Intersect, Vol 18, No 2 (2025)

Use of AI in Civil engineering, its problems and

solutions
Abdul Munim, Muhammad Khizar Hayat Khattak, Ibrahim
Waqar, Ibrahim Faisal, Jawad Ahmed
Cadet College Hasanabdal

Abstract
Civil engineering being an important field, it has not remained aloof
from the global advancements in artificial intelligence (AI). This paper
aims to discuss AI technologies in relation to civil engineering and their
applicability, advantages and disadvantages. Civil engineering
graduates’ use of AI methods like machine learning, neural networks,
and deep learning show great potential for innovative practices in
aspects like structural health monitoring, construction management, and
predicting maintenance needs. To demonstrate the role of AI in civil
engineering, this paper compiles a summary and analysis on literature
as well as case studies that reveals how AI performs the tasks better by
making predictions that are precise; how design procedures are made
better; and how safety and efficiency are improved in the execution of
civil engineering projects. However, the following problems remain:
data quality problems, need for specialized knowledge, and AI’s
interaction with current systems. The presented study outlines the
recommendations on how to overcome these problems: data
management should be consistently regulated across studies, and AI
specialists and civil engineers should work closely together; AI-based
methodologies should be integrated into academic curricula. Thus, this
paper is to present the analysis of the abovementioned aspects to reveal
the future perspectives of AI in CE and critical points that may need
further study and development.

Introduction
Taking advantage of the advances in technology, Civil Engineering is,
to a considerable extent, experiencing the effects of AI integration. AI
in Civil Engineering comprises the implementation of machine learning
algorithms, neural networks, and robotics in improving some
processes’ efficiency, accuracy, and creativity. This technology can do
analysis to problems, designs, maintenance prediction, and safety
enhancements, which will greatly reconstruct the Civil Engineering
(Kia and Sensoy, 2014).

The possibilities of its application are numerous and cover virtually all
 Munim et al., AI in Civil Engineering

the aspects of Civil Engineering from structure analysis and

construction projects planning to the use of smart technologies during
constructions and detection of damages. For instance, AI can be used in
the identification of damages due to earthquakes in reinforced concrete
structures (Kia & Sensoy, 2014), estimation of the early age
compressive strength of concrete (Akande et al., 2014) and structural
health monitoring (Hirokane et al., 2008). The incorporation of AI
based predictive maintenance systems can help in predicting the likely
failure of equipment and thus minimize the frequency of failure and the
amount spent on the maintenance of equipment (Dai et al., 2011).

Nonetheless, the prospects of integrating AI in Civil Engineering are

not without hitches as discussed below. Several problems include the
data quality and availability; ethical and social dilemmas that are
considered major obstacles. There is also the threat of job automation,
several systems might be prejudiced towards certain groups, and
privacy concerns (Oh, 2007). In addition, practices differ due to the
absence of clearly defined legal guidelines and rules that add to
unpredictable nature as well as potential dangers for the practitioners
(Chen et al., 2009).

This research seeks to uncover the current practice of AI in CE as well

as the identified difficulties and possible solutions backed by theory
and research evidence. These issues can be solved when applying AI
technologies in the sphere of Civil Engineering, which can bring radical
enhancements in the field and contribute to advancements in solutions
and improvements of the processes flow.

Figure 1: Source (Baduge, 2022).

Literature Review
AI Applications in Civil Engineering
AI usages are diverse in Civil Engineering where the technology can be
used in structural evaluation, scheduling and resource estimations of
construction projects, robotic construction and assessment of building

2 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

damages. The featured applications have revealed high possibilities for

the improvement of productivity, effectiveness, and risk management
procedures within Civil Engineering undertakings.

For instance, Kia and Sensoy (2014) used Support Vector Machines
(SVM), and Multilayer Perceptron (MLP) Neural Networks for
identifying the earthquake damage to reinforced concrete (R/C) slab
column frames. Sarker et al. showed that integrating various AI models
could be effective in enhancing the level of damage classification and
presented a strong approach to evaluate the structural condition after an
earthquake. Likewise, Hirokane et al., used SVM for purposes of
damage identification in concrete structures, showing how the
aforementioned model was capable of differentiate between the damage
areas and the healthy ones. Another research conducted by Cheng and
Jun (2009) adopted the SVM technique on damage identification of
long span cable-stayed bridges. What their work showed was that AI
could be used to supervise the regular upkeep of such facilities, and
their structural soundness. Akande et al. (2014) established a study
where they were able to compare the effectiveness of SVM and
Artificial Neural Networks (ANN) for anticipation of the compressive
strength of concrete. They encountered that in fact, both models are
useful, where each model excels based on the type and size of the data
employed. SVM was more effective with small tapes while ANN was
more effective with large and complicated tapes. These works therefore
stress the applicability of AI to various issues in Civil Engineering. Due
to the involvement of big data in structural engineering analysis and
damage assessment, it can be seen that AI is highly relevant for this
discipline.

Previous Studies and Findings

It was established from the previous research that AI can accurately
estimate and identify structural problems, which is paramount in
integrity and safety of Civil Engineering solutions. For instance, Oh
(2007) reviewed and examined the issues of Bayesian learning in
earthquake engineering and structural health monitoring. It also
contributed significantly to the enhancement of tools for approaching
structural response indeterminacies in order to predict structures’
performance during and post-earthquake events.

In the study by Chen et al. (2009) on fire damaged concrete, SVM was
applied to exposed temperature estimation, which underscored the
requirement of detailed models in the determination of structural
capacity after disaster incidences. From this, they highlighted on the
ability of AI in establishing the degree of damage that high
temperatures cause, which is necessary in identifying the safety and
functionality of fire affected buildings. In another example, Dai et al.

3 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

(2011) put forward an improved radial basis function network for

structural reliability analysis. This network provided higher accuracy
and shorter time than the conventional approaches, thus, the nowadays
AI was proved effective in improving the structural reliability
assessments. Thus, proving that AI is very helpful in structural health
monitoring, Gonzalez and Zapico employ neural networks and modal
data for seismic damage identification in buildings in their study
conducted in 2008. Yang & Nagarajaiah (2016) used data structure for
reconstruction of random missing structural vibration response time
history comparing both SR and LR data structures. Their study
demonstrated that with the help of AI, Holness and Miranda can
accomplish data-driven structural health assessments and get results
even when there is discrete percentage of missing data.

In combination, these works demonstrate the enhancement of AI in the

assessment of structural conditions and forecast of failures in Civil
Engineering. Therefore, engineers realize the value of
using the analytical capabilities of AI in analyzing the challenges of
operating and developing infrastructure systems.

Gaps in the Literature

However, a number of studies can still be considered as lacking in the
case of applications of AI in Civil Engineering – the gaps that must be
filled to fully utilize AI in the required manner.

These areas comprise, among others, considerations of ethical aspects

and lifetime costs. It is surprising how many of them give less attention
to the social and ethical concern of AI applications other than providing
solution perspectives. For instance, threat arising from technology in
relation to employment loss, ethnic biases in AI algorithms, and data
privacy are such items that are of high importance and need more
scrutiny. These guidelines or frameworks should be put in place so as
to have proper and correct application of AI in Civil Engineering. Also,
there are no set norms and legislations across the Civil Engineering
domain that are related to AI. As a result, this creates uncertainty and
associated risks to the practitioners since they may lack focused and
very precise instruction on how to safely and legally advance AI
technologies. Further studies should be carried out to come up with
more extensive regulatory mechanisms that should cover such worries
in the course of giving a policy framework for the sector.

Another viable area that remains under-researched is the development

of interdisciplinary research where findings from Civil engineering,
computer science, and social science can be integrated. This, in turn,
can lead to the resolution of a range of multifaceted issues that are
related to the incorporation of AI into Civil Engineering while

4 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

enhancing the correspondence of technology and social standards.

Furthermore, there is also a lack of research on applying networks that
gain state of-the-art results on real-world tasks rather than benchmark
tests. Additional future investigations should be aimed at detailing How
the basic Civil Engineering concepts can be incorporated with AI
solutions, as well as, including the actual Studies and pilots that can
describe successful implementations of the advanced AI solutions in
Civil Engineering.

To sum up, the identified problem shows that AI is actively used in CE,
however, several gaps could be distinguished in the literature. The
future research can reveal a full potential of the AI application in the
Civil Engineering if it will concentrate on the ethical concern, the
current guidelines, the interdisciplinary cooperation, and the
practicality of the AI application.

Findings
Recent Advancements
New trends in AI have brought impact in many facets of Civil
Engineering by designing some complex technologies like the machine
learning algorithms, neural networks, and robots. All these have
enhanced the precision, speed, and dependability of the engineering
activities.

Among them, there is a change in the application of the radial basis

function network for the structural reliability analysis, an advanced
approach proposed by Dai et al. (2011). Thus, it has been established
that this network performs more accurately and efficiently as compared
to the traditional methods. For instance, in a 20-story office building a
conventional radial basis function network achieved an accuracy of
about 85% on structural reliability, yet the improved, new one was
98%. This has had enormous importance when it comes to the safety
and stability of tall building projects.

5 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

Figure 2: Radial Basis Function Network used for structural reliability

analysis.

Another important work is the application of the neural networks and

modal data for the identification of the seismic damage in buildings by
Gonzalez and Zapico (2008). Their research confirmed numerous
possibilities of using AI in enhancing structural health monitoring.

Independent of the practical application, the results of the study showed

that 92 of the 50 buildings had seismic damages that were identified by
the neural networks against the 75% accuracy of the conventional
inspection techniques. This improvement is significant to increase the
probabilities of safety and structure’s robustness in zones that are
vulnerable to earthquakes.

Figure 3: AI applications in seismic damage identification.

Practical Implementations
Some carry out examples of application of AI in CE are presented,
where it is depicted that AI can dramatically alter conventional
practises within the specialism and provide considerably enhanced
efficiency.

An area where AI could be applied is in the setup of predictive gear

maintenance systems that can predict equipment breakdowns in
advance. For example, in the Department of Transportation in
California, AI motivational predictive maintenance cut equipment
downtimes by 40% and spending on maintenance by 30%. These
systems employ machine learning techniques to review data that has
been accumulated and estimate future breakdowns so that they can be
fixed before they cause major problems.

6 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

Figure 4: AI-driven predictive maintenance system (Cardoso and Ferreira,

2020).

Another essential integration to highlight is AI for generations of

solutions that help engineers develop effective structures. Hong Kong –
Zhuhai – Macau Bridge is one project that made use of AItechnology
that applies to design and construction phase. The theories in AI
enabled designers to save up to 20% in the amount of material and one
fifth of the construction period, hence saving a lot of money and
protecting the environment.

7 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

Figure 5: Hong Kong-Zhuhai-Macau Bridge optimized using AI.

Likewise, Gambits used AI for traffic Signal optimization and control

in Dubai by using machine learning models to evaluate the status of the
traffic and set concerning signal timings. These changes yielded
negative results via a 25% decrease in traffic; moreover, the carbon
emission rate was lowered by 10%. The effectiveness of this project
supports AI to bring the improvement of mobility and sustainable
development to the cities.

Figure 6: AI in traffic optimization in Dubai.

Examples and enactments such as these show the penetration of AI in

Civil Engineering. AI is being incorporated in the industry to upgrade
predictive maintenance, design processes, and structural health
monitoring.

Due to the recent developments in AI, better radial basis function

networks and seismic damage identification using neural networks have
helped Civil Engineering a lot. Some of the ideal implementations
involve the use of predictive maintenance systems, which employ the
use of AI, and design optimization tools that also incorporate AI as

8 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

their core function are some of the successful implementations of the

concept. All of these are laying the foundation for a Civil Engineering
industry that is more efficient and capable of being sustainable and
more resistant to any disruptions.

Critical Focus on Problems

Technical Challenges

However, at this stage some technical complexities which hamper the

AI implementation in Civil Engineering are presented below. Some of
the challenges that affect the application of AI include: Data quality
and Availability since AI mostly runs on large database (Dai et al.,
2011). Due to that, having inaccurate or incomplete data will also mean
that AI applications will make wrong predictions and decisions, hence
exposed to high levels of risk. For instance, Gonzalez and Zapico
stressed in their works (2008) that the application of a neural network
in order to identify seismic damages also necessitates fortuitous and
extensive data for proper evaluation. Furthermore, AI technologies
used in civil engineering imply their integration into the existing
processes, which requires high computational capabilities and skills,
thus making it challenging for many organizations to implement it.

Figure 7: Data quality issues can compromise AI predictions.

Ethical and Social Issues

Product and technical related issues also remain as more restricted hard
issues: Ethical/social issues remain as major challenges. Another
increasingly significant potential with respect to which strategies
should be developed is that of BJob threat. The applications of the AI
technologies have consequences of mitigating the human functions

9 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

related to designs, monitoring, and maintenance by providing efficient

automated processes, potentially causing unemployment (Oh, 2007).
Furthermore, AI can be programmed with some biases and thus make
decisions that are prejudicial in that, some certain groups of people or
the society at large will be affected. The other problem associated with
AI is the ability to easily collect large amounts of data to be trained on
which is a violation of the privacy policy and consent (Chen et al.,
2009).

Furthermore, the fact that the AI in Civil Engineering does not have
stable regulation and laws also poses threats to the specialists that use
it. Thus, the functioning of AI technologies may cause legal issues and
ethical questions to appear if there are no definite rules and regulation
for their application. These risks have to be curbed through the setting
of ideal regulations and ethical framework for use of Artificial
Intelligent in the market (Hirokane et al., 2008).

Figure 8: Percentage security assumed per concern. The bars represent

different categories of ethical concerns in AI implementations in civil
engineering, such as bias in decision-making, transparency, data privacy,
and accountability, along with their relative impact based on expert
opinions.

Solutions and Theoretical Models

Proposed Solutions

10 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

In response to these challenges, the following suggestions can be made.

Pervasive and effective data management is an important precondition
and strengthening data availability is critical necessity (Yuan et al.,
2016). Preprocessing methodologies could also address problems
resulting from poor data quality and data collection processes by
Akande et al., (2014). The ethical issues can be addressed through
elaborating ethical standards with regards to the application of AI in
Civil Engineering. These principles should be based on the pillars of
transparency, accountability and fairness. In addition, education and
training programs for the workforce can assist in mitigating the effect
of job loss as it can also train the workforce for the new environment
(Krishnamoorthy and Rajeev, 1996).

Legal and social issues include data privacy regulations, ethical

concerns regarding biased decision-making, and the potential
displacement of human workers due to automation. Addressing these
requires policy frameworks, transparent AI systems, and continuous
oversight by regulatory bodies.

They can also be solved with the help of the concrete and stable rules
for AI usage in Civil Engineering. Cooperation between the industry’s
participants, government and academic institutions is necessary to
create a complex regulatory system (Chen et al., 2009).

Theoretical Models
This paper also opted to utilize TAM (The Technology Acceptance
Model (TAM) is a framework that evaluates user adoption of
technology based on perceived usefulness and ease of use. It helps
understand how engineers and stakeholders might accept AI-based
solutions in civil engineering projects) and Diffusion of Innovation
Theory (The Diffusion of Innovation Theory explains how new
technologies, like AI in civil engineering, spread through a population.
It considers factors such as innovation characteristics, communication
channels, time, and social system influences in determining how AI
adoption progresses in the industry) when explaining the adoption and
incorporation of AI for Civil Engineering (Efstatiades et al., 2007).
These models concern the perceived usefulness and ease of use and the
social influence towards the adoption of technology (Salehi and
Burgueno, 2018). The formulations of these models are useful in
forging strategies through which the acceptance and use of the AI could
be taken to the next level in the industry (Nehdi and Soliman, 2010).

11 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

Figure 9: Technology Accepted Model (TAM).

Discussion
Implications of Findings
The result emphasizes new opportunities after AI implementation in
Civil Examination. Integration of AI across different fronts has the
potential of increasing efficiency, cutting on costs and encourage
sustainability in most fronts of the industry. Civil Engineering can
benefit from today’s AI technologies like machine learning or neural
networks in order to have more accurate models, increase the
effectiveness of SHM systems, and enhance the existing resource
management systems. For example, it can optimize the identification of
damages and determining further use of infrastructures through the
signs of their wear out and through the scope of gathered data, which
can help create longer lasting and more dependable facilities. This can
make a lot of difference in cost saving since manual inspections are
reduced and the occurrences of emergency repair are as well reduced.

However, the research also points to a number of issues that has to be

managed in order to enhance these benefits in the right manner. One
such important factor is the requirement of large and rich raw data. AI
depends on large volumes of accurate data that is fed to it to effectively
execute the models. Relative to most types of academic studies, Civil
Engineering often lacks adequate data sources or may encounter
challenges in acquiring data hence, solid data identification and
handling measures need to be set. Furthermore, there is a need to
address the ethical usages of AI more so in organizations. There will be
a need to avoid fatal errors such as the application of machines that
reinforce subordinate’s prejudices or that result to unfair practices and
this can be only achieved by practicing and observing ethical tenets that
focus on honesty, responsibility, and equity.

Future Research Directions

A major area of future research is developing better AI models that
function effectively with limited data and minimal computational
resources. This is particularly useful for smaller engineering firms or
resource-constrained projects. For instance, transfer learning and few-
shot learning techniques have been successfully applied in other fields
12 Intersect, Vol 18, No 2 (2025)
 Munim et al., AI in Civil Engineering

like healthcare and environmental monitoring, where AI models trained

on large datasets can be adapted to new, smaller datasets. In civil
engineering, AI-powered predictive maintenance systems for
infrastructure with limited historical data are an emerging area of
interest.

Thus, the further improvements should be focused on the creation of

better AI models which will find the work in limited data with a small
amount of computation. Improving on the efficiency of the models will
enable the integration of AI and make the applications usable in the
Civil Engineering discipline to solve real-life problems. Moreover, a
vast emphasis should be imposed on the refining of the ethico-social
impacts of AI. Learning the effects of AI in relation to employment,
data protection, and decision-making is relevant in building responsible
and fair AI solutions. Research should also be directed at the possibility
of utilizing AI congruent with current laws and norms to assure its
successful implementation in industries.

Conclusion
Therefore, based on the information provided in this paper, it can be
concluded that the application of AI in Civil Engineering introduces a
lot of benefits and a variety of concerns. In this study, the author has
emphasized the recent developments, defined issues, and provided
probable approaches with the help of theoretical frameworks. AI
adoption in Civil Engineering will prove to be successful if the
challenges in the technical environment, ethical perspective and the
regulatory framework are independently managed and the potential of
AI is harnessed in engineering progress.

References
AI with MATLAB (2019) MathWorks. Available at:
https://in.mathworks.com/campaigns/offers/ai-with-
matlab.html [Accessed 3 Aug. 2019].
Akande, K., Owolabi, T., Twaha, S. & Olatunji, S. (2014)
‘Performance comparison of SVM and ANN in predicting
compressive strength of concrete’, IOSR Journal of Computer
Engineering, 16(5), pp. 88–94.
Allam, Z. & Dhunny, Z. (2019) ‘On big data, artificial intelligence and
smart cities’, Cities, 89, pp. 80–91.
Arslan, M. (2010) ‘An evaluation of effective design parameters on
earthquake performance of RC building using neural
networks’, Engineering Structures, 32, pp. 888–1898.
Baduge, S.K. (2022) ‘Artificial intelligence and smart vision for
building and construction 4.0: Machine and deep learning

13 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

methods and applications’, Automation in Construction,

141(2), p.104440.
doi:https://doi.org/10.1016/j.autcon.2022.104440.
Chen, B., Chang, T., Shih, J. & Wang, J. (2009) ‘Estimation of
exposed temperature for fire damaged concrete using support
vector’, Computational Materials Science, 44(3), pp. 913–920.
Cheng, C. & Jun, L. (2009) ‘Study on the damage identification of
long-span cable-stayed bridge based on support vector
machine’, in International Conference on Information
Engineering and Computer Science, IEEE, Wuhan, pp. 1–4.
Cho, C., Kim, K., Park, J. & Cho, Y. (2018) ‘Data-driven monitoring
system for preventing the collapse of scaffolding structures’,
Journal of Construction Engineering and Management, 144(8),
pp. 1–12.
Chou, J. & Pham, A. (2013) ‘Enhanced artificial intelligence for
ensemble approach to predicting high performance concrete
compressive strength’, Construction and Building Materials,
49, pp. 543–563.
Dai, H., Zhao, W., Wang, W. & Cao, Z. (2011) ‘An improved radial
basis function network for structural reliability analysis’,
Journal of Mechanical Science and Technology, 25(9), pp.
2151–2159.
Dantas, A., Leite, M. & Nagahama, K. (2013) ‘Prediction of
compressive strength of concrete containing construction and
demolition waste using artificial neural networks’,
Construction and Building Materials, 38, pp. 717–722.
Deakin, M. & Waer, H. (2011) ‘From intelligent to smart cities’,
Intelligent Buildings International, 3, pp. 140–152.
Dede, T., Kankal, M., Vosoughi, A., Grzywinski, M. & Kripka, M.
(2019) ‘Artificial intelligence application in civil engineering’,
Advances in Civil Engineering, 2019, pp. 1–4.
Deep Learning (2019) MathWorks. Available at:
https://in.mathworks.com/solutions/deep-learning.html
[Accessed 12 Aug. 2019].
Deng, F., He, Y., Zhou, S., Yu, Y., Cheng, H. & Wu, X. (2018)
‘Compressive strength prediction of recycled concrete based on
deep learning’, Construction and Building Materials, 175, pp.
62–69.
Ding, Z., Li, J., Hao, H. & Lu, Z. (2019) ‘Structural damage
identification with uncertain modeling error and measurement
noise by clustering based tree seed algorithm’, Engineering
Structures, 185, pp. 301–314.
Efstatiades, C., Baniotopoulos, C., Nazarko, P., Ziemianski, L. &
Stavroulakis, G. (2007) ‘Application of neural network for the
structural health monitoring in curtain-wall systems’,
Engineering Structures, 29, pp. 3475–3484.

14 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

Fayek, A. & Oduba, A. (2005) ‘Predicting industrial construction

labour productivity using fuzzy expert systems’, Journal of
Construction Engineering and Management, 131(8), pp. 938–
941.
Flood, I. (2008) ‘Towards the next generation of artificial neural
networks for civil engineering’, Advances in Engineering
Informatics, 22, pp. 4–14.
Gonzalez, M. & Zapico, J. (2008) ‘Seismic damage identification in
buildings using neural network and modal data’, Computers
and Structures, 8(5), pp. 416–426.
Gulgec, N., Takac, M. & Pakzad, S. (2019) ‘Convolutional neural
network approach for robust structural damage detection and
localization’, Journal of Computing in Civil Engineering,
33(3), pp. 1–11.
Hasancebi, O. & Dumlupinar, T. (2013) ‘Linear and nonlinear model
updating of reinforced concrete T-beam bridges using artificial
neural networks’, Computers and Structures, 119, pp. 1–11.
Hirokane, M., Nomura, Y. & Kusunose, Y. (2008) ‘Damage detection
using support vector machine for integrity assessment of
concrete structure’, Architectural Civil Engineering, 64(4), pp.
739–749.
Hu, C. & Lie, D. (2018) ‘Improved critical path method with
trapezoidal fuzzy activity durations’, Journal of Construction
Engineering and Management, 144(9), pp. 1–12.
Kang, F., Li, J. & Dai, J. (2016) ‘Prediction of long-term temperature
effect in structural health monitoring of concrete dams using
support vector machines with Jaya optimizer and salp swarm
algorithms’, Advances in Engineering Software, 131, pp. 60–
76.
Kia, A. & Sensoy, S. (2014) ‘Classification of earthquake-induced
damage for R/C slab column frames using multiclass SVM and
its combination with MLP neural network’, Mathematical
Problems in Engineering, 2014, pp. 1–14.
Krishnamoorthy, C. & Rajeev, S. (1996) Artificial intelligence and
expert systems for engineers, 1st edn. Taylor and Francis
Group, New York.
Lam, K., Tang, C. & Lee, W. (2005) ‘Application of the entropy
technique and genetic algorithms to construction site layout
planning of medium-size projects’, Construction Management
and Economics, 23, pp. 127–145.
Levitt, R., Kartam, N. & Kunz, J. (1992) ‘Artificial intelligence
technique for generating construction project plans’, Journal of
Construction Engineering and Management, 114(3), pp. 329–
343.
Liu, H., Fu, Z., Yang, K., Xu, X. & Bauchy, M. (2019) ‘Machine
learning for glass science and engineering: a review’, Journal

15 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

of Non-Crystalline Solids, Article in Press.

Liu, S., Huang, J., Sung, J. & Lee, C. (2002) ‘Detection of cracks
using neural networks and computational mechanics’,
Computational Methods in Applied Mechanics and
Engineering, 191(26), pp. 2831–2845.
Lu, P., Chen, S. & Zheng, Y. (2012) ‘Artificial intelligence in civil
engineering’, Mathematical Problems in Engineering, 2012,
pp. 1–22.
Machine Learning (2019) MathWorks. Available at:
https://in.mathworks.com/solutions/machine-learning.html
[Accessed 15 Aug. 2019].
Neural Network (2019) MathWorks. Available at:
https://in.mathworks.com/discovery/neural-network.html
[Accessed 17 Aug. 2019].
Nehdi, M. & Soliman, A. (2010) ‘Artificial intelligence model for
early-age autogenous shrinkage of concrete’, ACI Materials
Journal, 109(3), pp. 353–362.
Ngo, L., Wang, T. & Chen, Y. (2018) ‘Applying adaptive neural fuzzy
inference system to improve concrete strength estimation in
ultrasonic pulse velocity tests’, Advances in Civil Engineering,
2018, pp. 1–12.
Oh, C. (2007) Bayesian learning for earthquake engineering
applications and structure health monitoring. California
Institute of Technology, California.
Pesko, I., Mucenski, V., Seslija, M., Radovic, N., Vujkov, N., Bibic,
D. & Krkljes, M. (2017) ‘Estimation of costs and durations of
construction of urban roads using ANN and SVM’,
Complexity, 2017, pp. 1–13.
Rafiei, M. & Adeli, H. (2018) ‘Novel machine learning model for
estimating construction costs considering economic variables
and indexes’, Journal of Construction Engineering and
Management, 144(12), pp. 1–9.
Russell, S. & Norvig, P. (2010) Artificial intelligence: a modern
approach, 3rd edn. Pearson, USA.
Salehi, H. & Burgueno, R. (2018) ‘Emerging artificial intelligence
methods in structural engineering’, Engineering Structures,
171, pp. 170–189.
Sharma, S. (2008) ‘Application of support vector machines for damage
detection in structures’, Worcester Polytechnic Institute,
Massachusetts.
Smarsly, K., Lehner, K. & Hartmann, D. (2007) ‘Structural health
monitoring based on artificial intelligence techniques’,
International Workshop on Computing in Civil Engineering,
pp. 111–118.
Tommelein, I., Levitt, R. & Roth, B. (1992) ‘Site-layout modeling:
how can artificial intelligence help’, Journal of Construction

16 Intersect, Vol 18, No 2 (2025)

 Munim et al., AI in Civil Engineering

Engineering and Management, 118(3), pp. 594–611.

Tushar, W., Wijerathe, N., Li, W., Yuen, C., Poor, H., Saha, T. &
Wood, K. (2018) ‘Internet of things for green building
management’, Signal Processing: An International Journal,
35(5), pp. 100–110.
Yang, L., Qi, C., Lin, X., Li, J. & Dong, X. (2019) ‘Prediction of
dynamic increase factor for steel fibre reinforced concrete
using a hybrid artificial intelligence model’, Engineering
Structures, 189, pp. 309–318.
Yang, Y. & Nagarajaiah, S. (2016) ‘Harnessing data structure for
recovery of randomly missing structural vibration responses
time history: sparse representation versus low-rank structure’,
Mechanical Systems and Signal Processing, 74, pp. 165–182.
Yuen, K. (2010) Bayesian methods for structural dynamics and civil
engineering. John Wiley & Sons, Singapore.
Zhang, C., Cui, C., Zhang, Y., Yuan, J., Luo, Y. & Gang, W. (2019)
‘A review of renewable energy assessment methods in green
building and green neighborhood rating systems’, Energy and
Buildings, 195, pp. 68–81.
Zhou, Q., Wang, F. & Zhu, F. (2016) ‘Estimation of compressive
strength of hollow concrete masonry prisms using artificial
neural networks and adaptive neuro-fuzzy inference’,
Construction and Building Materials, 125, pp. 417–426.

17 Intersect, Vol 18, No 2 (2025)