while maintaining cost-effective- voltammetry plot and the low equivalence series resistance of
ness and long-term operational stability. 65 Ω reported in the galvanostatic charge−discharge experi-
In the work by Abdulwahid et al.122 on advanced biobased ment further reinforce the potential of PPC in the enhance-
polymers for energy, the use of potato and chitosan starch, ment of energy devices, showing average energy density and
doped with NH4SCN as the host electrolyte, portrays an specific capacitance of 15 Wh/kg and 128 F/g respectively.
innovative approach to developing electrochemical energy Future research could delve deeper into optimizing the ionic
storage devices. The researchers produced novel plasticized conductivity and enhancing the overall electrochemical
solid biopolymer electrolytes with nontoxic glycerol, which stability beyond the reported 2.05 V.
were used as mediators in electric double-layer capacitor The work by Monisha et al.125 explored the development of
(EDLC) applications. This methodology significantly reduced a proton-conducting solid biopolymer electrolyte by employing
crystallinity, as confirmed by XRD patterns, enhancing the ion a solution casting technique. They utilize cellulose acetate
conductivity (1.62 × 10−3 S cm−1) and large electrochemical (CA) and ammonium thiocyanate (NH4SCN) for the creation
potential stability (2.1 V), especially for the PSBE composition of the polymer electrolyte. Their comprehensive XRD analysis
with 24 wt % Gly. However, ion movement restrictions were significantly highlights an increase in the amorphous nature of
observed for Gly-loaded samples (32 and 40 wt %), impacting the CA complex with an escalation in NH4SCN salt
ion transport and conductivity negatively. The assembled concentration, leading to higher ionic conductivity. Further,
EDLC device displayed a specific capacitance of 16.1 Cspc F/g the work documents the testing of electrical conductivity using
at a 10 mV/s scan rate, exhibiting stable and high performance an AC impedance analyzer, showcasing an increase in ionic
over 2500 cycles. conductivity with heightened salt concentration up to
In the critical examination by Aziz et al.123 on the MC:Dex 50CA:50NH4SCN, which exhibits a maximum ionic con-
polymer blend electrolyte system with NH4I salt for EDLC ductivity value of 3.31 × 10−3 S cm−1. The detailed
applications, notable results and techniques unfold. The XRD electrochemical impedance spectroscopy analysis bolsters
and FTIR analyses unveiled the complexation of MC:Dex these results, emphasizing a decline in resistance from 924 to
polymer blend and NH4I salt, with a discernible decline in 8.6 Ω with increased NH4SCN concentration. Such technical
crystallinity upon increasing salt concentration. Remarkably, aspects underscore the potential application in developing fuel
the electrolyte composition with 40 wt % NH4I showcased an cells and primary proton batteries. Additionally, the authors
apex in ionic conductivity at 1.12 × 10−3 S/cm and a stability provide an insightful observation regarding the
window of 1.27 V, presenting itself as predominantly ionic. 50CA:50NH4SCN polymer electrolyte, which displays the
These outcomes highlight its potential for high-performance highest ionic conductivity (3.31 × 10−3 S cm−1) at room
EDLCs. The EDLC, equipped with activated carbon electrodes temperature, significantly outperforming pure CA (1.285 ×
and utilizing the highest-conducting electrolyte system, 10−7 S cm−1). This notable finding is attributed to the
exhibited an initial specific capacitance of 79 F/g, an energy transition from a semicrystalline phase to an amorphous phase
density of 8.81 Wh/kg, and a power density of 1111.1 W/kg at of the polymer complex, combined with an increase in charge
a current density of 0.2 mA/cm2. The electrochemical stability carrier concentration.
assessment of the MC:Dex:NH4I system under the LSV The research by Harikumar and Batabyal126 portrayed a
method underscored its stability up to 1.27 V, aligning it as apt novel study into creating a flexible, transparent, and
for proton-based energy devices. Despite these advancements, biodegradable supercapacitor electrode using a pectin bio-
the EDLC performance observed a diminishing trend in polymer and a biocompatible electrolyte. The work compre-
prolonged cyclic tests. For future research, the exploration into hensively explored pectin biopolymer-based electrodes due to
enhancing the cyclic durability of the EDLCs developed with their stability and specific capacitance. Notably, the pectin
this electrolyte system would be paramount. Diving deeper electrode with 10% graphite retained an impressive 98.74%
Energy Fuels 2024, 38, 1593−1617
Figure 1. Biobased polymers process in the fuel industry.
capacitance after 2500 cycles at 11.48 mF/cm2, showcasing its role in enhancing the production process of biofuels is
potential for enduring efficiency in energy storage. Moreover, prominent. The contribution of these polymers to the efficient
the specific capacitances of supercapacitors, especially the PP conversion of biomass into fuel is being acknowledged,
supercapacitors, displayed encouraging results, showing 7.25 underscoring their critical role in promoting the production
and 4.64 mF/cm2 specific capacitance at 10 and 100 mV/s of environmentally friendly fuels. The promising potential of
respectively with a notable capacitance retention of 86.8%. In these polymers to improve and increase the output of biofuel
terms of technical highlights, the methodological use of EDX production is being recognized, opening new avenues for
and elemental mapping is crucial for showcasing a uniform sustainable fuel production and environmental protection.
distribution of various elements, aiding the establishment of Among these biobased polymers, cellulose, PHA, and PLA are
the most effective supercapacitors. The work commendably particularly notable for their roles in fuel industry applications,
indicates the enhanced ionic movement during charging and offering innovative pathways in producing sustainable fuels.
discharging to maintain the GCD shape after numerous cycles. A growing usage of biobased polymers in biofuel production
For future research, the practical application of these advanced processes is being witnessed. The polymers are aiding in
biobased polymer supercapacitors should be a primary focus. developing efficient and advanced biofuel production tech-
This includes testing under various environmental and nologies. Their use in the production process enhances the
operational conditions to ensure versatility and reliability. overall efficiency, thereby contributing to the increased
Furthermore, refining the graphite-to-pectin weight ratios and production of sustainable fuels. These advancements are vital
exploring alternative biocompatible materials can unearth more in promoting ecofriendly fuels and addressing global energy
optimized solutions for sustainable and efficient energy storage demands without harming the environment. The practical
systems, contributing to the advancement of ecofriendly applications of biobased polymers in fuel production processes
technology in the energy sector. showcase their substantial impact on the industry. Innovative
In conclusion, the comprehensive investigation of energy- biofuel production methods and technologies are being
related advanced biobased polymer case studies elucidates the developed, credited to integrating these polymers. The
paramount importance of these materials in enhancing the advancements include enhanced production efficiency, in-
performance and sustainability of energy devices. The revealed creased output, and improved environmental sustainability.
advancements pave the way for further research, aiming to Promoting these advancements by biobased polymers is
optimize and expand the utilization of biobased polymers, essential in establishing a solid foundation for sustainable
fortifying their crucial role in the future of sustainable energy fuel production, highlighting their crucial role in the industry.
solutions. Furthermore, the role of biobased polymers in fuel
4.3. Biobased Polymers in the Fuel Industry. A production is not limited to biofuels. These polymers
substantial contribution is being made by biobased polymers significantly contribute to other sustainable fuel production
in developing sustainable fuels.18,127,128 Figure 1 shows the processes, including creating hydrogen fuel and other
biobased polymer process in the fuel industry. Extracted from alternative, sustainable fuel sources.132,133 Specifically, bio-
biological sources, these polymers align with environmental based polymers like cellulose and lignin-derived materials are
sustenance.129 The in-depth exploration of biobased polymers’ instrumental in the catalytic processes crucial for hydrogen
roles in sustainable fuel production and enhancement is production, enhancing hydrogen generation efficiency from
presented in this section, illuminating their fundamental biomass. Additionally, these polymers contribute to developing
contributions and future prospects. The biobased polymers, advanced bioelectrochemical systems, enabling more effective
derived from renewable biological resources, are marking a energy extraction from alternative sustainable fuels and thus
crucial shift toward sustainable fuel production.18,130,131 Their broadening the scope of their application in the energy sector.
Energy Fuels 2024, 38, 1593−1617
The impact of biobased polymers on these alternative fuel meticulously discussed. A notable highlight is the discernible
production methods is being realized, supporting the increase in HBME yield, rising from 12.8 to 70.7% with a
continued growth and advancement of sustainable fuel reaction time increase from 10 to 50 h. The document lays a
technologies and promoting environmental sustainability. In foundation demonstrating the influence of diverse factors such
summary, it has been demonstrated that biobased polymers as reaction time, temperature, and catalyst type on the yield of
play an indispensable role in the evolution of the fuel industry. HAME-based biofuels. The presence of low cetane numbers
Their contributions, extending beyond biofuel production to and high heat of vaporization in oxygenated additives like HA
encompass alternative sustainable fuel sources, including esters may pose challenges in diesel engine fuelling.
hydrogen fuel, are pivotal in the transition toward a more The work by Akinwumi et al.135 addresses the production
ecoconscious energy sector. Incorporating these polymers not and utilization of PHA-based biofuels, analyzing their pros,
only enhances the efficiency and output of biofuel production cons, and commercial viability. The PHA methyl esterification
but also signifies a leap forward in environmental stewardship. process, used to produce biofuels like 3HBME and 3HAME, is
4.4. Case Studies of Biobased Polymers in the Fuel examined for its sustainable and petroleum-free approach. The
Industry. In pursuing ecofriendly alternatives within the fuel work reveals that despite low octane and cetane numbers,
industry, significant emphasis has been placed on developing which hinder performance, alternative PHAs with longer
and assessing biobased polymers. Various case studies in this carbon lengths may provide improved biofuel qualities. This
section rigorously investigate the efficient conversion of feature is critical for advancing biobased polymers in the fuel
biomass and biopolymers into sustainable fuels, showcasing industry, indicating a need for more extensive research on
innovative methods and catalysts that have the potential to various PHA types and their corresponding biofuel character-
revolutionize the fuel industry. istics. The work uncovers crucial data, such as the significant
The work by Liu et al.134 offers a comprehensive increase in combustion heat when 3HBME and 3HAME are
investigation into the production of high-density aviation fuel blended with ethanol, demonstrating the potential efficacy of
from cellulose, a bountiful, nonedible biomass. The process these biofuels. However, it also highlights the issues of high
involves converting cellulose to 2,5-hexanedione with a yield of production costs, estimated at $1,200/ton, which could limit
71.4%, followed by obtaining a mixture of C12 and C18 the broad-scale application of this technology. The detailed
branched polycycloalkanes with a carbon yield of 74.6% using analysis of HBME as a potential fuel additive is noteworthy,
the aldol method. The polycycloalkane mixture demonstrated emphasizing its superior flashpoint, oxygen content, and
low freezing points and high density, marking its potential as temperature properties compared to ethanol. Despite these
an advanced aviation fuel. The article underscores the positive aspects, the low octane and cetane numbers and
utilization of HCl and Pd/C for cellulose hydrolysis and potential phase separation issues underscore the need for
hydrogenation, attaining a carbon yield of 64.2% under specific further development and optimization of PHA-based biofuels.
conditions. The study further explores the effectiveness of the In addressing the production process, the work reports on the
HCl + Pd/C catalyst in the hydrogenolysis of other effectiveness of both acid and alkali catalysts in PHA
carbohydrates, achieving carbon yields ranging from 40.4% to conversion to biofuels. The elucidation of the method
74.0%. Further research could focus on exploring alternative involving chloroform solvent, methanol, and acid or base for
catalysts and methods that may enhance the overall efficiency esterification at 67 °C for 50−100 h is meticulously outlined.
and sustainability of the fuel production process. In the context Explaining the subsequent processes, such as the separation
of producing high-density polycycloalkanes, the work presents and vacuum evaporation, adds depth to understanding the
the efficacy of both pure and metal-modified MgO as catalysts, biofuel production methodology. Furthermore, the work sheds
achieving a conversion of 99.1% and a carbon yield of 98.3%. light on the comprehensive characterization of PHA-based
The bimetallic Cu-Ni/MgO-p catalysts showcased the highest biofuel, elaborating on its physicochemical properties,
total carbon yields, indicating their superior performance in including dynamic viscosity, flashpoint, and oxygen content.
producing C12 and C18 oxygenates. For future research, The comparison with petrol, ethanol, and diesel strengthens
exploring more environmentally benign catalysts and further the argument for the potential use of HBME as a fuel additive
optimizing the fuel production process, focusing on max- despite the highlighted challenges, such as its lower cetane
imizing yield while minimizing environmental footprint, number and research octane number, necessitating additives.
remains paramount. The work by Xu et al.136 provides a comprehensive
The work by Riaz et al.18 posits a novel exploration into the exploration into the solvent-free catalytic hydrogenolysis of
potential of PHAs in biofuel production. These bacterial PLA powder. Achieving a 100% conversion with a carbon
polymers exhibit versatility and compatibility for methyl utilization of 99%, the study presents an ecofriendly and
esterification, making them suitable candidates for biofuel efficient process. The fuel produced exhibited an HHV of 29.9
production, akin to biodiesel but with higher oxygen content MJ/kg, and the carbon recovery for discarded PLA straws was
and absent nitrogen or sulfur. The work delineates the reported to be 95%. One significant aspect is the meticulous
production of hydroxyalkanoates methyl ester (HAME) and scrutiny of reaction temperatures to optimize the hydro-
hydroxybutyrate methyl ester (HBME) from PHAs, showcas- genolysis process. The decomposition temperature of PLA,
ing a promising path for sustainable fuel generation. Notably, which was affected by the addition of Pd/C, lowered to 351
the work highlights a significant increase in combustion heat by °C, underscoring the catalytic effect on the degradation of PLA
30% when HBME was blended with ethanol. The essential powder. A careful selection of the reaction temperature range
point is that the work asserts that these PHA-based biofuels do (170−300 °C) was employed, ensuring the complete
not necessitate significant purification, suggesting a possible conversion of PLA powder, yielding mainly light-yellow liquid
cost-effective production pathway, utilizing wastewater as a products and CO-enriched gas. The extensive experiments
source, thereby negating competition with food resources. indicated that hydrogen pressure was pivotal in enhancing the
Furthermore, the optimization of the production parameters is liquid product yield, from 69.6 ± 6.2 wt % to 93.9 ± 5.7 wt %
Energy Fuels 2024, 38, 1593−1617
upon increasing H2 pressure. This indicates the potential HMF yield when using microwave-assisted heating compared
scalability and reliability of this method. Furthermore, utilizing to conventional oil-bath heating, and it elaborates on a detailed
different catalysts besides Pd/C, such as Raney Co, Raney Ni, mechanism for the isomerization of glucose into fructofur-
and Cu/Zn/Al, underlines the versatility of the hydrogenolysis anose, followed by the production of HMF, further solidifying
process. The liquid products derived exhibit a considerable the study’s comprehensiveness. The recycling aspect of
HHV of 29.9 MJ/kg, highlighting their practical utility in the Zr(O)Cl2 catalyst, which sustains activity across five cycles
fuel industry. Future research could delve deeper into with only a 4% loss, is a promising finding for sustainable
enhancing the hydrogenolysis process by exploring novel biofuel production. Yet, the formation of CMF and LA as side
catalysts that could optimize the reaction conditions and products indicates potential avenues for optimization to
product yield. enhance the yield and purity of HMF. For future research,
Tseng et al.137 examined the biological decomposability of exploration into the anomalies in the catalytic effectiveness
PLA by thermophilic methane fermentation (TMF) and related to pH and different metal chloride catalysts is essential
analyzed the microorganisms involved in PLA decomposition. to optimize the process further. It would also be valuable to
The research utilized disposable cutlery and pure poly L-lactic investigate the intricate impact of various solvents and heating
acid (PLLA) pellets for both small and large-scale batch tests, methods on the HMF yield and potential ways to mitigate side
observing a 70−77% decomposition of PLA by TMF based on reactions that result in CMF and LA, ensuring a more efficient
weight changes, and CH4 yield ranged from 321−343 mL and sustainable biofuel production using biobased polymers.
CH4/g PLA consumed, a significant figure underscoring the The study by Cheng et al.139 on the synthesis of five
potential for methane production from PLA. The study Brønsted-Lewis acidic ionic liquids and their use in converting
identified a considerable role of microbial activity, specifically cellulose to levulinic acid (LA), a key intermediate in the fuel
lactic acid-consuming bacteria, in enhancing PLA decom- industry. The cellulose to LA conversion, in pure water
position doubling the physicochemical degradation rate. The without additives at 180 °C for 10 h, yielded over 49% more
research unveiled that Methanothermobacter, a hydrogenotro- LA than utilizing Brønsted-Lewis IL [HO3S-(CH2)3-py]Cl-
phic methanogen, was the primary archaea in methane FeCl3, highlighting the efficiency and potential ecofriendliness
production from PLA degradation. The bacterial microflora of this method. Despite the formation of some solid residues,
involved in the depolymerization of PLA and/or degradation identified as benzene or amorphous fused benzene rings, the IL
of LA were also analyzed, and bands such as B1, B7, B8, and reusability and catalytic performance remained consistent after
B9 were identified as dominant in the PLA decomposition five reuses, an essential factor for sustainable and practical
process by TMF. The bacterial genera involved included application in industry. The study’s methodologies are
Defluviitoga, Anaerosalibacter, Tepidimicrobium, and Jonquetella. thoroughly outlined, including the preparation of the
Interestingly, bands B2 and B3, associated with genera Brønsted-Lewis acidic IL and the testing of its catalytic
Streptococcus and Tumebacillus, were observed to become properties. The results show that the synthesized ILs had Lewis
dominant during PLA degradation, although they had not been acidic centers, with ZnCl2 being the strongest, followed by
previously reported in PLA degradation, indicating potential FeCl3, CuCl, and CrCl3. A cellulose conversion exceeding 70%
new pathways for PLA decomposition. The exploration of and the highest LA yield of 57.6% were achieved, supporting
carbon-13 isotope tracing in future studies is poised to the efficacy of the Brønsted-Lewis acidic ILs in cellulose to LA
elucidate the production of CH4 and CO2 from PLA conversion. Furthermore, the IL [HO3S-(CH2)3-py]Cl-FeCl3
decomposition, and the isolation and evaluation of Tepid- showed the best catalytic performance among all investigated,
imicrobium’s LA-consuming ability will fortify the findings of with cellulose conversion at 71.4% and LA and glucose yields
this study. The efficient PLA treatment by TMF is emphasized, at 49.1% and 10.2%, respectively. Future research in this area
and the critical role of microbial activity in this process is could focus on optimizing IL structures for maximized LA
unambiguously highlighted, proposing a potential sustainable yield and cellulose conversion.
avenue for biofuel generation from biobased polymers. Further The work by Khan et al.140 offers several valuable insights
research into the precise microbial pathways and mechanisms, and findings in the realm of sustainable technology. The
along with the optimization of TMF for PLA degradation, research focuses on utilizing cellulose for the production of
stands out as a crucial future direction to enhance the viability levulinic acid (LA) through the use of dicationic ionic liquids
of this biotechnological approach for sustainable biofuel as a catalyst. Notably, a significant catalytic activity for cellulose
production. to LA conversion was achieved with [C4(Mim)2][(2HSO4)-
The study by Saha et al.138 stands out for exploring Lewis (H2SO4)2], showcasing a 55% conversion rate at 100 °C within
acidic metal chlorides in producing biofuel precursor, 5- 3 h, without requiring an additional catalyst or solvent. This
hydroxymethylfurfural (HMF), from carbohydrates and aspect underscores the potential efficacy and efficiency of the
biopolymers. The research reveals the superiority of Zr(O)Cl2 utilized ionic liquids, contributing positively to the sustain-
as a catalyst, achieving 63% and 42% HMF yield from fructose ability and feasibility of the method. The research also provides
and glucose, respectively, in a water-MIBK biphasic solvent a profound insight into the influence of factors such as IL type,
system. This yield is impressively heightened to 84% and 66% amount, temperature, and reaction time on catalytic con-
in a [BMIM]Cl-MIBK biphasic solvent, showcasing the version, thereby ensuring a comprehensive exploration of the
impactful role of solvents in catalytic efficiency. However, subject. The experiments performed at varying temperatures
although thoroughly investigated, pH’s impact on the catalytic between 80 and 120 °C revealed an optimal yield at 100 °C,
process demonstrates some ambiguity. Despite the lower pH of emphasizing the importance of temperature control in
Zr(O)Cl2 leading to higher HMF yields, the trend does not enhancing the LA yield.
consistently follow for all metal chloride catalysts. This In sum, the meticulously conducted case studies demon-
suggests that other unaccounted factors could be influencing strate significant advancements in biobased polymer con-
the catalytic effectiveness. The work emphasizes the superior version for fuel production. Despite the promising results,
Energy Fuels 2024, 38, 1593−1617
several research gaps and opportunities for optimization and In summary, from optimizing renewable energy production
enhancement are highlighted. Continual exploration in this and consumption to ensuring the peak performance of energy
realm is vital for realizing more sustainable and efficient fuel storage systems and from refining energy conversion processes
production processes using biobased polymers, contributing to advancing the development and integration of biobased
substantially to global environmental conservation efforts. polymers, ML has emerged as a critical ally in the global
4.5. ML in Energy Systems. In recent years, a marked pursuit of a more efficient, sustainable, and ecofriendly energy
advancement in ML application in energy systems has been future. The continued exploration and harnessing of its
observed.141,142 Significant enhancements in the efficiency and immense potential are paramount to realizing these global
sustainability of these systems have been realized by harnessing aspirations, reaffirming the indispensability of ML in the
the predictive and analytical capabilities of ML algo- evolution of energy systems toward unparalleled efficiency and
rithms.141,142 The optimization of renewable energy produc- sustainability.
tion, particularly from solar and wind sources, stands as a 4.6. ML for Fuel Development. In the ever-evolving
striking illustration of this trend.143,144 Real-time data are landscape of fuel development, the substantial influence of ML
analyzed to predict energy output, allowing for more efficient is being acknowledged.14,150 A significant surge in efficiency,
grid integration and energy distribution.145 This analysis sustainability, and innovation in fuel development is being
primarily utilizes data such as weather forecasts, historical observed, owing to the integration of advanced ML
energy usage patterns, and real-time sensor readings from algorithms.67 An exploration into the multifaceted impact of
energy generation equipment. Moreover, the capacity for ML on fuel development is explored in this section,
accurate energy consumption forecasting by industries and underlining its pivotal role in reshaping and enhancing the
households has been augmented. This improvement enables industry.
more effective demand-side management and aids in The enhancement of fuel development processes is seen as a
minimizing energy wastage, underscoring the crucial role direct consequence of ML.151,152 By processing vast data sets
played by ML in bolstering the efficiency and sustainability of and deriving actionable insights, ML is aiding in the
energy systems.146 optimization of fuel production processes.14 These advance-
The domain of energy storage, too, has been positively ments result in heightened efficiency, thereby reducing
impacted by the integration of ML.75,76,78 Enhanced perform- resource utilization and promoting environmental sustain-
ance and lifespan of batteries are achieved through the real- ability. Furthermore, the role of ML in the predictive
time analysis and monitoring facilitated by ML, ensuring maintenance of fuel production machinery is being realized,
optimal functioning and reliability of energy storage systems. preventing unforeseen downtime and ensuring consistent and
These improvements are largely attributed to predictive optimal production.153,154 The technology is enabling the rapid
maintenance strategies, where ML algorithms anticipate development and testing of novel fuel formulations, contribu-
maintenance needs and schedule interventions to prevent ting to the emergence of more efficient and environmentally
failures. Additionally, degradation modeling of battery friendly fuel alternatives. The ability of ML algorithms to
components, enabled by ML, aids in understanding and analyze and model complex chemical reactions is being
mitigating wear and tear, further enhancing lifespan and leveraged, resulting in the accelerated discovery and develop-
performance. Strategies for effectively managing and maintain- ment of new fuels.98,155 This innovative approach drives the
ing these systems have been formulated, leading to substantial industry forward, ensuring it stays abreast of the growing global
improvements in their overall efficiency and longevity. These energy demands while maintaining sustainability.
advancements resonate with the global impetus toward Moreover, the integration of ML in fuel development is
bolstering the efficiency and sustainability of energy systems promoting sustainability.156 Through the optimized use of
by leveraging cutting-edge technologies, exemplified by the resources and enhanced production efficiency, ML is
integration of ML. contributing to the reduction of the environmental impact of
Moreover, in the field of energy conversion, ML has fuel production. It aids in the development of cleaner, more
emerged as a transformative tool.79,147,148 It aids in the sustainable fuels by analyzing and predicting the environmental
refinement and optimization of energy conversion processes, impact of various fuel types, thereby guiding the industry
ensuring maximized output and minimized waste. The fine- toward more ecofriendly alternatives.157,158 This commitment
tuning of these processes, facilitated by ML, underscores its to sustainability is crucial in addressing the urgent global
pivotal role in enhancing the efficiency and sustainability of environmental challenges faced today. In conclusion, the
energy conversion systems. Furthermore, its application in the incorporation of ML within the realm of fuel development is
assessment and optimization of novel energy conversion bringing forth substantial advancements in efficiency, sustain-
technologies expedites their development and integration ability, and innovation. Its role in enhancing and optimizing
into the existing energy infrastructure. This dynamic illustrates fuel production processes, promoting the discovery of new
the substantial contribution of ML in advancing the efficiency fuels, and guiding the industry toward ecofriendly alternatives
and sustainability of energy conversion systems. In the realm of highlights its crucial significance in the ongoing and future
enhancing biobased polymers for energy applications, ML has developments within the fuel industry. The sustained
displayed a substantial capacity for innovation. It has facilitated exploration and integration of ML within the industry hold
the rapid, efficient design and assessment of biobased polymers the promise of a more efficient, innovative, and sustainable
for diverse applications in renewable energy systems, energy future for fuel development.
storage, and energy conversion.27,149 This accelerated develop- 4.7. Case Studies of ML Applied in Biopolymers for
ment and optimization process ensures the timely integration Fuel Development and Energy applications. 4.7.1. ML
of these ecofriendly and efficient materials into the energy Applied to Biopolymers for Energy Applications. In the
landscape, further augmenting the sustainability and efficiency exploration of biopolymers for fuel and energy applications,
of energy systems globally. ML emerges as a paramount tool. Significant advancements are
Energy Fuels 2024, 38, 1593−1617
Figure 2. ML enhancement process of biopolymer in energy applications.
realized in fuel development, with ML optimizing biopolymer- interaction dynamics, helping to visualize the parameter
based solid polymer electrolytes, enhancing fuel cell perform- synergy, a crucial aspect for material engineers. One significant
ance, and predicting ionic conductivity within biopolymer highlight is the demonstrated accuracy of the ANN model in
electrolytes for zinc-ion batteries. This section meticulously predicting ionic conductivity and potential window with high
discusses various case studies to delineate the impact and R2 values of 0.999 and 0.998, respectively, showing a minuscule
potential of ML in biopolymer research for fuel and energy error margin. This accuracy is a compelling achievement in the
applications. Figure 2 shows the ML enhancement process of realm of SPEs, as it provides a robust model for further
biopolymers in energy applications. experimental designs. Future research could be directed toward
The study by Adam et al.159 embarks on the optimization of understanding the mechanical properties of these SPEs and
cellulose and its derivatives-based solid polymer electrolytes their compatibility with other materials for diverse energy
(SPEs), leveraging ML. The research employs response surface applications. This could pave the way for the development of
methodology (RSM) and artificial neural networks (ANNs) for more efficient and sustainable energy storage devices employ-
predicting and optimizing PC/MC-based SPE complexed with ing biopolymers. In essence, the work stands out for its in-
potassium phosphate (K3PO4) and glycerol. The study reveals depth analysis, the employment of ML tools, and clear,
significant influences of K3PO4 and glycerol on SPE’s ionic demonstrable results, setting a precedent for future research in
conductivity and potential window, especially with higher the realm of biopolymer-based SPEs for energy applications.
potassium salt content. An optimal interaction of ∼3 × 10−4 S The work by Tian et al.160 presents a significant stride
cm−1, 4.19 V is achieved at 60 wt % K3PO4 and 41.37 wt % toward enhancing the efficacy of polymer electrolyte
glycerol, revealing effective numerical optimization. The membrane (PEM) fuel cells. The work adeptly combines
research provides a detailed insight into the role of each ANN and genetic algorithm (GA) to forecast and augment
variable, showing limited effects at low concentrations while PEM fuel cell performance. Leveraging a robust 3D multi-
pointing out the increasing ionic conductivity with a surge in physics model, the work meticulously trains the ANN, yielding
salt concentration. This aspect is crucial as it highlights the a prediction error below 2.5% and 1.5% under varying current
interplay of these materials in enhancing ionic conductivity. densities. The authors reveal a peak power of approximately
The effectiveness of glycerol and K3PO4 in impacting the ionic 0.78 W/cm2 at 368.8 K, achieved using the ANN-GA method,
conductivity and potential window is meticulously analyzed, a pivotal insight for practical system design and expeditious
giving readers a profound understanding of their roles and control in fuel cell applications. The examination of diverse
interactions. It is intriguing to note the linear correlation in the operational temperatures also provides essential perspectives
residuals of the two models, indicating a normal distribution of on fuel cell performance. The work establishes a nonlinear
errors. In addressing ionic conductivity, the research relationship between temperature and maximum power,
demonstrates the minimal impact at low K3PO4 concen- further underlining the temperature’s critical influence on
trations, a crucial observation for practical application. It fuel cell output. Notably, a maximum power increase is
portrays the intricate relationship between K3PO4 and glycerol, identified until around 363−373 K, after which a subtle decline
signifying their significant interaction in the PE. The detailed is observed. Such granular insights, notably the detailed
analysis using contour plots splendidly illustrates the analysis of relative humidity impacts on anode and cathode
Energy Fuels 2024, 38, 1593−1617
sides, offer substantial contributions to fuel cell operational within the realm of materials engineering for energy
understanding. The work demonstrates a thorough approach, applications. Future research could potentially delve deeper
utilizing the ANN-GA framework to confirm results with the into enhancing the algorithm’s predictive capabilities and
3D multiphysics model, showcasing robust alignment and exploring additional biopolymer candidates for diversified
underscoring the ANN-GA’s prediction accuracy. In practice, energy storage solutions.
the model enables swift adjustments to alterations in The insightful case studies accentuate the indispensable role
environmental temperature, a crucial capability for real-world of ML in advancing biopolymer research for fuel and energy
fuel cell applications. For future work, it would be interesting applications. These investigations not only highlight the
to delve deeper into exploring the impacts of varying optimization and prediction capabilities of ML models but
environmental factors and their intricate interplay on the fuel also pave the path for future endeavors. Evidently, ML stands
cell performance and how the ANN-GA model can be further as a robust ally, promising enhanced efficiency and innovation
optimized to adapt to these multifaceted conditions. in biopolymers for fuel development and diverse energy
The work by Jha et al.161 predicted the capacitance variation applications.
of lignin-based supercapacitors. The work has adroitly utilized 4.7.2. ML Applied to Biopolymer Fuel Applications. The
four ML algorithms, including linear regression (LR), support surge in environmental concerns has necessitated innovations
vector machine (SVM), decision tree (DT), and ANN, ranking in sustainable energy, with particular emphasis on biopolymer
their accuracy as LR < SVM < DT < ANN. This is validated fuels. The section illuminates the intersection of ML and
using the F-test, wherein ANN emerges as the most precise, biopolymer fuel applications. Herein, pioneering strides are
reliable, and robust model, capable of anticipating specific expounded upon, providing a compelling narrative on the
capacitance variation even for material ratios not in the training optimization of lignin depolymerization and hydrothermal
set. In their methodology, the data set is divided into 80% for liquefaction using sophisticated ML models.
training and 20% for validation, which prevents model The work by Liu et al.163 is an exhaustive exploration into
overfitting, ensuring higher prediction accuracy for optimal the optimization of lignin depolymerization, focusing on
material weight percentage and specific capacitance (SPC) influencing factors for enhancing yields of bio-oil and high-
variation. The ANN model’s superior performance is evident value aromatic products through lignin hydrogenolysis. The
with the lowest root mean square error (RMSE) deviations of study effectively utilizes ML models, namely xgboost, to
0.234, 0.240, and 1.384 mF cm−2 for SC1, SC2, and SC3, simulate and predict optimal reaction parameters. The R2
despite training with reduced data. ANN’s models for SC1 and scores reflecting the reliability of these models are notably
SC2 displayed impressive R2 values of 0.676 and 0.979 and high, 0.92 for solid residue and 0.88 for aromatic yield,
RMSE values of 0.209 and 0.234, respectively. Furthermore, revealing a strong reliability in predictions. Crucially, the
the ANN model predicts capacitance retention with significant research highlights the paramount impact of the lignin-to-
accuracy, reflecting an understanding of nonlinear systems solvent ratio and average pore size on lignin hydrogenolysis
unattainable by parametric modeling. Further exploration of results. It underscores that an optimal lignin-to-solvent ratio
the ANN’s robustness and accuracy with other biopolymer- hovers around six, while the catalyst’s pore size significantly
based supercapacitors and varying compositions will enhance influences the solid yield, positioning these factors as central in
the understanding and applicability of ML in enhancing energy refining the hydrogenolysis process. Moreover, the ML models
applications of biopolymers. reveal that nickel and ruthenium exert higher effects on the
The work by Wei et al.162 revealed a significant exploration models’ output than other metals. However, the work indicates
into the potentialities of ML for predicting ionic conductivity some limitations in its scope, particularly in the potential
within biopolymer electrolytes for zinc-ion batteries. Utilizing variation of lignin sources, which were not entirely considered
the gradient-boosting decision tree algorithm, the authors in the models. The study’s results are instrumental for
constructed models to predict the contribution of polymer advancing the field, providing clear insights into parameter
functional groups to ionic conductivity, yielding promising and significance, and offering direction for further optimization in
vital results. The synthesized and sulfonated series of cross- industrial applications. Yet, it leaves room for expanding
linked polymers denoted as SPTPT delivered noteworthy research into exploring diverse lignin sources and their distinct
outcomes. The prepared membrane displayed a Zn 2+ impacts on the hydrogenolysis process. Future research can
conductivity of 12 mS cm−1 and a proton (H+) conductivity delve into the comprehensive examination of various lignin
of 22 mS cm−1 in water at 30 °C, marking an encouraging types beyond alkaline and kraft lignin to ensure broader
achievement in the advancement of polymer electrolytes for applicability and robustness in the ML models’ predictive
zinc-ion batteries. The research demonstrated that the Zn/ capabilities for lignin hydrogenolysis.
MnO2 flow battery, utilizing the proposed membrane as the The work by Shafizadeh et al.17 explores the use of ML in
electrolyte, delivered a peak power density of 150 mW cm−2 characterizing and quantifying hydrothermal liquefaction
and a significant specific capacity of 1.95 mAh cm−2. This byproducts. The document provides an insightful analysis,
resulted in a robust cycling capacity retention rate of 71% after demonstrating the application of ML models to optimize the
1000 cycles at 30 mA cm−2, signifying the potential for biocrude oil yield, a significant aspect of fuel development. The
enhanced longevity and reliability in real-world applications. work outlines that the Gaussian process regression (GPR)
Notably, the tpt-SPTPT membrane exhibited exceptional ionic model showed the most promise, with a correlation coefficient
conductivity, offering 17 mS cm−1 to Zn2+ and 42 mS cm−1 to above 0.926 and a mean absolute error below 0.031,
H+ at 80 °C under 100% RH. Moreover, the tpt-SPTPT-based showcasing robust predictive capabilities. The analysis of
Zn/Zn flow battery showcased an admirable corrosion optimal biomass components for the highest biocrude oil yield,
potential increase and reduced overpotential of nucleation, standing at 48.7−53.5%, presents clear, impactful statistics that
highlighting its operational efficiency and stability. These reinforce the work’s findings. It notes optimal conditions for
compelling results underscore the innovative integration of ML biocrude oil production, specifically emphasizing biomass
Energy Fuels 2024, 38, 1593−1617
composition and operational conditions such as temperature application and interpretation of ML could potentially be
(394−400 °C) and pressure (30.0−35.6 MPa). The article also refined. The work states that a reduction in hemicellulose and
elaborates on the process optimization and feature importance lignin to below 10% will result in enhanced yields, confirming
analysis, showing that biomass composition had a more this with glucose yields exceeding 50 g/L and ethanol yields
significant impact on biocrude oil yield (58.18%) compared to over 40 g/L under these conditions. While these numbers are
operating conditions (41.82%). The article further provides compelling, the work could provide more insight into the
practical data on how various factors, such as increasing robustness of the model against varying biomass types and
biomass oxygen over 42%, could detrimentally affect biocrude conditions. The real-world biomass samples might not always
oil yield. These specifics offer crucial insights for practical align with the ideal conditions prescribed, thereby affecting the
implementation, supporting the avoidance of nonoptimal practical applicability of the model’s predictions. A notable
conditions for biocrude production. Future research could strength of the work is the comprehensive 3-D surface analysis,
focus on the development of universal ML models for lending a visual and quantitative dimension to the relation
nonwater hydrothermal liquefaction solvents, a potential area between various factors like cellulose content, temperature,
noted by the authors. The integration of ML in real-time and yield. This kind of multidimensional analysis is pivotal for
monitoring and control of hydrothermal liquefaction reactors, the holistic understanding and optimization of biopolymer
as suggested in the article, could substantially enhance biofuel processing for fuel development. In future research, a more
quality and quantity, presenting an exciting avenue for diverse range of biomass types and real-world conditions
subsequent exploration and development. should be incorporated to enhance the model’s robustness.
In the work by Kartal et al.,27 a novel application of artificial Additionally, the model could be expanded to predict other
neural networks (ANNs) using the TensorFlow library is essential metrics of the biofuel production process.
employed to model the thermal degradation of essential The work by Castro Garcia et al.165 elaborates on the
biomass biopolymers: hemicellulose (HC), cellulose (CL), and underutilized potential of lignin, a significant component of
lignin. With an exceptional R2 value above 0.998, the ANN plant matter, in depolymerization for renewable aromatic
model impressively demonstrates its robustness in predicting chemicals and biofuel production. The research emphasizes
differential thermogravimetric (DTG) curves for HC, CL, and using ML to develop predictive models for bio-oil and solid
lignin, facilitating instantaneous calculation of biopolymer residue yields using limited reaction variables. These models,
fractions in degraded biomass, a feat not previously achieved. A exhibiting an R2 score of 0.83 and 0.76 for bio-oil and solid
meticulous laboratory setup, including precise thermal residue, respectively, were validated through experimental
conditioning and measurement using the NETZSCH STA comparisons. The study emphasizes temperature and reaction
409 PC Luxx, underscores the reliability of the data used for time as critical predictive variables for experimental outcomes.
ML training and evaluation. The neural network topology, The models displayed good performance in predicting bio-oil
incorporating layers with 5, 150, and 100 neurons, yields, with an R2 of 0.836 and RMSE of 10.522, notably at
demonstrates a deft balance between complexity and computa- lower to middle bio-oil yields (20−60 wt %). Key variables
tional efficiency, contributing to the model’s exemplary include reactor volume to H2O volume ratio, ratios of lignin to
predictive performance. In testing, R2 values consistently H2O, lignin to catalyst, temperature, and reaction time.
above 0.998 highlights the model’s excellent generalizability to However, the research revealed the complexity and variability
unseen data, reinforcing its potential for broader application in in the role of these variables, reflecting on the diverse nature of
biomass characterization and fuel development. Notably, the lignin and its solubility, highlighting the challenges in
study reveals subtle variabilities in prediction accuracy among comparing one variable to another within a limited
different biopolymers, with CL showing the most predictable experimental space. The study recommends the establishment
DTG points and lignin the least. The findings suggest a more of concrete guidelines for reporting in lignin depolymerization,
pronounced challenge in estimating lignin thermal degrada- underscoring the critical importance of specific variables like
tion, underscoring an area warranting further research. The the reactor-H2O volume ratio and reaction time and their
innovative application of ANN for the analysis of biopolymer intricate interplay in influencing bio-oil and solid residue
thermal degradation signals a significant stride in enhancing yields. Nevertheless, while the ML models provided significant
the efficiency of biomass-based thermal processes, setting a insights and predictions, deviations in experimental results
firm foundation for the advancement of renewable fuel from model predictions, particularly in bio-oil yield, call for
technologies while also elucidating clear pathways for future careful consideration and further refinement in modeling
research, particularly in the nuanced prediction challenges approaches. For future research, the emphasis should be laid
presented by specific biopolymers such as lignin. on the advancement of ML models to enhance the precision of
The work by Vinitha et al.164 utilizes an ML-based predictions, alongside a more detailed exploration of the key
optimized decision-making system (OD-MS) to enhance the variables and their interactions. The work hints at the need for
yield of glucose and ethanol from biomass. With a substantial a more comprehensive and clearer understanding of lignin’s
data set of 250 experimental results, the study claims a diverse characteristics and behavior in depolymerization
remarkable 95% accuracy in predicting the optimal conditions reactions, as well as the crucial role of reaction variables in
for enzymatic hydrolysis saccharification and fermentation, optimizing bio-oil and solid residue yields for sustainable fuel
achieving an R2 value of 0.97623. The intricate model development.
considers various parameters, such as cellulose content, In conclusion, the exploration of ML in enhancing
temperature, and pH levels, and their influence on yield. For biopolymer fuel applications heralds a promising horizon.
instance, an increase in cellulose (>73%) and specific While significant advancements have been observed, especially
temperature (55−60 °C) and pH (7−9) conditions for in optimizing reaction parameters and understanding biomass
saccharification markedly enhanced the yield. However, a composition, the need for continual refinement in ML models
critical examination of the study reveals areas where the is paramount. The unfolding journey bears potential for a
Energy Fuels 2024, 38, 1593−1617
Figure 3. ML process in biobased polymer for biochemical production.
cleaner and more sustainable energy frontier, driven by a heightened by the incorporation of ML, enhancing their
deeper grasp of biopolymer properties and innovative development and application.168
computational approaches. A diverse array of biobased polymers, such as PLA and
In summarizing the potential of ML in enhancing PHAs, offer unique characteristics that have been extensively
biopolymer fuel applications, it is crucial to acknowledge exploited in the biomedical field.169,170 In the arena of drug
inherent challenges and propose clear future research delivery, the employment of these polymers facilitates the
directions. Implementing ML in this field often encounters controlled and targeted release of pharmaceutical agents.171
obstacles such as the variability of biomass materials, the This capability ensures not only enhanced therapeutic efficacy
complexity of biological processes, and the need for extensive but also minimizes adverse effects. The biocompatibility and
data to train accurate models. These challenges necessitate a biodegradability of biobased polymers remain paramount for
more nuanced approach to data collection and model training, their utilization in medical devices.172 These materials
ensuring that models are both robust and adaptable to diverse underpin the creation of prosthetics, sutures, and various
conditions. Looking ahead, research should focus on other medical implements, underscoring their indispensability
developing universal ML models that can adapt to various in healthcare.173
biomass types and conditions, enhancing the predictive In conclusion, the critical role of biobased polymers in
accuracy for different biopolymers. Additionally, expanding biochemical production and beyond remains unequivocal.
the scope to include real-time monitoring and control in Their beneficial attributes, such as biodegradability and
biopolymer processing using ML can significantly improve biocompatibility, coincide with the global impetus toward
both the quality and efficiency of biofuel production. This sustainability. The intersection of ML technologies further
approach not only addresses current limitations but also sets a emboldens the advancements in biobased polymers, propelling
solid foundation for advancing sustainable fuel technologies, research and development in drug delivery, medical devices,
contributing to a cleaner energy future. and energy solutions. The continual exploration and enhance-
ment of biobased polymers, augmented by ML, signal a
promising trajectory for realizing a sustainable future.
5. BIOCHEMICALS
5.2. Case Studies of Advanced Biobased Polymers for
5.1. Biobased Polymers and Biochemical Production. Biochemical Production. In recent years, advances in
Insights into utilizing biobased polymers permeate various biobased polymer biochemical production have been examined
sectors, particularly emphasizing their crucial role in meticulously. A focus has been laid on optimizing biodegrad-
biochemical production. This critical evaluation elucidates able food packaging materials such as polylactic acid (PLA), its
their multifaceted applications, chiefly in drug delivery and reactions with food simulants, and enhancing its properties.
medical devices. The production of biobased polymers, Additionally, exploring novel materials like Pennisetum
predominantly derived from biological resources, significantly purpureum/Napier cellulose nanowhiskers (NWCs) PHA for
curtails the reliance on fossil fuels.166 Their biodegradability diverse applications, including ecofriendly packaging and
and compatibility with the environment strengthen their personalized implants, is gaining momentum. Figure 3 shows
position as sustainable alternatives to conventional poly- the ML process in biobased polymers for biochemical
mers.167 The prominence of biobased polymers is further production.
Energy Fuels 2024, 38, 1593−1617
The work by Aznar et al.174 explored the utilization and properties, with a noteworthy increase in tensile strength and a
analysis of polylactic acid (PLA) for food packaging, an significant reduction in water vapor permeability in a 50−50
emerging field due to its environmental benefits. The PLA-starch ratio. In terms of future research, exploring safer,
methodological approach employed included the optimization more effective compatibilizers is essential to overcome the
of a dissolution/precipitation sample treatment using dichloro- existing limitations of PLA-starch blends and multilayer films
methane/ethanol as solvent/antisolvent, with recovery rates for food packaging.
reported between 100.9−114.0%. The study is methodologi- The study by Sucinda et al.176 introduces an inventive
cally sound, identifying the main nonvolatile components of approach for producing ecofriendly packaging material
PLA by UPLC-MS(QTOF) analysis. The investigation’s reinforced with Pennisetum purpureum/Napier cellulose
unique aspect is the in-depth analysis of PLA-polyester blend nanowhiskers (NWCs) in a polylactic acid (PLA) matrix.
pellets and films. The outcomes detailed significant findings, The bionanocomposite films exhibited promising thermal
wherein the four most intensive compounds in pellet samples stability ranging between 343−359 °C. Distinctive observa-
were cyclic oligomers from the polyester blend, comprising tions were made regarding the dispersion of NWC in the PLA
adipic acid (AA), phthalic acid (PA), and butanediol. The matrix. Optimal dispersion was noticed at 0.5−1.5 wt % NWC,
research reported new compounds in migration solutions leading to a smoother and denser surface structure as opposed
resulting from PLA components reacting with food simulants. to the 3.0 wt % NWC films, which had a rough surface due to
In terms of migration experiments using different ethanol the aggregation of NWCs. The tensile strength peaked at 21.22
percentages as food simulants, the results indicate the MPa with a modulus of 11.35 MPa for the PLA/1.0% NWC
emergence of new compounds, contributing to the study’s film, demonstrating superior mechanical properties. Water
comprehensive insights. Such compounds, specifically 14 new absorption was recorded highest at 1.94%, providing insights
ones, were potentially formed by reactions with the packaging into the hydrophilic behavior of the bionanocomposite films.
material components. A notable statistic is the similarity in However, a decline in transparency to 16.16% at λ800 and
composition between pellets and films, with a Pearson UVA and UVB transmittance to 7.49% and 4.02%, respectively,
correlation factor of 0. 996. The work concludes effectively was noted for PLA/3.0% NWC film. This aspect, although
by outlining the high intensities of cyclic oligomers from the beneficial for UV protection, may have limitations in specific
polyester part in PLA blend samples and migration studies, packaging applications demanding higher transparency. A
offering essential data for further research and practical comprehensive evaluation, including FESEM analysis, revealed
applications. For future research, a profound exploration into a more uniform and compact surface structure with lower
the reactions between PLA components and various food NWC content. The study presents a critical analysis of the
simulants will be beneficial. Additionally, a detailed quantita- integration of NWC in PLA to enhance its properties. Yet, the
tive assessment of detected compounds is essential for a agglomeration at higher wt % NWC indicates a crucial need for
comprehensive material risk assessment, aiding in the further research to optimize the NWC content for balanced
enhancement and safe application of biobased polymers in mechanical and physical properties. Further research might
food packaging. explore the practical implications of these findings, particularly
The work by Muller et al.175 fundamentally investigates the the scalability of this technology for industrial applications and
potential of poly(lactic) acid (PLA) and starch as ecofriendly assessing the long-term performance and biodegradability of
replacements for conventional nondegradable petrochemical these bionanocomposite films in real-world conditions. The
polymers used in food packaging. The research analyzes the critical exploration of other biobased nanofillers and their
barrier and mechanical properties of PLA and starch films, comparative performance with NWC can be another potential
utilizing strategies like blending or creating multilayer films, avenue for advancing this field of research. Additionally, the
which show promising results in enhancing polymer environmental impact assessment over the life cycle of these
compatibility and performance. Highlighting some notable bionanocomposite films could provide a more holistic
results, a smoother microstructure and a higher tensile strength understanding of their sustainability profile.
(68 MPa) were observed in the PLA-starch blend (55:45) with In the work by Zhang et al.,177 the spotlight is cast on PHA,
0.5 wt % MDI, signifying improved compatibility and a category of biopolyesters known for their mechanical,
mechanical properties. Yet, the use of MDI, classified as a biodegradable, and tissue-compatible properties. A distinct
harmful substance, underscores a significant limitation for food innovation seen within the work is the utilization of PHA,
packaging applications, emphasizing the need for safer particularly polyhydroxybutyrate (PHB) composites, for the
alternatives. Another method explored was the use of maleic 3D printing of personalized implants. This offers a remarkable
anhydride for enhancing polymer phase interfacial adhesion, step forward by maintaining stable local pH during
resulting in a stable and homogeneous interface and enhancing degradation, thus ensuring cellular and immune system
water resistance and tensile properties. However, despite these tolerance. This innovation is further evident in the 3D-printed
advancements, the work reveals persistent challenges with custom tricalcium phosphate-PHB scaffolds, achieving success-
phase separation in the PLA-starch blends, necessitating ful osteogenic differentiation. PHB’s application does not halt
further research into innovative compatibilizers or treatment here. It shows potential as an osteoplastic material, notably in
methods to optimize the blends for practical application. the construction of porous 3D implants that promote
Moreover, the work demonstrates the improvement in attachment, proliferation, and directed differentiation. Beyond
functional properties of multilayer assemblies due to the 3D printing, the work details other PHA production methods,
complementary barrier capacity of each polymer, offering high such as lithography and nanofiber creation. Lithography,
resistance to both polar and nonpolar molecules and thus particularly soft lithographic methods, is harnessed to produce
emerging as an effective packaging material. Furthermore, the PHBHHx microstructures. This technique demonstrates the
study illustrates the advancements with PLA-starch bilayer potential of PHA polymers to mimic the cellular micro-
films, showcasing improved tensile and water vapor barrier environment, enhancing our understanding of microstructure-
Energy Fuels 2024, 38, 1593−1617
cell function relationships. Similarly, the work highlights the microbial growth by 98% with the ChCNC-coated tissue
use of PHA in nanofiber matrices. These matrices, emulating paper. This statistic emphasizes the robust antimicrobial
the extracellular matrix, present a promising frontier for tissue activity of the developed material. The method of enhancing
engineering due to their supportive role in cell growth and the antimicrobial properties by plasma treatment showcases
their nontoxicity to NIH 3T3 mouse fibroblast cells. For innovation, enhancing the coating’s antimicrobial activity.
injectable implants, the use of PHBHHx dissolved in nontoxic However, the variation in water absorption�with CNC
organic solvents forms a nontoxic film around the animal’s increasing it and Ch decreasing it�reveals a critical balance
injection site, preventing surgical tissue adhesion. In bone that needs to be maintained for optimal performance. The
tissue engineering, the combination of PHA with other ChCNC-coated glass slide’s contact angle was found to be 41°,
materials, such as hydroxyapatite, showcases enhanced cell a crucial statistic that indicates a balance between hydro-
growth and alkaline phosphatase activity, reinforcing its philicity and hydrophobicity. Using various sophisticated
potential in the field of bone tissue engineering. Future studies techniques such as SEM, ToF-SIMS, and Auger electron
could explore the possibilities of combining PHA with other microscopy reinforces the comprehensive assessment and
biodegradable polymers to enhance its properties, potentially verification of the ChCNC-treated substrate’s morphology
leading to developing more advanced and effective biobased and chemical characterization. Despite the commendable
polymers for biochemical production. antimicrobial activity, the study shows that only the
The work by Siracusa and Blanco29 presents a compre- ChCNC-coated tissue paper inhibited the human hand-
hensive examination of the progress of biobased polymers. It is collected microbial sample, which highlights a possible
reported that biobased materials’ production is substantially limitation in its broad-spectrum antimicrobial activity. This
less, being under 2% of the total plastic production, despite an could be a vital area for future research�expanding the
astonishing ability to process large amounts of biomass. The antimicrobial spectrum of the ChCNC coating.
global production of polymers from natural resources like In the study by Aristri et al.,179 an emphasis on tannin-based
starch and cellulose is about 20 million tons per year, a mere biopolyurethanes (bio-PUs) and their potential for environ-
7% of the total plastics production. The study highlights mentally friendly applications is highlighted. The research
significant advancements in processing technologies for highlights the successful synthesis of tannin-based bio-PUs,
refining biomass feedstocks to obtain biobased monomers, confirmed through various analytical techniques like FTIR,
especially focusing on Bio-PE, Bio-PP, and Bio-PET. The DSC, TGA, MALDI-TOF mass spectrometry, and GPC.
geographic analysis reveals the United States and Europe as Notably, a key finding is that as the tannin content increased,
predominant in biobased plastic production, trailed by the Asia the transition glass (Tg) temperature decreased from 32.91 to
Pacific region and South America. The work delineates 11.91 °C, indicative of an increase in backbone stiffness and
technological challenges, noting the variance in development chain interactions. This phenomenon emphasizes tannin
stages for diverse biobased polymers, from research and content’s role in enhancing bio-PU’s thermal properties. The
development to large and commercial stages. The production thermal analysis showed three degradation stages of PU resins,
of Bio-PP is emphasized as especially difficult due to limited with the initial one occurring at 220 °C, attributed to urethane
knowledge and technological barriers. Furthermore, the work bond degradation. Significantly, no weight loss was observed,
discusses the impact of competition with food, feed, and in line with the low isocyanate concentration used in the PU
biofuels for raw materials, recognizing the potential of formation, highlighting the potential for a more stable and
lignocellulosic feedstocks as future starting chemicals. This sustainable product. The thermogravimetric analysis show-
aspect highlights the technological complexities in trans- cased the degradation of ester and carbonyl groups from
forming cellulose into sugar monomers. The work also tannins at 290−300 °C, providing essential insights into the
provides a critical evaluation of environmental performance, thermal stability and potential applications of these bio-PUs in
comparing various routes to obtain bio-PTA for the synthesis various industrial sectors. Moreover, the research leveraged
of bio-PET, emphasizing the greenest route to be that using MALDI-TOF to determine the condensed tannin oligomer’s
orange peels. The study concludes by presenting an optimistic distribution and derivatives. The MALDI-TOF results reveal a
scenario for the future of biobased plastics, projecting a rise in clear differentiation in the molecular weight ranges between
worldwide capacity and emphasizing the importance of the tannin-based bio-PUs produced at room temperatures and
biobased PE and PHA alongside PLA and starch plastics. It a reference mix, further accentuating the unique properties
underscores the interest in biobased durable plastics to curtail attained through tannin incorporation. In view of future
waste, taking advantage of biomass from food and agricultural research, a comprehensive investigation into the long-term
waste. Despite the promising outlook, the work underscores stability and performance of tannin-based bio-PUs in practical,
the challenges of reducing production and processing costs and real-world applications is imperative. Additionally, exploration
minimizing environmental impacts, crucial for commercial into the optimization of tannin content for enhanced material
applications of biobased polymers. For future research, properties, alongside a detailed cost-benefit analysis, would
focusing on enhancing the technological efficiency of biomass significantly contribute to the field, offering a more holistic
processing, exploring more sustainable and less competitive understanding and paving the way for the extensive industrial
feedstock alternatives, and comprehensive environmental adoption of tannin-based bio-PUs.
impact assessment of various biobased polymer production The work by Alinejad et al.180 gives an extensive and
routes will be crucial in advancing the sector and overcoming detailed review of the substitution of lignin for polyol in
delineated challenges. producing polyurethane products. Using lignin, an underutil-
The research by Tyagi et al.178 delves into the creation of ized renewable aromatic polymer, is a unique approach to
functionalized tissue paper by hydrophobic spray-coating of producing polymeric materials. The work outlines the
chitosan (Ch) and cellulose nanocrystals (CNCs). A note- procedure of making rigid polyurethane foams with lignin,
worthy finding in the study is the impressive inhibition of emphasizing the significance of thermal conductivity in this
Energy Fuels 2024, 38, 1593−1617
process. Despite the environmental concerns surrounding use of ML facilitates the prediction and optimization of
using certain blowing agents, the work indicates a transition to production parameters for these crucial biochemical entities.185
more environmentally friendly options such as pentane and Accurate predictions ensure that the biochemical production
water, ensuring sustainable production. The production processes are not only streamlined but also made more
process explained in the document, beginning with water environmentally friendly and sustainable. Through ML, the
and isocyanate, elucidates how the exothermic reactions biochemical industry is rendered more adaptable to the
involved led to the creation of amine and CO2 and, burgeoning demands for sustainability and efficiency.186 This
subsequently, the polyurethane. The work discloses the issues adaptation embodies a significant stride toward a more
with unmodified lignin�leading to brittle foams with low sustainable and ecofriendly future in biochemical production.
compression strength, especially with incorporation over 30 wt Additionally, ML plays a fundamental role in the
%. To counter this, chain extenders like castor oil, optimization of fermentation processes, a core aspect of
polypropylene glycol triol, and butanediol have been biochemical production.155,187,188 The optimal conditions for
employed. The work’s extensive exploration of using various fermentation are crucial for maximizing yield and product
lignins in rigid polyurethane foams shows a comprehensive quality. ML algorithms help in determining these optimal
effort to ascertain optimal materials and procedures. Despite conditions, leading to enhanced production efficiency. The
detailed investigation, the study suggests the ambiguity in the precision afforded by ML ensures that the resources are used
relationship between lignin properties and foam performance, judiciously, and waste is minimized, aligning biochemical
pointing to an area that needs more detailed research to production with sustainability goals. The enhanced control
enhance understanding and refine processes. In the domain of over fermentation processes is a noteworthy advancement in
flexible polyurethane foams, the document offers an analysis of biochemical production, offering a promising avenue for
lignin’s potential as a filler and cross-linker. Even though some further research and development.
success was reported with modified lignins in enhancing ML further finds its application in biocatalysis, a significant
thermal stability and mechanical properties, complete replace- aspect of biochemical production.189−191 Through ML
ment with certain types of lignin resulted in inferior products. algorithms, the most suitable catalysts for specific biochemical
The detailed comparison with control foams is appreciable for reactions are efficiently identified, ensuring that the reactions
its depth, providing clear insights into the practical advantages proceed optimally. This efficiency leads to enhanced
and limitations of lignin use. As for the production of productivity and sustainability in biochemical production.
polyurethane-lignin elastomers, the work reveals the con- The integration of ML in this domain exemplifies the seamless
straints imposed by lignin’s high glass transition temperature amalgamation of technology and biochemistry, heralding a new
and low flexibility. Nevertheless, the findings that lignin fillers era of enhanced and optimized biochemical production.
enhance mechanical properties and tensile modulus signify its In essence, the infusion of ML into the biochemical sector
potential use in polyurethane elastomer synthesis, contingent signifies a monumental leap toward optimized and sustainable
on selecting appropriate types of lignin. Future research could production. ML’s capability to analyze vast data sets, identify
focus on improving the reactivity of lignin, exploring more patterns, and make accurate predictions is invaluable in
environmentally friendly modification methods, and detailed enhancing and fine-tuning biochemical production. Its role in
investigations into the influence of lignin types and optimizing production parameters, fermentation processes, and
modification methods on the properties of the resulting biocatalysis is instrumental in ensuring increased efficiency,
polyurethane products. reduced waste, and alignment with sustainability goals. This
In conclusion, significant progress is observed in the field of synergy between ML and biochemical production stands as a
advanced biobased polymer biochemical production, from beacon of progress, illuminating the path toward a more
enhancement of PLA properties to exploration of new, sustainable and efficient future in biochemical production.
innovative materials and methodologies. Despite the advance- 5.4. Case Studies of ML Applied to Biopolymer for
ments, several challenges and areas for future research and Biochemical Purposes. This section presents a critical
optimization are unveiled, emphasizing the continual need for examination of various case studies addressing ML applications
innovation and scrutiny in this critical field to ensure safety, to biopolymers for biochemical purposes. The focus remains
efficiency, and environmental sustainability. on understanding the effective utilization of different ML
5.3. ML in Biochemicals. The impact of ML on the models in enhancing and optimizing biopolymer properties
biochemical sphere has become increasingly profound. Its role and processes. The breakthroughs, limitations, and future
in boosting and fine-tuning biochemical production is perspectives are extensively analyzed, providing a well-rounded
pivotal.181 An expansive collection of data inherent in view of the impact and potential of ML in the sphere of
biochemical processes is effectively managed and analyzed biopolymer research and application.
through ML algorithms. This data management allows for the The work by Löfgren et al.192 demonstrates an innovative
identification of patterns and trends that would be otherwise application of Bayesian optimization in enhancing the process
obscure, granting an enhanced understanding of diverse of lignin biorefinery for efficient biochemical applications. The
biochemical processes. Optimal conditions for biochemical study focuses on optimizing AquaSolv omni biorefinery for
production are effectively identified through ML, facilitating lignin, an abundant biopolymer, using a ML framework. This
increased yields and process efficiency.69,70,182 Enhanced approach enables linking various biorefinery conditions to the
efficiency conserves resources and substantially reduces experimental outputs effectively. The research reported the use
production time and costs. ML’s influence transcends tradi- of Bayesian optimization for training two surrogate models for
tional boundaries, imbuing the biochemical realm with lignin yield and β-O-4 content. The authors efficiently
unprecedented precision and control. visualized these models using 2D contour plots, revealing
In the biochemical industry, the production of enzymes, substantial improvements in lignin yield and β-O-4 content as
amino acids, and other biobased materials is central.183,184 The new data were acquired using the CA strategy. The work’s
Energy Fuels 2024, 38, 1593−1617
most crucial highlight is the revelation of optimal processing attributes of the films, showcasing a robust R2 value of 0.84,
conditions for lignin yield and β-O-4 linkages for depolyme- emphasizing the model’s reliability in navigating the complex-
rization into platform chemicals, showing the profound impact ities of bioplastic film properties.
of ML in accelerating sustainable chemical processing In the work by Bejagam et al.,26 ML models were employed
methods. Further insights from the work discuss the to predict the melting temperature (Tm) of various PHAs,
comparison between two acquisition strategies, CA and PA, utilizing a data set of experimentally measured Tm values,
providing a deeper understanding of their effectiveness in the molecular weights, and polydispersity indices for many PHA
biorefinery process. The study illustrates that CA generates a homo- and copolymer chemistries. The model showcased
more accurate and developed surrogate model than PA, robust predictions with an average RMSE in Tm predictions of
proving to be a better acquisition strategy for BO-driven 8.47 °C for training and 10.69 °C for the test set,
experiments. This comparative analysis strengthens the work’s demonstrating the model’s efficacy and lack of overfitting.
contribution by demonstrating the relative efficacy of different The work underlines the critical feature importance of first-
strategies in lignin biorefinery. However, despite these order topology (Chi1) and second-order shape/connectivity
commendable findings, the work could offer more extensive indices (Kappa2) in the prediction models, emphasizing their
insights into the potential impact of the optimized biorefinery role in understanding the atomic spatial density in a fragment.
process on broader sustainable development and biochemical Furthermore, applying an evolutionary algorithm-based search
applications. The study’s results significantly contribute to strategy optimizes polymer design by identifying candidates
enhancing lignin biorefinery, yet the discussion on its far- that best meet the target chemical space criteria, underscoring
reaching implications appears limited. In terms of future the model’s practical utility in real-world applications. In future
research, the work sets a solid foundation for further research, enhancing the model’s robustness through integra-
exploration of ML applications in optimizing other biopolymer tion with other ML algorithms or expanding the data set for a
refineries. It opens avenues for investigating the effectiveness of more comprehensive analysis would be a constructive step
other ML algorithms in improving biopolymer refinery forward. Moreover, assessing the model’s performance across
processes and their subsequent impact on the production of various biopolymer types and exploring its potential in
high-value byproducts. In summary, the study presents a predicting other crucial properties beyond Tm could offer
commendable integration of ML in optimizing biopolymer more extensive insights and applications in the realm of
biorefinery, providing valuable insights for enhancing lignin sustainable Bioplastic formulations and biochemical applica-
yield and β-O-4 content effectively. The comparative analysis tions.
of acquisition strategies further enriches the work’s contribu- The work by Pilania et al.82 offers insight into the
tion to the field while highlighting opportunities for expansive application of ML to polyhydroxyalkanoate-based biopolymers,
future research in this domain. emphasizing the prediction of glass transition temperature
The work by Patnode et al.193 focused on soy and zein for (Tg). The work collected experimental Tg values, molecular
the development of sustainable bioplastic films is not only weights, and polydispersity indices for PHA-based polymers,
innovative but timely. The employment of ML to forecast and developing a fingerprinting scheme based on topology, shape,
enhance the properties of proteopposite films shows a and charge/polarity to represent polymers numerically. The
commendable intersection of materials science and computa- constructed model demonstrated the ability to efficiently
tional technology. An R2 value of 0.85 underpins the model’s predict new PHA polymer properties with notable accuracy,
accuracy, reinforcing the credibility of the ML predictions and citing a Pearson correlation coefficient of 94.67%, RMSE of
their practical application. The study eloquently blends 4.80 K, and mean absolute error (MAE) of 18.99 K. The
experimental and computational research to assess the uniqueness of this study lies in its methodical approach, using a
synergistic impact of zein, soy, and POBM-latexes in large feature space recursively to enumerate analytical
proteopposite films. The work observed a significant enhance- functions describing Tg, producing 283, 86.7 × 103, and 12.5
ment in the flexibility and moisture resistance of the soy-zein × 109 elements for various feature sets. The surrogate model,
films with the integration of POBM-latexes. Considering the combined with an evolutionary algorithm-based search
films’ targeted application in food packaging, this aspect is strategy, was able to find multicomponent polymer composi-
pivotal, where these properties are paramount. Specifically, the tions with a specified Tg efficiently. The model’s robustness is
elongation at the break of the films surged by over 400%, a confirmed by its consistent performance on 20 randomly
staggering improvement that holds practical and industrial selected training/test splits, producing an average RMSE of
relevance. Yet, the exploration did not end here; the study 4.76 K and a variance of 1.19 K2. The research adequately
delved deeper, examining the influence of POBM-latex particle addresses the significance of Tg prediction for various
size, unveiling that smaller particle sizes afford greater biopolymers, successfully utilizing ML models to forecast Tg
uniformity and enhanced interaction in the proteopposite values and explore the chemical space of PHAs. Nevertheless, a
film structure. Despite the advancements and the high critical evaluation reveals that the model’s applicability may be
prediction accuracy, there lies a necessity for further validation limited to the data and features utilized in the study. The
and testing in real-world applications. This is crucial for discussion emphasizes the model’s resistance to overfitting and
assessing Bioplastic films’ true efficacy and feasibility in highlights the established parameters for the RF model,
replacing traditional petrochemical food packaging. Moreover, including a maximum tree depth of 6 and the number of
while the study delivers insights into the mechanical and estimators set to 35. However, these fixed parameters might
barrier properties of the modified soy-zein proteopposites, a pose restrictions for other biopolymers not considered in this
comprehensive assessment of their antimicrobial properties study. In terms of future research, the exploration of other ML
and surface morphology remains uncharted, presenting a clear algorithms for predicting different properties of biopolymers
pathway for future research endeavors. The comprehensive beyond Tg and the enhancement of the current model for
ML-based QSAR model successfully predicted the mechanical broader chemical spaces could be undertaken.
Energy Fuels 2024, 38, 1593−1617
The work by Jiang et al.194 endeavored to predict the The development of robust ML models relies heavily on the
performance properties of PHAs using a deep neural network availability and quality of data.198,199 One of the challenges in
(DNN) model is remarkable. The methodological approach is this field is the limited access to comprehensive data sets that
comprehensive, utilizing variables such as molecular weight capture the complexity of biopolymer systems. Future research
and monomer percentages to estimate PHA glass transition should prioritize the creation of extensive, high-quality data
temperatures (Tg). The study achieved a substantial R2 value of sets. This could involve collaborations between academic and
0.869, MAE 4.010, and RMSE 5.339 K, demonstrating the industrial sectors to pool resources and data. Also, there is a
model’s high level of accuracy and reliability in prediction. This need for standardizing data collection and reporting methods
approach outperformed other ML models, further solidifying to ensure the consistency and reliability of the data used in ML
its credibility. However, the issue of model symmetry and models.
sensitivity to missing data require attention. The initial DNN Another critical research direction is the application of ML
model did not capture symmetry, making it sensitive to in biopolymer recycling and waste reduction.12,200,201 As the
monomer order and highlighting a significant limitation. world grapples with plastic pollution, biopolymers offer a
Nevertheless, the researchers astutely addressed this by sustainable alternative. ML can be leveraged to improve
retraining the model, achieving improved results with R2 recycling processes, optimize waste management systems, and
increasing to 0.897. Although the DNN model’s performance develop new biodegradable materials. Future research could
is laudable, the study illuminates the crucial aspect of explore ML models that predict the recyclability of
symmetry in ML models for biopolymer prediction. Moreover, biopolymers based on their chemical compositions and
the investigation into the DNN model’s robustness with environmental conditions.
missing or inaccurate data is praiseworthy, offering insights The integration of ML in producing and processing
into the potential practical challenges of employing ML in biopolymers is a promising research area. ML can be used to
predicting biopolymer properties. Despite the decrease in R2 to optimize production parameters, reduce energy consumption,
0.5 with omitted variables, the research insightfully demon- and enhance the overall efficiency of biopolymer manufactur-
strates the critical role of fractional composition in the DNN ing processes. Future studies could investigate the use of ML in
model, underscoring its importance in maintaining prediction real-time monitoring and control of biopolymer production,
accuracy. Moving forward, potential research could delve focusing on maximizing output while minimizing environ-
deeper into enhancing the DNN model’s robustness against mental impact.
missing data. Furthermore, exploration of additional ML Biopolymers such as alginate, cellulose, PLA, chitosan, and
frameworks might yield more streamlined or effective lignin have great potential in energy storage systems, such as
approaches, potentially further improving the prediction batteries and supercapacitors. ML can play a pivotal role in
accuracy and reliability for biopolymer applications and enhancing the performance of these systems. Research should
expanding the study’s implications for sustainable technology be directed toward developing ML models that can accurately
and engineering. predict and optimize the ionic conductivity, charge−discharge
In conclusion, examining case studies reveals the pivotal role cycles, and overall efficiency of biopolymer-based energy
ML holds in augmenting biopolymer research for biochemical storage systems.
applications. Despite some limitations, the diverse machine- Designing and developing novel biopolymers using ML
learning approaches discussed significantly enhance the algorithms is an exciting future prospect. Using ML,
prediction and optimization of biopolymer properties and researchers can predict and create new biopolymer structures
processes. The explored studies underscore the burgeoning with desired properties for specific applications. This approach
potential and avenues for further research in this innovative could revolutionize the field, developing innovative materials
intersection of ML and biopolymer, driving advancements in for various industries, from healthcare to aerospace.
sustainable and efficient biochemical applications. Furthermore, understanding the interactions between biopol-
ymers and other materials is crucial for broadening their
application scope. Future research could use ML to model and
6. FUTURE WORK
predict the behavior of biopolymer composites, blends, and
The intersection of ML and biobased polymers represents a hybrids.85,202,203 This would enable the development of
significant and rapidly evolving field for research. This materials with tailored properties for specific uses, such as
convergence unlocks unprecedented opportunities for devel- biocompatible medical devices or high-performance construc-
oping sustainable energy, fuels, and biochemical solutions.12,195 tion materials.
As we delve into this dynamic domain, the potential for While biopolymers are inherently more sustainable than
innovative breakthroughs that can drive us toward a more traditional polymers, there is a need to further enhance their
sustainable future is immense. environmental friendliness. Future research could explore how
A significant avenue for future research lies in enhancing the ML can be used to analyze and optimize the life cycle of
efficiency of biopolymers. ML has shown promise in biopolymers, from production to degradation. This would
optimizing various properties of biopolymers, but there is involve developing models to assess the environmental impact
still room for improvement. Future studies could focus on of biopolymers and finding ways to reduce their carbon
refining ML algorithms for more precise predictions and footprint.
optimizations of biopolymer properties, such as thermal The use of biopolymers in drug delivery systems offers a
stability, mechanical strength, and degradation rates. For promising research avenue.204,205 ML can assist in designing
instance, research could explore deep learning models to biopolymer-based carriers that optimize drug release profiles
predict the interplay of biopolymer molecular structures with and target specific tissues or cells. Future studies could develop
environmental factors, thereby enhancing their performance in ML models that simulate the interactions between biopolymers
specific applications.196,197 and various pharmaceutical compounds, aiding in creating
Energy Fuels 2024, 38, 1593−1617
more effective and safer drug delivery systems. Furthermore, Aydin Berenjian − Department of Chemical and Biological
the exploration of ML applications in biocatalysis within Engineering, Colorado State University, Fort Collins,
biochemical production is deemed promising, likely leading to Colorado 80523, United States
enhanced productivity and sustainability in biochemical Ao Xia − Key Laboratory of Low-Grade Energy Utilization
production.189,191,206 Technologies and Systems, Chongqing University, Ministry of
Finally, the future of ML and biopolymers research lies in Education, Chongqing 400044, China; Institute of
collaborative and cross-disciplinary efforts. Combining the Engineering Thermophysics, School of Energy and Power
expertise of chemists, material scientists, computer scientists, Engineering, Chongqing University, Chongqing 400044,
and engineers will be key to advancing this field. Collaborative China; orcid.org/0000-0003-0428-287X
projects can lead to breakthroughs in understanding and Complete contact information is available at:
leveraging the capabilities of ML in biopolymer research, https://pubs.acs.org/10.1021/acs.energyfuels.3c03842
leading to innovations that can significantly impact various
sectors and contribute to a sustainable future. In conclusion, Notes
the path forward in converging ML and biopolymers has The authors declare no competing financial interest.
exciting opportunities and challenges. By addressing these key
Biographies
areas, the scientific community can unlock the full potential of
this synergy, paving the way for groundbreaking advancements Abu Danish Aiman Bin Abu Sofian is a chemical engineering and
in sustainable materials and energy solutions. physics researcher. He has undertaken research work at Khalifa
University, University of Malaya, and University of Nottingham
7. CONCLUSION Malaysia. His work primarily involves using machine learning for
sustainable energy storage materials and biopolymers. His research
The nexus between ML and biobased polymers heralds a involves enhancing nickel-rich NCM and NCA cathodes, lithium
transformative phase in energy, fuels, and biochemicals. anodes, and solid-state electrolytes for all-solid-state lithium-ion
Biobased polymers, with their sustainable origins, are batteries (ASSB). He focuses on optimizing ASSB for improved
progressively influencing the energy and fuel domains. Their safety, energy density, stability, capacity, and sustainability. He also
integration with ML amplifies their inherent potential and does research on battery upcycling and recycling.
optimizes renewable energy processes, storage solutions, and
conversion mechanisms. Through diverse case studies, the Dr. Xun Sun is an associate professor at the School of Mechanical
efficacy of these polymers in energy applications is Engineering, Shandong University, China. He received his Ph.D. from
accentuated, while ML’s potential to enhance fuel efficiency Hanyang University (South Korea) in 2018. He has been working
stands elucidated. The cusp of this synergy also brings to light with several top researchers in process intensification by hydro-
groundbreaking strides in biochemical production, notably in dynamic cavitation, cavitating flow, computational fluid dynamics, and
drug delivery and medical instrumentation. It is evident that water treatment. He has published more than 60 SCI papers and
the symbiotic relationship between ML and biobased polymers obtained three National Natural Science Foundation of China
offers a beacon for global sustainability in the energy and (NSFC) projects as the principal investigator.
biochemical realms. Embracing this amalgamation is para- Dr. Vijai Kumar Gupta holds a doctoral degree in microbiology from
mount to ushering in an era of innovation and steadfast Dr RML Avadh University, India. Currently, he is working as Senior
commitment to a sustainable future. Fellow and Group Leader at the Center for Safe and Improved Foods
■ AUTHOR INFORMATION
Corresponding Authors
& Biorefining and Advanced Materials Research Center, SRUC,
Edinburgh, UK. He is the Secretary of the European Mycological
Association and Visiting Professor at SCBG-China; MATE-Hungary;
USTM-India. Dr. Gupta is a Fellow of the Linnean Society of London
Zengling Ma − National and Local Joint Engineering Research
and the Mycological Society of India. He has an h-index of 80 and has
Center of Ecological Treatment Technology for Urban Water
been cited more than 27000 times.
Pollution, Wenzhou University, Wenzhou 325035, China;
Email: [email protected] Professor Dr. Aydin Berenjian is a Full Professor of Chemical &
Pau Loke Show − Department of Chemical Engineering, Biological Engineering at Colorado State University. He obtained his
Khalifa University, Abu Dhabi, United Arab Emirates; Ph.D. from the University of Sydney. He has a prolific research
orcid.org/0000-0002-0913-5409; publication record, having an h-index of 41 and has been cited more
Email: [email protected] than 7158 times. Beyond his own research, he has made significant
contributions to the scientific literature through prominent long-term
Authors editorial positions in several prestigious journals, and he currently
Abu Danish Aiman Bin Abu Sofian − Department of serves as the Editor-in-Chief of Molecular Biotechnology.
Chemical and Environmental Engineering, Faculty of Science
and Engineering, University of Nottingham Malaysia, 43500 Professor Dr. Ao Xia is a professor in School of Energy and Power
Semenyih, Selangor Darul Ehsan, Malaysia Engineering at Chongqing University (CQU). He serves as an
Xun Sun − Key Laboratory of High Efficiency and Clean associate editor for Frontiers in Bioengineering and Biotechnology and
Mechanical Manufacture of Ministry of Education, School of Frontiers in Energy Research, and also serves as an editorial board
Mechanical Engineering, Shandong University, Jinan 250061, member for Energies and Coal Science and Technology. He completed
China his PhD research in 2013 in energy engineering from Zhejiang
Vijai Kumar Gupta − Biorefining and Advance Material University (ZJU). He was also a postdoctoral researcher at the
Research Centre, SRUC, Parkgate, Dumfries DG1 3NE, Environmental Research Institute (ERI) at University College Cork
United Kingdom (UCC).
Energy Fuels 2024, 38, 1593−1617
Professor Dr. Zengling Ma is the Dean in College of Life and (12) Bin Abu Sofian, A. D. A.; Lim, H. R.; Manickam, S.; Ang, W. L.;
Environmental Science and the Leader and Chair Professor at the Show, P. L. Towards a Sustainable Circular Economy: Algae-Based
Zhejiang Provincial Key Laboratory for Subtropical Water Environ- Bioplastics and the Role of Internet-of-Things and Machine Learning.
ment and Marine Biological Resources Protection, Wenzhou ChemBioEng. Rev. 2023, DOI: 10.1002/cben.202300028.
(13) Bin Abu Sofian, A. D. A.; Lim, H. R.; Chew, K. W.; Khoo, K. S.;
University, China. He attended Shantou University and Qufu Normal
Tan, I. S.; Ma, Z.; Show, P. L. Hydrogen production and pollution
University for his education. He also produced over 113 SCI
mitigation: Enhanced gasification of plastic waste and biomass with
publications while being the first/corresponding author in over 30 of machine learning & storage for a sustainable future. Environ. Pollut.
them. 2024, 342, 123024.
Prof. Ir. Ts. Dr. Pau Loke Show is a Full Professor of Biochemical (14) Wang, Z.; Peng, X.; Xia, A.; Shah, A. A.; Huang, Y.; Zhu, X.;
Engineering at Khalifa University, UAE. Earning his PhD in two years Zhu, X.; Liao, Q. The role of machine learning to boost the bioenergy
from Universiti Putra Malaysia, he holds numerous prestigious titles and biofuels conversion. Bioresour. Technol. 2022, 343, 126099.
(15) Sharma, V.; Tsai, M.-L.; Chen, C.-W.; Sun, P.-P.; Nargotra, P.;
and memberships. He published over 850 papers and has been cited
Dong, C.-D. Advances in machine learning technology for sustainable
over 35,000 times, leading to an h-index of 94. He is the Editor-in- biofuel production systems in lignocellulosic biorefineries. Sci. Total
Chief and Editor of several high impact international journals. He is a Environ. 2023, 886, 163972.
reviewer who has reviewed for over 150 esteemed journals and (16) Shahbeik, H.; Rafiee, S.; Shafizadeh, A.; Jeddi, D.; Jafary, T.;
handled over 5500 submitted manuscripts. Lam, S. S.; Pan, J.; Tabatabaei, M.; Aghbashlo, M. Characterizing
sludge pyrolysis by machine learning: Towards sustainable bioenergy
■ ACKNOWLEDGMENTS
The authors sincerely thank Lim Hooi Ren from the
production from wastes. Renew. Enery 2022, 199, 1078−1092.
(17) Shafizadeh, A.; Shahbeig, H.; Nadian, M. H.; Mobli, H.;
Dowlati, M.; Gupta, V. K.; Peng, W.; Lam, S. S.; Tabatabaei, M.;
Department of Chemical and Environmental Engineering, Aghbashlo, M. Machine learning predicts and optimizes hydrothermal
Faculty of Science and Engineering, University of Nottingham liquefaction of biomass. Chem. Eng. J. 2022, 445, 136579.
Malaysia, for his contributions to ensuring the smooth (18) Riaz, S.; Rhee, K. Y.; Park, S. J. Polyhydroxyalkanoates (PHAs):
publication of this article. Pau Loke Show would like to biopolymers for biofuel and biorefineries. Polymers. 2021, 13 (2), 253.
acknowledge the Khalifa University (FSU-2024-001) with (19) Lizundia, E.; Kundu, D. Advances in natural biopolymer-based
electrolytes and separators for battery applications. Adv. Funct. Mater.
project reference number 8474000580.
2021, 31 (3), 2005646.
■ REFERENCES
(1) Nastasi, B.; Markovska, N.; Puksec, T.; Duić, N.; Foley, A.
(20) Jo, Y. K.; Lee, D. Biopolymer microparticles prepared by
microfluidics for biomedical applications. Small 2020, 16 (9),
1903736.
Renewable and sustainable energy challenges to face for the (21) Nathanael, A. J.; Oh, T. H. Biopolymer coatings for biomedical
achievement of Sustainable Development Goals. Renew. Sust. Energy applications. Polymers. 2020, 12 (12), 3061.
Rev. 2022, 157, 112071. (22) Vinodh, R.; Sasikumar, Y.; Kim, H.-J.; Atchudan, R.; Yi, M.
(2) Fahad, S.; Adnan, M.; Saud, S.; Nie, L. Climate Change and Chitin and chitosan based biopolymer derived electrode materials for
Ecosystems: Challenges to Sustainable Development; CRC Press: 2022. supercapacitor applications: A critical review. J. Ind. Eng. Chem. 2021,
(3) Ibrahim, R. L.; Ajide, K. B. Disaggregated environmental impacts 104, 155−171.
of non-renewable energy and trade openness in selected G-20 (23) Haque, M. A.; Priya, A.; Hathi, Z. J.; Qin, Z.-H.; Mettu, S.; Lin,
countries: the conditioning role of technological innovation. Environ. C. S. K. Advancements and current challenges in the sustainable
Sci. Pollut. Res. 2021, 28, 67496−67510. downstream processing of bacterial polyhydroxyalkanoates. Curr. Opi.
(4) Zhang, T.; Liu, Y.; Zhong, S.; Zhang, L. AOPs-based in Green and Sust. Chem. 2022, 36, 100631.
remediation of petroleum hydrocarbons-contaminated soils: Effi- (24) Tumwesigye, K. S.; Oliveira, J.; Sousa-Gallagher, M. J.
ciency, influencing factors and environmental impacts. Chemosphere Integrated sustainable process design framework for cassava biobased
2020, 246, 125726. packaging materials: critical review of current challenges, emerging
(5) Bakır, H.; Aǧbulut, D. C.; Gürel, A. E.; Yıldız, G.; Güvenç, U.; trends and prospects. Trends Food Sci. Technol. 2016, 56, 103−114.
Soudagar, M. E. M.; Hoang, A. T.; Deepanraj, B.; Saini, G.; Afzal, A. (25) Takamura, A.; Tsukamoto, K.; Sakata, K.; Kikuchi, J.
Forecasting of future greenhouse gas emission trajectory for India Integrative measurement analysis via machine learning descriptor
using energy and economic indexes with various metaheuristic selection for investigating physical properties of biopolymers in hairs.
algorithms. J. Clean. Prod. 2022, 360, 131946. Sci. Rep. 2021, 11 (1), 24359.
(6) Nanda, N.; Bharadvaja, N. Algal bioplastics: current market (26) Bejagam, K. K.; Lalonde, J.; Iverson, C. N.; Marrone, B. L.;
trends and technical aspects. Clean Technol. Environ. Policy 2022, 24 Pilania, G. Machine learning for melting temperature predictions and
(9), 2659−2679. design in polyhydroxyalkanoate-based biopolymers. J. Phys. Chem. B
(7) Adeniran, A. A.; Shakantu, W. The health and environmental 2022, 126 (4), 934−945.
impact of plastic waste disposal in South African Townships: A (27) Kartal, F.; Dalbudak, Y.; Ö zveren, U. Prediction of thermal
review. Int. J. Environ. Res. Public Health. 2022, 19 (2), 779. degradation of biopolymers in biomass under pyrolysis atmosphere by
(8) Taherimehr, M.; YousefniaPasha, H.; Tabatabaeekoloor, R.; means of machine learning. Renew. Enery 2023, 204, 774−787.
Pesaranhajiabbas, E. Trends and challenges of biopolymer-based (28) Chen, M.; Yan, X.; Cheng, M.; Zhao, P.; Wang, Y.; Zhang, R.;
nanocomposites in food packaging. Compr. rev. in food sci. food safety Wang, X.; Wang, J.; Chen, M. Preparation, characterization and
2021, 20 (6), 5321−5344. application of poly(lactic acid)/corn starch/eucalyptus leaf essential
(9) Holzinger, A.; Keiblinger, K.; Holub, P.; Zatloukal, K.; Müller, oil microencapsulated active bilayer degradable film. Int. J. Biol.
H. AI for life: Trends in artificial intelligence for biotechnology. New Macromol. 2022, 195, 264−273.
Biotechnology 2023, 74, 16−24. (29) Siracusa, V.; Blanco, I. Bio-Polyethylene (Bio-PE), Bio-
(10) Gupta, R.; Srivastava, D.; Sahu, M.; Tiwari, S.; Ambasta, R. K.; Polypropylene (Bio-PP) and Bio-Poly(ethylene terephthalate) (Bio-
Kumar, P. Artificial intelligence to deep learning: machine intelligence PET): Recent Developments in Bio-Based Polymers Analogous to
approach for drug discovery. Molecular div. 2021, 25, 1315−1360. Petroleum-Derived Ones for Packaging and Engineering Applications.
(11) Wei, J.; Chu, X.; Sun, X. Y.; Xu, K.; Deng, H. X.; Chen, J.; Wei, Polymers. 2020, 12, 1641.
Z.; Lei, M. Machine learning in materials science. InfoMat 2019, 1 (30) Bugnicourt, E.; Cinelli, P.; Lazzeri, A.; Alvarez, V. A.
(3), 338−358. Polyhydroxyalkanoate (PHA): Review of synthesis, characteristics,
Energy Fuels 2024, 38, 1593−1617
processing and potential applications in packaging. Express Polym. (51) Appiah, E. S.; Dzikunu, P.; Mahadeen, N.; Ampong, D. N.;
Lett. 2014, 8, 791. Mensah-Darkwa, K.; Kumar, A.; Gupta, R. K.; Adom-Asamoah, M.
(31) Liu, Y.; Li, L.; Pan, N.; Wang, Y.; Ren, X.; Xie, Z.; Buschle- Biopolymers-Derived Materials for Supercapacitors: Recent Trends,
Diller, G.; Huang, T.-S. Antibacterial cellulose acetate films Challenges, and Future Prospects. Molecules 2022, 27 (19), 6556.
incorporated with N-halamine-modified nano-crystalline cellulose (52) Hassan, S. T.; Danish; Salah-Ud-Din, k.; Awais Baloch, M.;
particles. Polym. for Adv. Technol. 2017, 28 (4), 463−469. Tarar, Z. H. Is nuclear energy a better alternative for mitigating CO2
(32) Gomez-Lopez, A.; Panchireddy, S.; Grignard, B.; Calvo, I.; emissions in BRICS countries? An empirical analysis. Nuclear
Jerome, C.; Detrembleur, C.; Sardon, H. Poly(hydroxyurethane) Engineering and Technology 2020, 52 (12), 2969−2974.
Adhesives and Coatings: State-of-the-Art and Future Directions. ACS (53) Mishnaevsky Jr, L.; Jafarpour, M.; Krüger, J.; Gorb, S. N. A
Sustain. Chem. Eng. 2021, 9 (29), 9541−9562. New Concept of Sustainable Wind Turbine Blades: Bio-Inspired
(33) Hirpara, N. J.; Dabhi, M.; Rathod, P. Development of potato Design with Engineered Adhesives. Biomimetics 2023, 8 (6), 448.
starch based biodegradable packaging film. J. Food Process. Technol. (54) Rahman, N. A.; Hanifah, S. A.; Mobarak, N. N.; Ahmad, A.;
2021, 12, 529−541. Ludin, N. A.; Bella, F.; Su’ait, M. S. Chitosan as a paradigm for
(34) Stempfle, F.; Ortmann, P.; Mecking, S. Long-Chain Aliphatic biopolymer electrolytes in solid-state dye-sensitised solar cells.
Polymers To Bridge the Gap between Semicrystalline Polyolefins and Polymer 2021, 230, 124092.
Traditional Polycondensates. Chem. Rev. 2016, 116 (7), 4597−4641. (55) Vickram, A.; Saravanan, A.; Kumar, P. S.; Thamarai, P.;
(35) Roymahapatra, G.; Khatua, P. K. Bioplastic: the Green Yasodha, S.; Jamuna, G.; Rangasamy, G. An integrated approach to
Technology; and concern on biodegradability. In Environment Friendly the sustainable development and production of biofuel from
Biodegradable Polymers: Present and Future; Samanta, B. C., Maity, T., biopolymers and algal biomass derived from wastewater. Fuel 2023,
Eds.; Mallik Book Stall: Kolkata, 2016; Chapter 18, pp 200−222. 349, 128691.
(36) Jafferson, J.; Chatterjee, D. A review on polymeric materials in (56) Saha, B.; De, S.; Fan, M. Zr (O) Cl2 catalyst for selective
additive manufacturing. Mater. Today Proc. 2021, 46, 1349−1365. conversion of biorenewable carbohydrates and biopolymers to biofuel
(37) Baharlouei, P.; Rahman, A. Chitin and chitosan: Prospective precursor 5-hydroxymethylfurfural in aqueous medium. Fuel 2013,
biomedical applications in drug delivery, cancer treatment, and wound 111, 598−605.
healing. Marine Drugs 2022, 20 (7), 460. (57) Rababah, M. M.; AL-Oqla, F. M. Biopolymer composites and
(38) Schmid, M.; Müller, K. Whey protein-based packaging films sustainability. In Advanced Processing, Properties, and Applications of
and coatings. In Whey Proteins; Elsevier: 2019; pp 407−437. Starch and Other Bio-Based Polymers; Elsevier: 2020; pp 1−10.
(39) Praseptiangga, D. In Development of Seaweed-Based Biopolymers (58) Buescher, J. M.; Margaritis, A. Microbial biosynthesis of
for Edible Films and Lectins; IOP Conference Series: Materials Science polyglutamic acid biopolymer and applications in the biopharmaceut-
and Engineering, IOP Publishing: 2017; p 012003. ical, biomedical and food industries. Crit. rev. in biotech. 2007, 27 (1),
(40) Lenzen, M.; Geschke, A.; West, J.; Fry, J.; Malik, A.; Giljum, S.; 1−19.
Mila i Canals, L.; Pinero, P.; Lutter, S.; Wiedmann, T.; Li, M.; (59) Wróblewska-Krepsztul, J.; Rydzkowski, T.; Michalska-Pożoga,
Sevenster, M.; Potocnik, J.; Teixeira, I.; Van Voore, M.; Nansai, K.; I.; Thakur, V. K. Biopolymers for biomedical and pharmaceutical
Schandl, H. Implementing the material footprint to measure progress applications: Recent advances and overview of alginate electro-
towards Sustainable Development Goals 8 and 12. Nat. Sustain. 2022, spinning. Nanomaterials 2019, 9 (3), 404.
5 (2), 157−166. (60) Xu, T.; Liu, K.; Sheng, N.; Zhang, M.; Liu, W.; Liu, H.; Dai, L.;
(41) Kostetckaia, M.; Hametner, M. How Sustainable Development Zhang, X.; Si, C.; Du, H.; Zhang, K. Biopolymer-based hydrogel
Goals interlinkages influence European Union countries’ progress electrolytes for advanced energy storage/conversion devices: Proper-
towards the 2030 Agenda. Sus. Dev. 2022, 30 (5), 916−926. ties, applications, and perspectives. Energy Storage Mater. 2022, 48,
(42) Pandey, A.; Asif, M. Assessment of energy and environmental 244−262.
sustainability in South Asia in the perspective of the Sustainable (61) Butler, K. T.; Davies, D. W.; Cartwright, H.; Isayev, O.; Walsh,
Development Goals. Renew. Sust. Energy Rev. 2022, 165, 112492. A. Machine learning for molecular and materials science. Nature 2018,
(43) Cywar, R. M.; Rorrer, N. A.; Hoyt, C. B.; Beckham, G. T.; 559 (7715), 547−555.
Chen, E. Y.-X. Bio-based polymers with performance-advantaged (62) Hu, Y.; Buehler, M. J. Deep language models for interpretative
properties. Nat. Rev. Mater. 2022, 7 (2), 83−103. and predictive materials science. APL Mach. Learn. 2023, 1 (1),
(44) Baranwal, J.; Barse, B.; Fais, A.; Delogu, G. L.; Kumar, A. 010901.
Biopolymer: A sustainable material for food and medical applications. (63) Bone, J. M.; Childs, C. M.; Menon, A.; Póczos, B.; Feinberg, A.
Polymers. 2022, 14 (5), 983. W.; LeDuc, P. R.; Washburn, N. R. Hierarchical Machine Learning for
(45) Prasanth, S.; Kumar, P. S.; Harish, S.; Rishikesh, M.; Nanda, S.; High-Fidelity 3D Printed Biopolymers. ACS 2020, 6 (12), 7021−
Vo, D.-V. N. Application of biomass derived products in mid-size 7031.
automotive industries: A review. Chemosphere 2021, 280, 130723. (64) Nath, D. C.; Kundu, I.; Sharma, A.; Shivhare, P.; Afzal, A.;
(46) Nanda, S.; Patra, B. R.; Patel, R.; Bakos, J.; Dalai, A. K. Soudagar, M. E. M.; Park, S. G. Internet of Things integrated with
Innovations in applications and prospects of bioplastics and solar energy applications: a state-of-the-art review. Environ. Dev.
biopolymers: A review. Environ. Chem. Lett. 2022, 20 (1), 379−395. Sustain. 2023. DOI: 10.1007/s10668-023-03691-2
(47) Devadas, V. V.; Khoo, K. S.; Chia, W. Y.; Chew, K. W.; (65) Veza, I.; Afzal, A.; Mujtaba, M. A.; Tuan Hoang, A.;
Munawaroh, H. S. H.; Lam, M.-K.; Lim, J.-W.; Ho, Y.-C.; Lee, K. T.; Balasubramanian, D.; Sekar, M.; Fattah, I. M. R.; Soudagar, M. E.
Show, P. L. Algae biopolymer towards sustainable circular economy. M.; El-Seesy, A. I.; Djamari, D. W.; Hananto, A. L.; Putra, N. R.;
Bioresour. Technol. 2021, 325, 124702. Tamaldin, N. Review of artificial neural networks for gasoline, diesel
(48) Hottle, T. A.; Bilec, M. M.; Landis, A. E. Biopolymer and homogeneous charge compression ignition engine. Alex. Eng. J.
production and end of life comparisons using life cycle assessment. 2022, 61 (11), 8363−8391.
Resour. Conserv. Recycl. 2017, 122, 295−306. (66) Packwood, D. Bayesian Optimization for Materials Science;
(49) Yates, M. R.; Barlow, C. Y. Life cycle assessments of Springer, 2017.
biodegradable, commercial biopolymers�A critical review. Resour. (67) Shelare, S. D.; Belkhode, P. N.; Nikam, K. C.; Jathar, L. D.;
Conserv. Recycl. 2013, 78, 54−66. Shahapurkar, K.; Soudagar, M. E. M.; Veza, I.; Khan, T.M. Y.; Kalam,
(50) George, A.; Sanjay, M.; Srisuk, R.; Parameswaranpillai, J.; M.A.; Nizami, A.-S.; Rehan, M. Biofuels for a sustainable future:
Siengchin, S. A comprehensive review on chemical properties and Examining the role of nano-additives, economics, policy, internet of
applications of biopolymers and their composites. Int. J. Biol. things, artificial intelligence and machine learning technology in
Macromol. 2020, 154, 329−338. biodiesel production. Energy 2023, 282, 128874.
Energy Fuels 2024, 38, 1593−1617
(68) Kim, J.; Kang, D.; Kim, S.; Jang, H. W. Catalyze materials polymers with high thermal conductivity using a molecular design
science with machine learning. ACS Materials Letters 2021, 3 (8), algorithm. Npj Comput. Mater. 2019, 5 (1), 66.
1151−1171. (88) Wu, Y.-J.; Fang, L.; Xu, Y. Predicting interfacial thermal
(69) Patterson, S. B.; Wong, R.; Barker, G.; Vilela, F. Advances in resistance by machine learning. Npj Comput. Mater. 2019, 5 (1), 56.
continuous polymer analysis in flow with application towards (89) Elsayad, A. M.; Zeghid, M.; Ahmed, H. Y.; Elsayad, K. A.
biopolymers. J. Flow Chem. 2023, 13, 103. Exploration of Biodegradable Substances Using Machine Learning
(70) Al-Kharusi, G.; Dunne, N. J.; Little, S.; Levingstone, T. J. The Techniques. Sustainability. 2023, 15 (17), 12764.
role of machine learning and design of experiments in the (90) Zhan, Z.; Li, L.; Tian, S.; Zhen, X.; Li, Y. Prediction of chemical
advancement of biomaterial and tissue engineering research. biodegradability using computational methods. Mol. Simul. 2017, 43
Bioengineering. 2022, 9 (10), 561. (13−16), 1277−1290.
(71) Li, F.; Peng, X.; Wang, Z.; Zhou, Y.; Wu, Y.; Jiang, M.; Xu, M. (91) Puranik, A.; Dandekar, P.; Jain, R. Exploring the potential of
Machine learning (ML)-assisted design and fabrication for solar cells. machine learning for more efficient development and production of
Energy & environ. mater. 2019, 2 (4), 280−291. biopharmaceuticals. Biotechnol. Prog. 2022, 38 (6), No. e3291.
(72) Cheng, B.; Yao, Y. Design and optimization of a novel U-type (92) Li, C.; Zheng, P.; Yin, Y.; Wang, B.; Wang, L. Deep
vertical axis wind turbine with response surface and machine learning reinforcement learning in smart manufacturing: A review and
methodology. Energy Convers. Manag. 2022, 273, 116409. prospects. CIRP J. of Manufact. Sci. and Technol. 2023, 40, 75−101.
(73) Chen, A.; Zhang, X.; Zhou, Z. Machine learning: accelerating (93) Chen, L.; Pilania, G.; Batra, R.; Huan, T. D.; Kim, C.;
materials development for energy storage and conversion. InfoMat Kuenneth, C.; Ramprasad, R. Polymer informatics: Current status and
2020, 2 (3), 553−576. critical next steps. Mater. Sci. Eng. R Rep. 2021, 144, 100595.
(74) Shen, S. C.; Khare, E.; Lee, N. A.; Saad, M. K.; Kaplan, D. L.; (94) Mohammadi, Y.; Saeb, M. R.; Penlidis, A.; Jabbari, E. J.; Stadler,
Buehler, M. J. Computational Design and Manufacturing of F. J.; Zinck, P.; Matyjaszewski, K. Intelligent machine learning: tailor-
Sustainable Materials through First-Principles and Materiomics. making macromolecules. Polymers. 2019, 11 (4), 579.
Chem. Rev. 2023, 123 (5), 2242−2275. (95) Zhou, T.; Song, Z.; Sundmacher, K. Big data creates new
(75) Ng, M.-F.; Zhao, J.; Yan, Q.; Conduit, G. J.; Seh, Z. W. opportunities for materials research: a review on methods and
Predicting the state of charge and health of batteries using data-driven applications of machine learning for materials design. Engineering
machine learning. Nat. Mach. Intell. 2020, 2 (3), 161−170. 2019, 5 (6), 1017−1026.
(76) Rangel-Martinez, D.; Nigam, K. D. P.; Ricardez-Sandoval, L. A. (96) Bhatti, S.; Manzoor, H. U.; Michel, B.; Bonilla, R. S.; Abrams,
Machine learning on sustainable energy: A review and outlook on R.; Zoha, A.; Hussain, S.; Ghannam, R. Revolutionizing Low-Cost
renewable energy systems, catalysis, smart grid and energy storage. Solar Cells with Machine Learning: A Systematic Review of
Chem. Eng. Res. Des. 2021, 174, 414−441. Optimization Techniques. Adv. Energy Sustainability Res. 2023, 4,
(77) Carvalho, T. P.; Soares, F. A.; Vita, R.; Francisco, R. d. P.; 2300004.
(97) Hassan, N. M.; Hamdan, A.; Shahin, F.; Abdelmaksoud, R.;
Basto, J. P.; Alcalá, S. G. A systematic literature review of machine
Bitar, T. An artificial intelligent manufacturing process for high-quality
learning methods applied to predictive maintenance. Comput. Ind.
low-cost production. Int. j qual. reliab. manage. 2023, 40 (7), 1777−
Eng. 2019, 137, 106024.
1794.
(78) Xiong, R.; Cao, J.; Yu, Q. Reinforcement learning-based real-
(98) Gu, G. H.; Noh, J.; Kim, I.; Jung, Y. Machine learning for
time power management for hybrid energy storage system in the plug-
renewable energy materials. J. Mater. Chem. A 2019, 7 (29), 17096−
in hybrid electric vehicle. Appl. Energy 2018, 211, 538−548.
17117.
(79) Wang, Y.; Seo, B.; Wang, B.; Zamel, N.; Jiao, K.; Adroher, X. C.
(99) Ahmad, T.; Madonski, R.; Zhang, D.; Huang, C.; Mujeeb, A.
Fundamentals, materials, and machine learning of polymer electrolyte Data-driven probabilistic machine learning in sustainable smart
membrane fuel cell technology. Energy and AI 2020, 1, 100014. energy/smart energy systems: Key developments, challenges, and
(80) Ramasubramanian, B.; Rao, R. P.; Chellappan, V.; future research opportunities in the context of smart grid paradigm.
Ramakrishna, S. Towards sustainable fuel cells and batteries with an Renew. Sust. Energy Rev. 2022, 160, 112128.
AI perspective. Sustainability. 2022, 14 (23), 16001. (100) Shen, Z. H.; Liu, H. X.; Shen, Y.; Hu, J. M.; Chen, L. Q.; Nan,
(81) Fredricks, J. L. Understanding Processing-Structure-Mechanical C. W. Machine learning in energy storage materials. Interdiscipli.
Property Relationships in Sustainable Biopolymer-Based Composites Mater. 2022, 1 (2), 175−195.
Using Design of Experiments and Machine Learning. (Doctoral (101) Ma, J.; Sahai, Y. Chitosan biopolymer for fuel cell applications.
dissertation, University of Washington), 2023. Carbohydr. Polym. 2013, 92 (2), 955−975.
(82) Pilania, G.; Iverson, C. N.; Lookman, T.; Marrone, B. L. (102) Khan, M. J.; Singh, N.; Mishra, S.; Ahirwar, A.; Bast, F.;
Machine-Learning-Based Predictive Modeling of Glass Transition Varjani, S.; Schoefs, B.; Marchand, J.; Rajendran, K.; Banu, J. R.;
Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Saratale, G. D.; Saratale, R. G.; Vinayak, V. Impact of light on
Copolymers. J.of Chem. Inf. and Mod. 2019, 59 (12), 5013−5025. microalgal photosynthetic microbial fuel cells and removal of
(83) Liu, R.; Kumar, A.; Chen, Z.; Agrawal, A.; Sundararaghavan, V.; pollutants by nanoadsorbent biopolymers: Updates, challenges and
Choudhary, A. A predictive machine learning approach for micro- innovations. Chemosphere 2022, 288, 132589.
structure optimization and materials design. Sci. Rep. 2015, 5 (1), (103) Admassie, S.; Ajjan, F.; Elfwing, A.; Inganäs, O. Biopolymer
11551. hybrid electrodes for scalable electricity storage. Mater. Horiz. 2016, 3
(84) Liu, Y.; Zhao, T.; Ju, W.; Shi, S. Materials discovery and design (3), 174−185.
using machine learning. Journal of Materiomics 2017, 3 (3), 159−177. (104) Verma, D.; Fortunati, E.; Jain, S.; Zhang, X. Biomass,
(85) Mairpady, A.; Mourad, A.-H. I.; Mozumder, M. S. Statistical Biopolymer-Based Materials, and Bioenergy: Construction, Biomedical,
and machine learning-driven optimization of mechanical properties in and Other Industrial Applications; Woodhead Publishing: 2019.
designing durable hdpe nanobiocomposites. Polymers. 2021, 13 (18), (105) Hasan, M. M.; Islam, M. D.; Rashid, T. U. Biopolymer-based
3100. electrolytes for dye-sensitized solar cells: A critical review. Energy Fuels
(86) Sharma, A.; Mukhopadhyay, T.; Rangappa, S. M.; Siengchin, S.; 2020, 34 (12), 15634−15671.
Kushvaha, V. Advances in computational intelligence of polymer (106) Mohiuddin, M.; Kumar, B.; Haque, S. Biopolymer composites
composite materials: machine learning assisted modeling, analysis and in photovoltaics and photodetectors. Biopolymer composites in
design. Arch. of Comput. Meth. in Eng. 2022, 29 (5), 3341−3385. electronics 2017, 459−486.
(87) Wu, S.; Kondo, Y.; Kakimoto, M.-a.; Yang, B.; Yamada, H.; (107) Roy, S.; Thakur, P.; Hoque, N. A.; Bagchi, B.; Sepay, N.;
Kuwajima, I.; Lambard, G.; Hongo, K.; Xu, Y.; Shiomi, J.; Schick, C.; Khatun, F.; Kool, A.; Das, S. Electroactive and high dielectric folic
Morikawa, J.; Yoshida, R. Machine-learning-assisted discovery of acid/PVDF composite film rooted simplistic organic photovoltaic self-
Energy Fuels 2024, 38, 1593−1617
charging energy storage cell with superior energy density and storage (125) Monisha, S.; Selvasekarapandian, S.; Mathavan, T.; Milton
capability. ACS Appl. Mater. Interfaces 2017, 9 (28), 24198−24209. Franklin Benial, A.; Manoharan, S.; Karthikeyan, S. Preparation and
(108) Sadasivuni, K. K.; Deshmukh, K.; Ahipa, T.; Muzaffar, A.; characterization of biopolymer electrolyte based on cellulose acetate
Ahamed, M. B.; Pasha, S. K.; Al-Maadeed, M. A.-A. Flexible, for potential applications in energy storage devices. J. Mater. Sci.
biodegradable and recyclable solar cells: a review. J. Mater. Sci. Mater. Mater. Electron. 2016, 27 (9), 9314−9324.
Electron. 2019, 30, 951−974. (126) Harikumar, M. E.; Batabyal, S. K. Fabrication of pectin
(109) Cavinato, L. M.; Fresta, E.; Ferrara, S.; Costa, R. D. Merging biopolymer-based biocompatible freestanding electrodes for super-
Biology and Photovoltaics: How Nature Helps Sun-Catching. Adv. capacitor applications. Polym. for Adv. Technol. 2023, 34 (9), 2890−
Energy Mater. 2021, 11 (43), 2100520. 2902.
(110) Fryń, P.; Bogdanowicz, K. A.; Górska, N.; Rysz, J.; Krysiak, P.; (127) Li, M.; Yu, Y.; Wu, H. Effect of Single/Mixed Model Solvents
Marzec, M.; Marzec, M.; Iwan, A.; Januszko, A. Hybrid materials on the Ternary Phase Diagrams of Pyrolytic Lignin, Model Solvent,
based on L, D-poly (lactic acid) and Single-Walled Carbon and Water. Energy Fuels 2020, 34 (12), 15355−15369.
Nanotubes as flexible substrate for organic devices. Polymers. 2018, (128) Li, M.; Zhang, M.; Yu, Y.; Wu, H. Ternary System of Pyrolytic
10 (11), 1271. Lignin, Mixed Solvent, and Water: Phase Diagram and Implications.
(111) Qi, Y.; Qu, J.; Moore, J.; Gollinger, K.; Shrestha, N.; Zhao, Y.; Energy Fuels 2018, 32 (1), 465−474.
Pradhan, N.; Tang, J.; Dai, Q. Interfacial passivation by polylactic acid (129) Kaur, S.; Dhillon, G. S. The versatile biopolymer chitosan:
in perovskite solar cells. Org. Electron. 2022, 106, 106543. potential sources, evaluation of extraction methods and applications.
(112) Zhang, T.-W.; Tian, T.; Shen, B.; Song, Y.-H.; Yao, H.-B. Critical reviews in microbiology 2014, 40 (2), 155−175.
Recent advances on biopolymer fiber based membranes for lithium- (130) Pagliano, G.; Ventorino, V.; Panico, A.; Pepe, O. Integrated
ion battery separators. Compos. Commun. 2019, 14, 7−14. systems for biopolymers and bioenergy production from organic
(113) Samsudin, A.; Lai, H.; Isa, M. Biopolymer materials based waste and by-products: a review of microbial processes. Biotechnol.
carboxymethyl cellulose as a proton conducting biopolymer electro- Biofuels 2017, 10 (1), 1−24.
lyte for application in rechargeable proton battery. Electrochim. Acta (131) Yu, Y.; Liu, D.; Wu, H. Formation and Characteristics of
2014, 129, 1−13. Reaction Intermediates from the Fast Pyrolysis of NaCl- and MgCl2-
(114) Zhang, S.; Ericsson, N.; Hansson, P.-A.; Sjödin, M.; Nordberg, Loaded Celluloses. Energy Fuels 2014, 28 (1), 245−253.
Å. Life cycle assessment of an all-organic battery: Hotspots and (132) Safari, F.; Javani, N.; Yumurtaci, Z. Hydrogen production via
opportunities for improvement. J. Clean. Prod. 2022, 337, 130454. supercritical water gasification of almond shell over algal and
(115) Boopathi, G.; Pugalendhi, S.; Selvasekarapandian, S.; agricultural hydrochars as catalysts. Int. J. Hydrogen Energy. 2018, 43
Premalatha, M.; Monisha, S.; Aristatil, G. Development of proton (2), 1071−1080.
conducting biopolymer membrane based on agar-agar for fuel cell. (133) Azadi, P.; Inderwildi, O. R.; Farnood, R.; King, D. A. Liquid
Ionics 2017, 23, 2781−2790. fuels, hydrogen and chemicals from lignin: A critical review. Renew.
(116) Aykol, M.; Herring, P.; Anapolsky, A. Machine learning for Sust. Energy Rev. 2013, 21, 506−523.
continuous innovation in battery technologies. Nat. Rev. Mater. 2020, (134) Liu, Y.; Li, G.; Hu, Y.; Wang, A.; Lu, F.; Zou, J.-J.; Cong, Y.;
5 (10), 725−727. Li, N.; Zhang, T. Integrated conversion of cellulose to high-density
(117) Kaka, F.; Keshav, M.; Ramamurthy, P. C. Optimising the aviation fuel. Joule 2019, 3 (4), 1028−1036.
photovoltaic parameters in donor-acceptor-acceptor ternary polymer (135) Akinwumi, A. R.; Nwinyi, O. C.; Ayeni, A. O.; Ahuekwe, E. F.;
solar cells using Machine Learning framework. Sol. Energy 2022, 231, Chukwu, M. N. An overview of the production and prospect of
447−457. polyhydroxyalkanote (PHA)-based biofuels: Opportunities and
(118) Rudhziah, S.; Ahmad, A.; Ahmad, I.; Mohamed, N. S. limitations. Scientific African 2022, 16, No. e01233.
Biopolymer electrolytes based on blend of kappa-carrageenan and (136) Xu, J.; Zhou, K.; Fu, J.; Tan, Z.; Qin, L.; Duan, P.; Xu, Y.;
cellulose derivatives for potential application in dye sensitized solar Kang, S. Near-zero-waste hydrogenolysis of poly(lactic acid) to
cell. Electrochim. Acta 2015, 175, 162−168. biofuel. Fuel 2023, 334, 126609.
(119) You, S.; Wang, H.; Bi, S.; Zhou, J.; Qin, L.; Qiu, X.; Zhao, Z.; (137) Tseng, H.-C.; Fujimoto, N.; Ohnishi, A. Biodegradability and
Xu, Y.; Zhang, Y.; Shi, X.; Zhou, H.; Tang, Z. A Biopolymer Heparin methane fermentability of polylactic acid by thermophilic methane
Sodium Interlayer Anchoring TiO2 and MAPbI3 Enhances Trap fermentation. Bioresour. Technol. 2019, 8, 100327.
Passivation and Device Stability in Perovskite Solar Cells. Adv. Mater. (138) Saha, B.; De, S.; Fan, M. Zr(O)Cl2 catalyst for selective
2018, 30 (22), 1706924. conversion of biorenewable carbohydrates and biopolymers to biofuel
(120) Rasal, A. S.; Korupalli, C.; Getachew, G.; Chou, T.-H.; Lee, precursor 5-hydroxymethylfurfural in aqueous medium. Fuel 2013,
T.-Y.; Ghule, A. V.; Chang, J.-Y. Towards green, efficient and stable 111, 598−605.
quantum-dot-sensitized solar cells through nature-inspired biopol- (139) Cheng, X.; Liu, Y.; Wang, K.; Yu, H.; Yu, S.; Liu, S. High-
ymer modified electrolyte. Electrochim. Acta 2021, 391, 138972. Efficient Conversion of Cellulose to Levulinic Acid Catalyzed via
(121) Yuan, X.; Zhao, Y.; Xie, D.; Pan, L.; Liu, X.; Duan, C.; Huang, Functional Brønsted-Lewis Acidic Ionic Liquids. Catal. Lett. 2022,
F.; Cao, Y. Polythiophenes for organic solar cells with efficiency 152 (4), 1064−1075.
surpassing 17%. Joule 2022, 6 (3), 647−661. (140) Khan, A. S.; Man, Z.; Bustam, M. A.; Kait, C. F.; Nasrullah, A.;
(122) Abdulwahid, R. T.; Aziz, S. B.; Kadir, M. F. Z. Environ- Ullah, Z.; Sarwono, A.; Ahamd, P.; Muhammad, N. Dicationic ionic
mentally friendly plasticized electrolyte based on chitosan (CS): liquids as sustainable approach for direct conversion of cellulose to
Potato starch (PS) polymers for EDLC application: Steps toward the levulinic acid. J. Clean. Prod. 2018, 170, 591−600.
greener energy storage devices derived from biopolymers. J. Energy (141) Forootan, M. M.; Larki, I.; Zahedi, R.; Ahmadi, A. Machine
Storage 2023, 67, 107636. learning and deep learning in energy systems: A review. Sustainability.
(123) Aziz, S. B.; Brza, M. A.; Mishra, K.; Hamsan, M. H.; Karim, W. 2022, 14 (8), 4832.
O.; Abdullah, R. M.; Kadir, M. F. Z.; Abdulwahid, R. T. Fabrication of (142) Alabi, T. M.; Aghimien, E. I.; Agbajor, F. D.; Yang, Z.; Lu, L.;
high performance energy storage EDLC device from proton Adeoye, A. R.; Gopaluni, B. A review on the integrated optimization
conducting methylcellulose: dextran polymer blend electrolytes. J. techniques and machine learning approaches for modeling, prediction,
Mater. Res. Technol. 2020, 9 (2), 1137−1150. and decision making on integrated energy systems. Renew. Enery
(124) Dannoun, E. M. A.; Aziz, S. B.; Abdulwahid, R. T.; Al-Saeedi, 2022, 194, 822−849.
S. I.; Nofal, M. M.; Sadiq, N. M.; Hadi, J. M. Study of MC:DN-Based (143) Rubavathy, S. J.; Kannan, N.; Dhanya, D.; Shinde, S. K.; Soni,
Biopolymer Blend Electrolytes with Inserted Zn-Metal Complex for N.; Madduri, A.; Mohanavel, V.; Sudhakar, M.; Sathyamurthy, R.
Energy Storage Devices with Improved Electrochemical Performance. Machine Learning Strategy for Solar Energy optimization in
Membranes 2022, 12 (8), 769. Distributed systems. Energy Rep. 2022, 8, 872−881.
Energy Fuels 2024, 38, 1593−1617
(144) Rodríguez, F.; Alonso-Pérez, S.; Sánchez-Guardamino, I.; (161) Jha, S.; Bandyopadhyay, S.; Mehta, S.; Yen, M.; Chagouri, T.;
Galarza, A. Ensemble forecaster based on the combination of time- Palmer, E.; Liang, H. Data-Driven Predictive Electrochemical
frequency analysis and machine learning strategies for very short-term Behavior of Lignin-Based Supercapacitors via Machine Learning.
wind speed prediction. Electr. Pow. Syst. Res. 2023, 214, 108863. Energy Fuels 2022, 36 (2), 1052−1062.
(145) Abualigah, L.; Zitar, R. A.; Almotairi, K. H.; Hussein, A. M.; (162) Wei, W.; Nan, S.; Wang, H.; Xu, S.; Liu, X.; He, R. Design and
Abd Elaziz, M.; Nikoo, M. R.; Gandomi, A. H. Wind, solar, and preparation of sulfonated polymer membranes for Zn/MnO2 flow
photovoltaic renewable energy systems with and without energy batteries with assistance of machine learning. J. Membr. Sci. 2023, 672,
storage optimization: A survey of advanced machine learning and 121453.
deep learning techniques. Energies 2022, 15 (2), 578. (163) Liu, Y.; Cheng, S.; Cross, J. S. Machine Learning Assisted
(146) Asha, P.; Mannepalli, K.; Khilar, R.; Subbulakshmi, N.; Chemical Process Parameter Mapping on Lignin Hydrogenolysis.
Dhanalakshmi, R.; Tripathi, V.; Mohanavel, V.; Sathyamurthy, R.; Energies 2023, 16 (1), 256.
Sudhakar, M. Role of machine learning in attaining environmental (164) Vinitha, N.; Vasudevan, J.; Gopinath, K. P. Bioethanol
sustainability. Energy Rep. 2022, 8, 863−871. production optimization through machine learning algorithm
(147) Wei, C.; Zhang, Z.; Qiao, W.; Qu, L. An adaptive network- approach: biomass characteristics, saccharification, and fermentation
based reinforcement learning method for MPPT control of PMSG conditions for enzymatic hydrolysis. Biomass Conv. and Biorefi. 2023,
wind energy conversion systems. IEEE Transact. on Power. Electro. 13 (8), 7287−7299.
2016, 31 (11), 7837−7848. (165) Castro Garcia, A.; Cheng, S.; McGlynn, S. E.; Cross, J. S.
(148) Hossain, E.; Khan, I.; Un-Noor, F.; Sikander, S. S.; Sunny, M. Machine Learning Model Insights into Base-Catalyzed Hydrothermal
S. H. Application of Big Data and Machine Learning in Smart Grid, Lignin Depolymerization. ACS Omega 2023, 8 (35), 32078−32089.
and Associated Security Concerns: A Review. IEEE Access 2019, 7, (166) Kabir, E.; Kaur, R.; Lee, J.; Kim, K.-H.; Kwon, E. E. Prospects
13960−13988. of biopolymer technology as an alternative option for non-degradable
(149) Akinpelu, D.; Adekoya, O.; Oladoye, P.; Ogbaga, C. C.; plastics and sustainable management of plastic wastes. J. Clean. Prod.
Okolie, J. A. Machine learning applications in biomass pyrolysis: from 2020, 258, 120536.
biorefinery to end-of-life product management. Digital Chem. Eng. (167) Awasthi, S. K.; Kumar, M.; Kumar, V.; Sarsaiya, S.; Anerao, P.;
2023, 8, 100103. Ghosh, P.; Singh, L.; Liu, H.; Zhang, Z.; Awasthi, M. K. A
(150) Jeon, P. R.; Moon, J.-H.; Ogunsola, N. O.; Lee, S. H.; Ling, J. comprehensive review on recent advancements in biodegradation
L. J.; You, S.; Park, Y.-K. Recent advances and future prospects of and sustainable management of biopolymers. Environ. Pollut. 2022,
thermochemical biofuel conversion processes with machine learning. 307, 119600.
Chem. Eng. J. 2023, 471, 144503. (168) Li, J.; Yu, X.; Martinez, E. E.; Zhu, J.; Wang, T.; Shi, S.; Shin,
(151) Kardani, N.; Hedayati Marzbali, M.; Shah, K.; Zhou, A.
S. R.; Hassan, S.; Guo, C. Emerging biopolymer-based bioadhesives.
Machine learning prediction of the conversion of lignocellulosic
Macromol. Biosci. 2022, 22 (2), 2100340.
biomass during hydrothermal carbonization. Biofuels 2022, 13 (6),
(169) Kaniuk, Ł.; Stachewicz, U. Development and advantages of
703−715.
biodegradable PHA polymers based on electrospun PHBV fibers for
(152) Ascher, S.; Watson, I.; You, S. Machine learning methods for
tissue engineering and other biomedical applications. ACS 2021, 7
modelling the gasification and pyrolysis of biomass and waste. Renew.
(12), 5339−5362.
Sust. Energy Rev. 2022, 155, 111902.
(170) Ebrahimi, F.; Ramezani Dana, H. Poly lactic acid (PLA)
(153) Hansen, S.; Mirkouei, A. In Past Infrastructures and Future
Machine Intelligence (MI) for Biofuel Production: A Review and MI- polymers: from properties to biomedical applications. Int. J. of Polym.
Based Framework; International Design Engineering Technical Mater. and Polym. Biomat. 2022, 71 (15), 1117−1130.
Conferences and Computers and Information in Engineering (171) Sharma, A.; Kaur, I.; Dheer, D.; Nagpal, M.; Kumar, P.;
Conference, American Society of Mechanical Engineers: 2018; p Venkatesh, D. N.; Puri, V.; Singh, I. A propitious role of marine
V004T05A022. source based PLS: Drug delivery and biomedical applications.
(154) Ç ınar, Z. M.; Abdussalam Nuhu, A.; Zeeshan, Q.; Korhan, O.; Carbohydr. Polym. 2023, 308, 120448.
Asmael, M.; Safaei, B. Machine learning in predictive maintenance (172) Yang, E.; Miao, S.; Zhong, J.; Zhang, Z.; Mills, D. K.; Zhang,
towards sustainable smart manufacturing in industry 4.0. Sustain- L. G. Bio-based polymers for 3D printing of bioscaffolds. Polymer Rev.
ability. 2020, 12 (19), 8211. 2018, 58 (4), 668−687.
(155) Cosgun, A.; Günay, M. E.; Yıldırım, R. Exploring the critical (173) Bibire, T.; Yilmaz, O.; Ghiciuc, C. M.; Bibire, N.; Dǎnilǎ, R.
factors of algal biomass and lipid production for renewable fuel Biopolymers for surgical applications. Coatings 2022, 12 (2), 211.
production by machine learning. Renew. Enery 2021, 163, 1299−1317. (174) Aznar, M.; Ubeda, S.; Dreolin, N.; Nerín, C. Determination of
(156) Sharma, V.; Tsai, M.-L.; Chen, C.-W.; Sun, P.-P.; Nargotra, P.; non-volatile components of a biodegradable food packaging material
Dong, C.-D. Advances in machine learning technology for sustainable based on polyester and polylactic acid (PLA) and its migration to
advanced biofuel production systems in lignocellulosic biorefineries. food simulants. Journal of Chromatography A 2019, 1583, 1−8.
Sci. Total Environ. 2023, 886, 163972. (175) Muller, J.; González-Martínez, C.; Chiralt, A. Combination of
(157) Ahmadi, P.; Raeesi, M.; Changizian, S.; Teimouri, A.; Poly(lactic) Acid and Starch for Biodegradable Food Packaging.
Khoshnevisan, A. Lifecycle assessment of diesel, diesel-electric and Materials 2017, 10 (8), 952.
hydrogen fuel cell transit buses with fuel cell degradation and battery (176) Sucinda, E. F.; Abdul Majid, M. S.; Ridzuan, M. J. M.; Cheng,
aging using machine learning techniques. Energy 2022, 259, 125003. E. M.; Alshahrani, H. A.; Mamat, N. Development and character-
(158) Ghoroghi, A.; Rezgui, Y.; Petri, I.; Beach, T. Advances in isation of packaging film from Napier cellulose nanowhisker
application of machine learning to life cycle assessment: a literature reinforced polylactic acid (PLA) bionanocomposites. Int. J. Biol.
review. Int. J. Life Cycle Assess. 2022, 27 (3), 433−456. Macromol. 2021, 187, 43−53.
(159) Adam, A. A.; Soleimani, H.; Shukur, M. F. B. A.; Dennis, J. O.; (177) Zhang, J.; Shishatskaya, E. I.; Volova, T. G.; da Silva, L. F.;
Abdulkadir, B. A.; Hassan, Y. M.; Yusuf, J. Y.; Shamsuri, N. A. B. A Chen, G.-Q. Polyhydroxyalkanoates (PHA) for therapeutic applica-
new approach to understanding the interaction effect of salt and tions. Mater. Sci. Eng. C 2018, 86, 144−150.
plasticizer on solid polymer electrolytes using statistical model and (178) Tyagi, P.; Mathew, R.; Opperman, C.; Jameel, H.; Gonzalez,
artificial intelligence algorithm. J. Non Cryst. Sol. 2022, 587, 121597. R.; Lucia, L.; Hubbe, M.; Pal, L. High-Strength Antibacterial
(160) Tian, P.; Liu, X.; Luo, K.; Li, H.; Wang, Y. Deep learning from Chitosan-Cellulose Nanocrystal Composite Tissue Paper. Langmuir
three-dimensional multiphysics simulation in operational optimization 2019, 35 (1), 104−112.
and control of polymer electrolyte membrane fuel cell for maximum (179) Aristri, M. A.; Lubis, M. A.; Iswanto, A. H.; Fatriasari, W.; Sari,
power. Appl. Energy 2021, 288, 116632. R. K.; Antov, P.; Gajtanska, M.; Papadopoulos, A. N.; Pizzi, A. Bio-
Energy Fuels 2024, 38, 1593−1617
Based Polyurethane Resins Derived from Tannin: Source, Synthesis, (198) Blanco-Gonzalez, A.; Cabezon, A.; Seco-Gonzalez, A.; Conde-
Characterisation, and Application. Forests 2021, 12 (11), 1516. Torres, D.; Antelo-Riveiro, P.; Pineiro, A.; Garcia-Fandino, R. The
(180) Alinejad, M.; Henry, C.; Nikafshar, S.; Gondaliya, A.; Bagheri, role of ai in drug discovery: challenges, opportunities, and strategies.
S.; Chen, N.; Singh, S. K.; Hodge, D. B.; Nejad, M. Lignin-Based Pharmaceuticals 2023, 16 (6), 891.
Polyurethanes: Opportunities for Bio-Based Foams, Elastomers, (199) Jan, Z.; Ahamed, F.; Mayer, W.; Patel, N.; Grossmann, G.;
Coatings and Adhesives. Polymers 2019, 11 (7), 1202. Stumptner, M.; Kuusk, A. Artificial intelligence for industry 4.0:
(181) Mowbray, M.; Savage, T.; Wu, C.; Song, Z.; Cho, B. A.; Del Systematic review of applications, challenges, and opportunities. Exp.
Rio-Chanona, E. A.; Zhang, D. Machine learning for biochemical Syst. with Appli. 2023, 216, 119456.
engineering: A review. Biochem. Eng. J. 2021, 172, 108054. (200) Andraju, N.; Curtzwiler, G. W.; Ji, Y.; Kozliak, E.;
(182) Abina, A.; Korošec, T.; Puc, U.; Zidanšek, A. Review of Ranganathan, P. Machine-Learning-Based Predictions of Polymer
Bioplastics Characterisation by Terahertz Techniques in the View of and Postconsumer Recycled Polymer Properties: A Comprehensive
Ensuring a Circular Economy. Photonics 2023, 10 (8), 883. Review. ACS Appl. Mater. Interfaces 2022, 14 (38), 42771−42790.
(183) Lee, S. Y.; Kim, H. U.; Chae, T. U.; Cho, J. S.; Kim, J. W.; (201) Tsui, T.-H.; van Loosdrecht, M. C.; Dai, Y.; Tong, Y. W.
Shin, J. H.; Kim, D. I.; Ko, Y.-S.; Jang, W. D.; Jang, Y.-S. A Machine learning and circular bioeconomy: Building new resource
comprehensive metabolic map for production of bio-based chemicals. efficiency from diverse waste streams. Bioresour. Technol. 2023, 369,
Nature catal. 2019, 2 (1), 18−33. 128445.
(184) D’Este, M.; Alvarado-Morales, M.; Angelidaki, I. Amino acids (202) Guizani, C.; Trogen, M.; Zahra, H.; Pitkänen, L.; Moriam, K.;
production focusing on fermentation technologies-A review. Bio- Rissanen, M.; Mäkelä, M.; Sixta, H.; Hummel, M. Fast and
technol. Adv. 2018, 36 (1), 14−25. quantitative compositional analysis of hybrid cellulose-based regen-
(185) Oyetunde, T.; Bao, F. S.; Chen, J.-W.; Martin, H. G.; Tang, Y. erated fibers using thermogravimetric analysis and chemometrics.
Cellulose. 2021, 28 (11), 6797−6812.
J. Leveraging knowledge engineering and machine learning for
(203) Al-Jarrah, R.; AL-Oqla, F. M. A novel integrated BPNN/SNN
microbial bio-manufacturing. Biotechnol. Adv. 2018, 36 (4), 1308−
artificial neural network for predicting the mechanical performance of
1315.
green fibers for better composite manufacturing. Comp. Struct. 2022,
(186) López-Guajardo, E. A.; Delgado-Licona, F.; Á lvarez, A. J.;
289, 115475.
Nigam, K. D.; Montesinos-Castellanos, A.; Morales-Menendez, R. (204) Hasnain, M. S.; Ahmed, S. A.; Alkahtani, S.; Milivojevic, M.;
Process intensification 4.0: A new approach for attaining new, Kandar, C. C.; Dhara, A. K.; Nayak, A. K. Biopolymers for drug
sustainable and circular processes enabled by machine learning. Chem. delivery. Advanced biopolymeric systems for drug delivery 2020, 1−29.
Eng. Processing-Process Intens. 2022, 180, 108671. (205) Fazal, T.; Murtaza, B. N.; Shah, M.; Iqbal, S.; Rehman, M.-u.;
(187) Khaleghi, M. K.; Savizi, I. S. P.; Lewis, N. E.; Shojaosadati, S. Jaber, F.; Dera, A. A.; Awwad, N. S.; Ibrahium, H. A. Recent
A. Synergisms of machine learning and constraint-based modeling of developments in natural biopolymer based drug delivery systems. RSC
metabolism for analysis and optimization of fermentation parameters. Adv. 2023, 13 (33), 23087−23121.
Biotechnol. J. 2021, 16 (11), 2100212. (206) Woodley, J. M. Accelerating the implementation of
(188) Pandey, A. K.; Park, J.; Ko, J.; Joo, H.-H.; Raj, T.; Singh, L. K.; biocatalysis in industry. Appl. microbiol. and biotech. 2019, 103 (12),
Singh, N.; Kim, S.-H. Machine learning in fermentative biohydrogen 4733−4739.
production: Advantages, challenges, and applications. Bioresour.
Technol. 2023, 370, 128502.
(189) Sampaio, P. S.; Fernandes, P. Machine Learning: A Suitable
Recommended by ACS
Method for Biocatalysis. Catalysts. 2023, 13 (6), 961.
(190) Khan, A. Z.; Bilal, M.; Rasheed, T.; Iqbal, H. M. Navigating the Expansive Landscapes of Soft Materials: A
Advancements in biocatalysis: From computational to metabolic User Guide for High-Throughput Workflows
engineering. Chin. J. Catal. 2018, 39 (12), 1861−1868. Erin C. Day, Abigail S. Knight, et al.
(191) Vasina, M.; Kovar, D.; Damborsky, J.; Ding, Y.; Yang, T.; DECEMBER 05, 2023
deMello, A.; Mazurenko, S.; Stavrakis, S.; Prokop, Z. In-depth analysis ACS POLYMERS AU READ
of biocatalysts by microfluidics: An emerging source of data for
machine learning. Biotechnol. Adv. 2023, 66, 108171. Using Active Learning for the Computational Design of
(192) Löfgren, J.; Tarasov, D.; Koitto, T.; Rinke, P.; Balakshin, M.; Polymer Molecular Weight Distributions
Todorović, M. Machine Learning Optimization of Lignin Properties
in Green Biorefineries. ACS Sustain. Chem. Eng. 2022, 10 (29), 9469− Haifan Zhou, Hanyu Gao, et al.
DECEMBER 25, 2023
9479.
ACS ENGINEERING AU READ
(193) Patnode, K.; Rasulev, B.; Voronov, A. Synergistic Behavior of
Plant Proteins and Biobased Latexes in Bioplastic Food Packaging
Materials: Experimental and Machine Learning Study. ACS Appl. PolyID: Artificial Intelligence for Discovering Performance-
Mater. Interfaces 2022, 14 (6), 8384−8393. Advantaged and Sustainable Polymers
(194) Jiang, Z.; Hu, J.; Marrone, B. L.; Pilania, G.; Yu, X. A Deep A. Nolan Wilson, Michael F. Crowley, et al.
Neural Network for Accurate and Robust Prediction of the Glass OCTOBER 19, 2023
Transition Temperature of Polyhydroxyalkanoate Homo- and MACROMOLECULES READ
Copolymers. Materials 2020, 13 (24), 5701.
(195) Paula, A. J.; Ferreira, O. P.; Souza Filho, A. G.; Filho, F. N.; Open Macromolecular Genome: Generative Design of
Andrade, C. E.; Faria, A. F. Machine learning and natural language Synthetically Accessible Polymers
processing enable a data-oriented experimental design approach for
producing biochar and hydrochar from biomass. Chem. Mater. 2022, Seonghwan Kim, Nicholas E. Jackson, et al.
34 (3), 979−990. MARCH 29, 2023
(196) Gianti, E.; Percec, S. Machine Learning at the Interface of ACS POLYMERS AU READ
Polymer Science and Biology: How Far Can We Go? Biomacromo-
lecules 2022, 23 (3), 576−591.
(197) Stuart, S.; Watchorn, J.; Gu, F. X. Sizing up feature descriptors
Get More Suggestions >
for macromolecular machine learning with polymeric biomaterials.
Npj Comput. Mater. 2023, 9 (1), 102.
Energy Fuels 2024, 38, 1593−1617

Biobased Polymer

Uploaded by

Copyright:

Available Formats

Biobased Polymer

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Biobased Polymer

Uploaded by

Copyright:

Available Formats

This article is licensed under CC-BY 4.

Advances, Synergy, and Perspectives of Machine Learning and

Cite This: Energy Fuels 2024, 38, 1593−1617 Read Online

ACCESS Metrics & More Article Recommendations

ABSTRACT: This review illuminates the pivotal synergy between

1. INTRODUCTION being made.21,22 Table 1 shows the Source and Overview of

property or feature ML’s role in enhancement potential impact references

Figure 1. Biobased polymers process in the fuel industry.

Figure 2. ML enhancement process of biopolymer in energy applications.

Figure 3. ML process in biobased polymer for biochemical production.

You might also like