Journal Pre-proofs

Precision Agriculture using IoT Data Analytics and Machine Learning

Ravesa Akhter, Shabir Ahmad Sofi

PII: S1319-1578(21)00128-2
DOI: https://doi.org/10.1016/j.jksuci.2021.05.013
Reference: JKSUCI 1023

To appear in: Journal of King Saud University - Computer and

Information Sciences

Received Date: 14 January 2021

Accepted Date: 27 May 2021

Please cite this article as: Akhter, R., Sofi, S.A., Precision Agriculture using IoT Data Analytics and Machine
Learning, Journal of King Saud University - Computer and Information Sciences (2021), doi: https://doi.org/
10.1016/j.jksuci.2021.05.013

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover
page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version
will undergo additional copyediting, typesetting and review before it is published in its final form, but we are
providing this version to give early visibility of the article. Please note that, during the production process, errors
may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

© 2021 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University.
 PRECISION AGRICULTURE USING IOT DATA ANALYTICS AND
MACHINE LEARNING∗
RAVESA AKHTER † AND SHABIR AHMAD SOFI ‡

Abstract. In spite of the insight commonality may have concerning agrarian practice, fact
is that nowadays agricultural science diligence is accurate, precise data-driven, and vigorous than
ever. The emanation of the technologies based on Internet of Things (IoT)has reformed nearly each
industry like smart city, smart health, smart grid, smart home, including ”smart agriculture or pre-
cision agriculture”. Applying machine learning using the IoT data analytics in agricultural sector
will rise new benefits to increase the quantity and quality of production from the crop fields to meet
the increasing food demand. Such world-shattering advancements are rocking the current agrarian
approaches and generating novel and best chances besides a number of limitations. This paper cli-
maxes the power and capability of computing techniques including internet of things, wireless sensor
networks, data analytics and machine learning in agriculture. The paper proposed the prediction
model of Apple disease in the apple orchards of Kashmir valley using data analytics and Machine
learning in IoT system. Furthermore, a local survey was conducted to know from the farmers about
the trending technologies and their effect in precision agriculture. Finally, the paper discusses the
challenges faced when incorporating these technologies in the traditional farming approaches.

Key words. Internet of Things (IoT),Data Analytics(DA, Machine Learning(ML).

1. Introduction. In India one of the main economic activity is the agriculture.

Around 60-70% of employment in India is dependent on agricultural sector. It has
the maximum arable land that is second largest after U.S. This is because of the high
soil fertility and large network of water sources for irrigation. Due the varying nature
of climatic conditions at different locations it ensures the high availability and pro-
ductivity of flora. Although the well presence of resources it does not the produce the
results equivalent to the availability.It is because of scarcity and incompetent use of
technology, deficiency of knowledge and awareness among the agrarians, use of some
antiquate methods [1]. In addition most of the crops are affected by pests, insects,
diseases resulting in decreased yields. Many crops are affected by the attack of insects
or pests. Insecticides or pesticides are not always proved effective because they may
be toxic to some kind of birds and animals. It also damages the natural animal food
web and also food chains [2]. Crop disease results in considerably low throughput.
The authors in [3] outlines the yield depletion between 20% and 40 % of worldwide
agricultural production caused by insects, pests, viruses, animals, and weeds. In
addition, they have a number of facets, some with short-term, and others with long-
term consequences for the global food security [4]. Crop production losses due to
pests and diseases are quite substantial, particularly in the Indian weather semi-arid
conditions [2]. Weather has an extremely extensive role in agricultural production.
Generally crops are more common in the weather based frangible agriculture systems.
Survey have challenged that with the rise in population upto 10 billion, then definitely
by 2050 we are moving towards food doomsday. It implies food production ability will
bankrupt unless we establish and advance the smart technologies in agriculture. So for
∗ This work has been funded under the seed grant initiative of TEQIP III project currently being

implemented at National Institute of Technology Srinagar, Jammu and Kashmir, India.

† Ravesa Akhter is a PhD scholar in the department of Information Technology at Na-

tional Institute of Technology Srinagar, Hazratbal, Jammu and Kashmir, India, 190006 (ravesa
05phd18@nitsri,net).
‡ Shabir Ahmad Sofi is an Assistant Professor in the department of Information Technology

at National Institute of Technology Srinagar, Hazratbal, Jammu and Kashmir, India, 190006
([email protected]).
1
2 Ravesa Akhter and Shabir Ahmad Sofi

proper management of limited resources it is necessary to develop an economical tech-

nology for Indian farmers. The system should help the farmers to prevent the diseases
of crops on time and improve the quantity and quality food.The system should be re-
liable enough to sustain in hilly areas like Jammu and Kashmir for timely prevention
and cure [1]. It is because of their capability to monitor environmental parameters,
soil parameters, plant parameters by spatially deploying sensors remotely. On time
prediction of diseases caused by the various harmful entities whether by the lack or
exceed in the normal values of the monitored parameters can aid the agriculturalists.
So that they can take special measures against the attack of these pests and insects
in a controlled manner. This will prevent any usage of chemicals and reduce the dis-
eases occurring in fauna. In addition, it would definitely boost the Aggie productivity
and hence will bridge the gap tween increasing population and increasing demand of
food. Evidently, overall loss percentage of crops would be reduced. In the last decade
science and technology has revolutionized the globe. Current era is the technological
era. To provide applicable information to the agriculturalists, presently, remote mon-
itoring techniques are being used.Wireless Sensor Networks and Internet of Things
plays an essential role in this connection. The miniaturization of the technology re-
sulted in Internet of Things (IoT) utopia [5]. The term ”Internet of Things” (IoT)
was first time used by Kevin Ashton, while the presentation on Management of sup-
ply Chain in 1999 [6]. IoT is an interconnected network of computational objects like
sensors which are uniquely identifiable smart objects. The term ”Things” represents
a general array of objects, sensors, people, smart devices and any other entity having
the ability to connect and share information with other entities, that is aware of its
context and is making anything available at anytime, anywhere. It means everything
is accessible without any place or time restrictions. In the IoT, wireless technologies
play a central role in data gathering and data communication [7]. Wireless Sensor
Networks (WSN) and radio- frequency identification (RFID) are considered as the
two main building blocks of sensing and communication technologies for IoT [8, 9].
Wireless sensor networks have been used in different applications, such as military,
agriculture, sports, medicine, and industry [10]. Due to which voluminous amount of
data is being generated [8]. Wireless sensor networks sensors, smart devices, RFID
tags, tablets, palmtops, laptops, smart meters, smart phones, smart healthcare, social
media, software applications and digital services generate the volume of data. They
continuously generate large amounts of structured, semi-structured and unstructured
data which is strongly increased. The growth of data in various domains of applica-
tions like network operation, healthcare management, social media,intelligent traffic
system, business, marketing, resource optimization, precision agriculture and social
behavior etc. to study all this, data analytics committed for diverse wireless sensor
networks to take benefits. Data analysis is a process of data collection, data transfor-
mation, data cleaning and modelling data with the goal of discovering the required
knowledge [11]. The results and findings so obtain are communicated by suggesting
conclusions and supporting decision making. Data analytics is the process of examin-
ing large data sets that contain a variety of data types [12] to reveal unseen patterns,
hidden correlations, market trends, customer preferences, and other useful business in-
formation [13]. Agronomy consideration is the most well-intentioned ability for WSN,
data analytics and machine learning to rise the crop yields and to decrease the her-
culean task of farmers [14]. Precision Agriculture (PA) or site specific farming is the
technological approach that uses modern data technology and knowledge to develop
the high quality agricultural production. WSN are economical procedures to improve
 Precision Agriculture using IoT Data Analytics and Machine Learning 3

Fig. 1.1. Internet of Things and Data Analytics Relationship

crop yield [15]. Precision agriculture is in its advanced phase, and some farmers have
started to implement PA in their terrains, and have obtained best results, manag-
ing to return the investment essential for its implementation. Hence, the activities
related to PA include: identification and localization of crops, insects and weeds, per-
formance monitoring, machinery, variable dozing of fertilizers, herbicides, insecticides
and fungicides, planting monitoring and mapping [5]. In [16] precision agriculture has
been discussed broadly. They gave the detailed overview of how IoT is playing a role
in precision agriculture by making the fields talk. With the help of IoT they gave
the idea how to increase the agricultural yield to meet the needs of the bulky popula-
tion by using the limited available arable land for cultivation, fresh water for irrigation
etc. by giving the precise and required quantities of fertilizers, insecticides, water, etc.
In [17] environment monitoring system has been designed and deployed for precision
agriculture using WSN. The system was tested in a red bayberry greenhouse situated
on a hillside by collecting the following parameters; temperature, voltage, humidity
etc. The system proved to be scalable, stable, and accurate and can provide real
time data for precision agriculture. Data Analytics and Machine Learning techniques
are playing an important role in the agrarian sector in order to handle the increasing
challenges due to the weather and climatic changes like temperature, rain, humidity
etc which are causing serious damage in crop production. It is necessary to increase
the accuracy of data analysis for vigorous and proliferating production. The capabil-
ity to analyze large amounts of data can help an organization deal with considerable
information that can affect the business [18]. The procedures and algorithms used in
such analytical tools must discover hidden patterns and correlations in the data [19].
The field data collected by the deployed sensors is in the form of multimedia which
helps in disease detection in stems, leaves fruits and roots, quality, health of fruits [20],
and presence or detection of weeds and smart irrigation [21–25].In order to produce
higher quantity and increase the quality of food and reduce the crop failure, integra-
tion of IoT sensing devices and drones seem to be helpful, the same devices monitor
the things in regular intervals for best results [21, 23, 25]. In figure 1.1 we have shown
the various steps of how IoT and data analytics are related to each other. By using
IoT data analytics with the machine learning we can make the precision agriculture
practical. Initially in the first step which comprises managing IoT data sources, where
connected sensors devices use applications to interact with one another. For example,
the interaction of devices such as CCTV cameras, drones, environmental sensors , soil
sensors, plant sensors etc produces huge amounts of data in diverse formats. This
generated data can be hoarded on the cloud using commodity hardware devices. In
the second go, data is complex due to their volume, velocity, and variety. Depends
4 Ravesa Akhter and Shabir Ahmad Sofi

upon the precision agriculture application specification and the type of data we are
interested in collection of, mainly precision agriculture datasets having data related
to crop patterns, crop rotations, weather parameters, environmental conditions, soil
types, soil nutrients, Geographic Information System (GIS) data, Global Positioning
System (GPS) data, farmer records, agriculture machinery data, such as yield moni-
toring and Variable Rate Fertilizers (VRT) [26].These enormous amounts of data are
stored in big files of data in shared and distributed fault- tolerant databases. The last
step applies analytics tools such as Map Reduce, Spark and Skytree that can analyze
the stored IoT data sets and find the value out of it. This implies integrating IoT data
analytics and machine learning techniques, there is the need to develop forecasting
models for crop management including disease and yield prediction.
The main aim of the paper is as follows; i)To provide a thorough review on the
use of IoT(sensors) and data analytics for precision agriculture; ii)To present a case
study on adoption of IoT and data analytics on apple orchards; iii) To understand
the challenges faced by traditional farmers in adopting technologies to complement
traditional farming.
The rest of the paper is organised as; Section 2 presents the literature survey of
Precision agriculture under the following sub headings i)IoT-Sensors and Networks;
ii)Data Analytics; iii)Applications of IoT and Data Analytics as smart System in
agriculture. Section 3 discusses the case study on adoption of IoT (sensors) and
data analytics in traditional Kashmir farms for prediction of apple scab. Section
4 discusses several challenges and open issues in adoption of IoT data analytics in
precision agriculture for traditional farmers, which is further categorized into the
following four categories: i) commercial; ii) Technical; iii) Sectorial; and iv)Data
Analytics. Section 5 concludes a paper by highlighting important findings briefly and
gives some future directions.
2. Literature Survey. A lot of activity has already been accomplished in the
area of precision agriculture using different technologies like IoT, machine learning for
making decision support system, data analytics, etc. We have divided the literature
survey under three subsections: 1)IoT/ Sensors and networks, 2)Data Analytics and
3)Applications of IoT and data analytics as smart system in Agriculture. The work
on precision in different fields in the literature are comprehensively mentioned in these
subsections below:
2.1. IoT-Sensors and Networks. Wireless sensor networks are used in diverse
agronomic applications, for example remotely observing environmental and soil condi-
tions in order to predict the healthfulness of crops. Watering schedule of agricultural
fields is forecasted by employing WSN as observant of environmental conditions like
pressure, humidity, temperature, soil moisture, soil salinity and soil conductivity. A
lot of work has been done in the literature, main contributions by various researchers
are discussed. In [27] authors proposed the scalable network architecture to monitor
and control agriculture fields in rural areas. They proposed a control system based
on IoT for development of farming and agriculture. All the system components and
improvements are examined and analyzed in all aspects.The solution of routing and
MAC in IoT achieved energy efficiency, less delay and high throughput.To achieve this
performance the system combines Wi-Fi based long distance (WiLD) network and fog
computing solution. In [1] authors have proposed WSN framework design , intention-
ally to setup a DSS for the detection of Apple Scab in Himachal Pradesh using Mills
tables. In [28] IoT was applied in agriculture to improve crop yields, improve crop
quality and reduce costs. Based on wireless sensor networks they proposed and devel-
 Precision Agriculture using IoT Data Analytics and Machine Learning 5

oped a system which can optimally water agricultural crops like lemon, home grown
vegetables. To control the effect of environmental factors in the crop fields, the sys-
tem proposed consist three main parts Hardware (Control box), Web application and
Mobile application. Control box was actually a WSN and electronic control system
which was helping in data collection. Using web application the data collected from
the control box is large scale data that was analyzed using data mining association
rules. The mobile application was used to notify the farmer about water content of the
soil and accordingly automatic or manual watering was done. Data mining showed
for high productivity of home grown vegetables and lemon temperature should be
29-30o C and humidity 72-81%. In [29] the authors have designed a system for pre-
cision agriculture which is economical known as Smartnode. For the optimal crop
development they used the platform of hardware and software that allows monitoring
of agro climatic parameters. They deployed the system into crop field to increase its
yield. The main aim of [30] was to apply a model to alert farmers when would be the
suitable moment to treat the downy mildew disease in a vineyard context. Following
the IoT paradigm they proposed the system named SEnviro (Sense our Environment
platform) to monitor vineyard fields. They used the edge computing paradigm to
mitigate the communication between ends. In [2] authors showed that the existing
systems are not reliable and cheap. They gave the information of using IoT and
machine learning in the precision agriculture to predict the diseases of crop. They
proposed a system model using machine learning and IoT. They took the environmen-
tal sensors like temperature, humidity etc and collect the data. After the final output
was generated the same was sent to the local farmers as an SMS. In [10] the authors
presented a review of WSN based agricultural applications. Authors compared var-
ious wireless technologies and protocol suites like Wi-Fi, Bluetooth, GPRS/3G/4G,
ZigBee, LoRa and Sig Fox. They showed LoRa and ZigBee wireless technologies are
highly efficient to use for Precision Agriculture because of suitable communication
range and low power consumption. Categorization of various techniques and algo-
rithms related to energy efficiency of wireless sensor networks are mentioned. They
have also mentioned the techniques that can be used in PA. Challenges and limita-
tions of WSN in PA are also mentioned. In [31] authors have combined the machine
learning approaches with the internet of things and showed their applicability in next
generation networks .They improved the energy efficiency in NOMA(non-orthogonal
multiple access)public safety networks by using UAV (Unmanned Aerial Vehicle)and
WPC (wireless powered communication)collectively which results in Public Safety
IoT (PS-IoT) ecosystem. In [32]the authors study proposes a creative service process
based on the cloud computing platform of the Internet of Things and it can be used
to improve the integration of the current cloud-to-physical networking and to improve
the computing speed of the Internet of Things. This research uses innovative platform
technology to be applied to the cloud agriculture platform. Through cloud integra-
tion, it can be applied to large area data collection and analysis, allowing farmland
with limited network information resources to be integrated and automated, including
agricultural monitoring automation, pest management image analysis.In [33] authors
presented system based on IoT by designing Nitrogen-Phosphorus-Potassium (NPK)
sensor which is a novel approach with Light Dependent Resistor (LDR) and Light
Emitting Diodes (LED). To monitor and analyze the nutrients present in the soil the
principle of colorimetric is used. Google cloud database is used to store the data
collected from fields for fast retrieval of data. Fuzzy logic concept has been applied in
order to know the lack of nutrients from sensed data. The sensed data is distinguished
6 Ravesa Akhter and Shabir Ahmad Sofi

into five fuzzy values which are very high, high, medium, low and very low while fuzzi-
fication. The intended hardware and the software incorporated in the micro-controller
are developed in Raspberrypi3 using Python. Three different samples of soil like red,
desert, and mountain soil have been tested by the proposed model. With respect to
the concentration of the solution soil the developed system resulted in linear varia-
tion . In order to analyse the performance of developed NPK sensor in the form of
end to end delay, throughput and jitter a sensor network scenario is deployed using
Qualnet simulator.The developed IoT system was found to be most needful to the
agrarians for high yielding of crop production when compared with the existing solu-
tions. In this article researchers have identified the most important applications using
IoT and an elaborated survey has been done particularly in precision agriculture [34].
Challenges faced while using IoT in smart agriculture. In [35] the authors surveyed
protocols, methodologies and applications in developing area that is IoT. The article
mentions new taxonomy for Internet of things technologies.It climaxes the most essen-
tial technologies that have the capability to make an extraordinary variation in human
beings lives, specially for the handicapped and the elderly. In comparison to the same
survey articles, this paper has covered major technologies from sensing devices to ap-
plications exhaustively and comprehensively . In [7] authors have proposed a survey
regarding the prime architectures in the history. Furthermore, the elementary unit
technologies which are well-accepted to suit IoT application requirements. They also
introduce a classification presenting the appropriateness of proposed architectures in
IoT characteristics. In addition, they have highlighted the advantages of present so-
lutions and proposed future directions on the basis of state of the art. In a future
research they are planning to design an approach which will be able to mitigate the
drawbacks of the IoT at each individual layer of the internet. In [36] authors exam-
ined the promising Wireless sensor network applications, challenges and limitations
associated while distributing WSN to improve crop yield. Smart devices, sensing de-
vices and communication technologies lined with WSN in agronomy applications are
emphasized completely. They mentioned different case studies to explore the present
solutions proposed in the literature. They have mentioned in the literature survey
that how precision agriculture has been implemented globally including India. They
have depicted the drawbacks of these existing solutions by presented the future di-
rections using advanced technologies. In [37] authors have investigated application of
IoT in precision agriculture. They used wireless communication technology to achieve
site specific monitoring of greenhouse. They proposed Remote greenhouse monitoring
system using wireless communications. An information management system has been
designed while system management has been taken in to account. The field data has
been utilized for research. By using this remote monitoring system, the field data
like temperature, humidity from the greenhouse has been sensed precisely and after
the proper research, system resulted in good growth condition of vegetables. The
proposed system has resulted in increased performance and reliability. The interface
of the system was user friendly for ordinary farmers. In [38] authors have proposed
a method for efficient crop monitoring for agricultural field. With the application of
IoT the data can be stored and retrieved from anywhere. Various sensors are used
to monitor and collect information about the field conditions. Collectively the farm
condition is sent to the farmer through GSM technology. In the proposed work, the
sensor part is limited only for monitoring of crops. In [39] authors research have fo-
cused on data collection from agricultural fields through various technologies. Using
WSN, IoT, Weather stations, smart-phones, drones and cameras are found to be use-
 Precision Agriculture using IoT Data Analytics and Machine Learning 7

ful during their study. In addition, authors advanced the platform based on IoT called
SmartFarmNet. This was able to process the collection of data from the field related
to various parameters like soil, moisture, irrigation, soil fertility, humidity, tempera-
ture etc. The proposed system was able to correlate the analyzed data and was able
to forecast crop status. In [40] authors emphasize the hoe various technologies are
important in precision agriculture. How the farmers of Germany are able to accept
the precision agriculture using smart devices like smart-phones. Regression analysis
showed a positive effect of precision agriculture on farmers. The authors have given
some research directions using IoT in agriculture.

2.2. Data Analytics. Before the advent of information technology, various tra-
ditional methods like manual detection of crop diseases and pests, calculations based
on statistics to estimate the quantity and predict the production and loss of crops
were generally cumbersome, this results in human error due to the lack of experience
of inspectors [41]. Machine learning is the ability of technology to learn through ex-
periences. Data analytics and machine learning allows us to draw the most important
conclusions from the large data collected from the crop fields. It reveals the hidden
patterns, hidden relationships between the parameters affecting the horticulture like
temperature, soil salinity, humidity etc. The mostly used and related machine learning
techniques in forecasting crop diseases and pests in which weather data are analysed
are Artificial Neural Network (ANN), SVM Regression and Logistic Regression, recog-
nition technology using neural network, Support Vector Machine (SVM) [42], fuzzy
technology for recognition etc. In [43] authors proposed a system for classification of
apple diseases using the machine learning classification algorithms. The two diseases
which they classify are apple scab and marsonina coronaria by using the images of
leaves of the apple trees as input. Classification algorithms Support Vector Machine,
K Nearest Neighbour, Decision Tree and Naı̈ve Bayes were used on the same data.
Matlab 2016 was used for the simulation proposed system. They showed it is the K
nearset neighbour which classified the diseases with the 99.4% accuracy. The system
was developed in the state of Himachal Pradesh, Uttarkhand. In [2] authors showed
that the existing systems are not reliable and cheap. They gave the information of
using IoT and machine learning in the precision agriculture to predict the diseases of
crop. They proposed a system model using machine learning and IoT. They took the
environmental sensors like temperature, humidity etc and collect the data. After the
final output was generated the same was sent to the local farmers as an SMS. In [44]
authors have used machine learning approaches to create the intelligent communi-
cations. In order to improve the QoS (quality of service) of limited wireless assets,
intelligent machine learning approaches have been used. In [45] the authors used IoT
technology and ML techniques for the prediction of late blight disease in potatoes.
The environmental parameters like Temperature and humidity were captured by the
use of sensor devices deployed in the farm fields which transmit the information to
the central gateway. The data collected helps to detect the level and risk of blight.
In [45] authors have focused on a moderate susceptible cultivation of potato crop
using a back- propagation network with an accuracy of 94%. In [46] authors have
used image processing and data analysis algorithms for precision agriculture for pre-
dicting the site-specific yield. They proved that there is a high correlation between
flower density and the fruit yield by predicting the yield of the apple orchard with
an accuracy of more than 80%. In [47] authors have established five onsite weather
stations in orchards that collect data. The collected data can be used in models to
predict the apple scab infection periods. Such models can help farmers to determine
8 Ravesa Akhter and Shabir Ahmad Sofi

Table 2.1
Literature Survey

Reference Contribution Results

Jayaraman SmartFarmNet application Proposed framework was capable of:
et al. • Making predictions related to
crop performance
• Computation of crop forecasts

Nurzaman They proposed a scalable network ar- Improved performance in terms of:
Ahmed et chitecture for minitoring and control- • Latency
al. ling agriculture and farms in rural ar- • Bandwidth
eas
Muangpra- Based on wireless sensor networks Data mining showed for high produc-
thub et they proposed and developed a sys- tivity of home grown vegetables and
al. tem which can optimally water agri- lemon:
cultural crops like lemon, home • Temperature should be 29-30
grown vegetables. ◦
C
• Humidity 72-81 %.

Fonthal et The authors have designed a system They deployed system:

al. of precision agriculture at a low cost • Increased the yield in tomato
called Smartnode. crop field.

Mazilu et They proposed an Orchard System The proposed scheme:

al. for Monitoring and Modelling Apple • Performed well in the locality
Scab (Venturia Inaequalis for that of Romania in terms of quality
they established five onsite weather and quantity
stations in orchards that collect
data.)
Hamad et Understanding the perception of Results obtained after applying Chi-
al. farmers regarding the usage of smart- square test:
phones in performing agricultural ac- • Lack of trust
tivities • High cost.

Trilles They proposed the system named They used:

Oliver et SEnviro (Sense our Environment • The edge computing paradigm
al. platform) to monitor vineyard fields. to mitigate the communication
between ends.

Jawad et Authors compared different wire- They showed:

al. less technologies and protocols • ZigBee and LoRa wireless pro-
such as Wi-Fi, Bluetooth, ZigBee, tocols are more convenient for
GPRS/3G/4G, LoRa, Sig Fox Precision Agriculture.

Lavanya et They present an IoT based sys- Proposed model proved to be helpful:
al. tem by designing a novel Nitrogen- • For high yielding of crops.
Phosphorus-Potassium (NPK) sen-
sor with Light Dependent Resistor
(LDR) and Light Emitting Diodes
(LED).
Shinde et The information about machine The review given concludes that:
al. learning and IoT implementation • Existing system are not reli-
used for crop diseases is given. able and cheap
 Precision Agriculture using IoT Data Analytics and Machine Learning 9

the need (or lack) of fungicide sprays to control apple scab. They posted the in-
formation on http://www.pomosat.ro for neighboring apple growers in Romania to
access for and use in decision making. In [48] a new prediction model for warning of
apple scab is proposed. The model proposed is based on Artificial Intelligence and
time series prediction. Infection period of apple scab was evaluated as the time series
prediction model instead of summation of wetness duration. Important hours were
determined with feature selection methods Pearson’s Correlation Coefficient, Fisher’s
Linear Discriminant Analysis, Adaptive Neuro fuzzy Classifier with Linguistic hedges.
Prediction was done by adaptive neural network model. To determine the apple scab
infection 24 hours are needed to capture the measurements. Five meteorological mea-
surements relative humidity, leaf wetness, temperature, day light and rainfall. After
every 12 minute data was collected so time was one more parameter for time series
prediction. They marked correlation between apple scab and meteorological measure-
ments. They detect appropriate time for infection. Besides this, classification and
prediction of apple disease was done. In [49] the authors present a novel decision
support system (DSS) for the prevention of late blight using the integration of WSN,
cloud and IoT. The model proved to be beneficial for preventing potato late blight dis-
ease. DSS was capable to estimate the precise quantity of fungicide to apply. Besides
this IoT sensors related to weather were deployed to collect real time data and was
then sent to cloud IoT framework for processing. The forecast model used the weather
related data from weather stations and historical data for the prediction of late blight.
The system was quite efficient and cost effective for the farmers. In [50] authors in-
tended to organize heterogeneous data approaching from diverse sources in the form
of datasets as a result of sensory systems. They also showed how useful companies
whether large scale or a small scale, a public or a private are trying to improve prof-
itability. Finding proper ways to use data that are recorded continuously are the best
possibility to achieve goals. It suggested how Regression analysis, Neural networks
and Machine Learning are useful decision-making . In [51] authors have emphasized
the importance of smart mobile phones for obtaining agronomy facts information of
different parameters like soil moisture, humidity, temperature etc. In the same article
they have highlighted benefits of smart-phones in the agricultural field. The authors
conducted the survey of around 230 farmers through questionnaires and interviews
to know what they want. After completing the process they come to the conclusion
that farmers are interested to make use of smart-phones to acquire information about
current farm data. Table 2.1 summarizes the key points of the literature survey, how
the authors in the existing technologies have contributed in the precision agriculture
and what they achieved.

2.3. Applications of IoT and Data Analytics as Smart System in Agri-

culture. IoT/sensor nodes are playing a key role in precision agriculture to collect
the real time data [52]. These nodes have the capability to make the system more
practical by collecting the real time data from the crop fields to make the agriculture
system precise. By incorporating data analytics and machine learning the agriculture
system becomes more workable. All these technologies have tremendous applications
in other fields. In precision agriculture various applications for farmers are developed
to inform them about the status of crops on time. The architecture for precision
agriculture is usually composed of three main phases as shown in figure 2.1. The first
phase it consists of the number of sensors/ IoT nodes to monitor physical or envi-
ronmental conditions, soil conditions, plant conditions, e.g the soil moisture sensor
records soil wetting reading, or soil nutrient sensor will check the fertility of the soil.
10 Ravesa Akhter and Shabir Ahmad Sofi

Central Database

Computer User
Public Cloud

Router

Sink Node

Wireless Sensor Networks

Fig. 2.1. Precision Agriculture Model

In the second phase we need to collect this precise data, we can either store the data
locally to the nearest fog node or we can send it on the cloud for higher computation
and remote monitoring it depends upon the need. In third phase of the architecture
the analytics methods are applied to know the status of the crop fields. This informa-
tion is then communicated to the end users(farmers) that helps them to identify that
if the reading is below or above threshold. Accordingly they initiate communication
to the actuator that would switch on(or off) the watering system to pour water to the
soil or farmer(end user) may need to spray some fertilisers potassium, nitrogen and
phosphorous to balance the fertility of soil. Using analytics and actuators a response
mechanism is activated upon recognition (sensing/predicting) of any critical scenario.
There are number of applications of IoT and WSN in the precision agriculture, some
of them are mentioned here. Figure 2.2 shows the applications related to precision
agriculture.
2.3.1. Soil Selection and Planning. Soil is the basic building block of every
agrarian practice. Without soil, the word crop does not exist. Soil is considered to be
the stomach of flora [53]. So to analyze the condition of soil is the first and foremost
step towards the best agrarian practice. By doing the soil testing we can analyze the
physical, biological, chemical statuses of the soil. Based on this the farmers can take
decisions accordingly regarding their fields. The main motive of precision farming
is to produce more from the scarce cultivable land. So to implement the new era
technologies is very important across the globe as we have to satisfy the increased
population with the limited resources. Usually soil tests based on weather and soil
conditions are done in Fall [54]. By doing the soil tests we can analyze the soil nutrients
which include the information related to the fertilizers requirement, copping history,
soil kind, irrigation level, etc. Presently we have various sensor based technologies
 Precision Agriculture using IoT Data Analytics and Machine Learning 11

Fig. 2.2. Applications related to precision agriculture

which are very helpful in soil selection and planning. These technologies help us to
decide the best crop for the best fit soil. A soil testing toolkit, Lab-in-a-Box, developed
by Agrocares is considered to be the complete laboratory test toolkit [54]. It can be
used by any farmer to test the soil of their fields without going without going any
agriculture laboratory. According to this toolkit it is said that around 100 samples
per day can be tested by any farmer without having any lab experience. It means
around 36000 samples per year can be tested without visiting any lab. Using the
vision based technologies with the sensors agriculturists can make a determination
of depth and distance for implant a seeds and plants proficiently [53]. In [55], using
the GPS (Global positioning system), sensors and autonomous robot based on vision
called Agribot was advanced for seed sowing. So in short we can say that present
technology is very helpful for every farmer to help them to select the best fit land for
the suitable crop.

2.3.2. Irrigation of Crop Fields. Irrigating the crop fields on requirement

bases is one of the best ways to generate more and more crops and manage the
available fresh water bodies. Humanity relies only on the 0.5% available fresh water.
Approximately 97% of the available water on the planet earth is salt water and the
remaining 3% is fresh water. About 67% of the fresh water is either in polar ice caps
or glaciers that is frozen [56, 57]. It means only remaining percentage of fresh water
is unfrozen which lies underground and only 0.5% is available for the flora and fauna
to survive [58]. It has been mentioned in [59, 60] that it is agricultural area which
consumes around 70% of the 0.5% available fresh water, even around 85% is utilized
for the same in underdeveloped countries. So it is the responsibility of the humanity
to manage the water resources. For that very purpose many researchers are working.
So the traditional methods of irrigation can be managed by adopting the emergent
technologies like IoT and WSN. We can deploy the WSN based system related to the
12 Ravesa Akhter and Shabir Ahmad Sofi

soil moisture which will notify us whenever we need to irrigate the system. In [61, 62]
based on IoT, crop Water stress index (CWSI) has been developed, which can be
used to increase the efficiency of crop. In CWSI system we are deploying the required
sensors in the needed field and collect the data, sending that data to the central
processor. A the central node we are also collecting the data from weather stations
and including the satellite images, based on all thus we decide whether we should
irrigate the field or not. In nutshell we can say by adopting the emerging technologies
we can maintain the required moisture for the crop and in turn will save the fresh
water resources.
2.3.3. Fertilizers. Fertilizers provide the nutrients to the soil which in turn are
transferred to the plants through roots. Fertilizers like potassium (K), Phosphorus
(P), Nitrogen (N) etc. all have their own uses to maintain the health of flora. Plants
need mainly NPK macro nutrients to maintain the health. P is used to maintain the
health of roots, flowers and helps in fruit development, K is used to for stem growth
and for proper functioning of xylem so that water can be transferred to every part
of the plant, and N helps the leaves in growth. So we need to prevent any sort of
deficiency of NPK fertilizers in plants or improper use may also lead bad results.
Excessive use of fertilizers imbalance the ecosystem. Precision agriculture helps in
proper use of NPK fertilizers by using WSN, machine learning and IoT technologies,
hence helps us in avoiding the negative results over the ecosystem. Using the aerial
/ satellite images to monitor the crop nutrients, in [63, 64] authors have used NDVI
(Normalized Difference Vegetation Index), from vegetation it is working on reflection
of visible and near infrared light. It helps the farmers in the estimation of vegetation
vigor, crop health, and density. It also helps in assessing the soil nutrient level. Hence
it helps the efficient use of fertilizers. NDVI contributing the precision agriculture uses
the emerging technologies like VRT (Variable Rate Technology) [65, 66], autonomous
vehicles [67], geo mapping [68] and Global positioning system (GPS) accuracy [69].
In short we can say that if the proper use of fertilizers cannot be done then there we
are creating difficulties for our incoming generations. So it is better to develop our
globe by adopting the new era technologies.
2.3.4. Crop Disease. Presently our entire globe is suffering from various crop
diseases such as leaf spot, apple scab, potato scab, anthracnose, late blight, early
blight, powdery mildew etc. These diseases cause financial losses up to billions. Be-
sides financial and economic losses crop disease affect the health of fauna. According
to the FAO (Food Agriculture Organization), it has been estimated that 20-40% crops
are lost due to the crop diseases and pest use [70]. It is the time to work on it, because
if we will leave this all untreated we will lose much more that this in near future. IoT
plays an important role in monitoring the condition of crop by using the wireless
sensors, drones, other IoT based intelligent devices which capture the condition of
the crop and analyses it in the high end processors and take the decisions accordingly
based on decision support systems using machine learning. A lot of work has been
applied to overcome all this by using various new era techniques. In [71] various ap-
proaches like automatic chemigation and vehicle spray, those are mainly used under
precision agriculture to treat diseases of crop.
2.3.5. Pest Management. By using various pesticides, herbicides, insecticides,
in order to remove the enemies of the crop, we try to maximize the yield. Most of the
farmers are ordinary people who are unaware about the current trends and techniques.
They are completely unaware about the precision farming technologies. Over and
 Precision Agriculture using IoT Data Analytics and Machine Learning 13
Table 3.1
District wise production of apples in Kashmir

District Production (In metric tonnes)

Baramulla 469.3
Anantnag 161.182
Pulwama 121.9
Kulgam 45.53
Srinagar 36.1

Table 3.2
Relationship between production and factors

Factor Multiple R-Squared Value

pH 0.0653
Phosphorus(P) 0.0209
Nitrogen(N) 0.07867 ∗ 10−5
Potassium(K) 0.236
Organic content(OC) 0.00029

under usage of pesticides, insecticides, etc. imbalance the nature. Excessive use of
pesticides leads bad effect over the environment. By using these germicides we are
creating more chances of chronic and fatal diseases like cancer, asthma, etc. In [72,73]
with the help of IoT we can stop the improper use of these pesticides. Modern IoT
based pest management based on real time environment monitoring, provides disease
prediction, modeling, etc. hence results more effective.
2.3.6. Yield Monitoring . Last but not the least application of internet of
things is to monitor the farm lands. In order to maximize the yield both qualitatively
and quantitatively good farmers should never hesitate in adopting the modern tech-
nologies because all farmers are interested in producing the best quantity from their
fields, they always prefer to increase the quantity and quality of the crop. Yield moni-
toring monitors the whole crop area from beginning till end means from cultivation to
harvesting. In harvesting we need to check how to store food? How to transport it?
How to deal with the diseases which are caused while storing it? All these problems
are solved using the wireless sensors and other related technologies. In [74–76] it has
been mentioned that quality of the crop and the yield of the crop depends upon self-
pollination and other environmental conditions. During dry conditions to monitor the
foods like papayas, multiple optical sensors are used [77].
3. Adoption of IoT (Sensors)and Data Analytics in tradtional Kashmir
farms for the prediction of apple scab. Apple is one amongst the most grown
fruits in the world. It grows mostly in dry areas. In Jammu and Kashmir where people
from most of the districts are dependent on farming and agriculture. It produces the
large quantity and diverse apples in India. Its industry is worth of thousands of crores
in J & K. As shown in Table 3.1 the district wise production of Apple crop in Kashmir
division.
But due to the various diseases, wide range of pests and lack of technology in
the fields we lose both quantity and quality of the crop. Apple scab is the most
troublesome disease for apple growers in all parts of Kashmir. Scab is caused by a
fungus that infects both leaves and fruit. Scabby fruit are often unfit for eating and
14 Ravesa Akhter and Shabir Ahmad Sofi

Fig. 3.1. Plots of Factors vs Production

Fig. 3.2. Safe zone

continued infection of leaves weakens the tree. Small black spots develop on fruit,
enlarging more slowly than on leaves. As these spots grow and become older, the
center loses the velvety appearance and becomes brown and scabby. Heavily infected
fruit becomes deformed and cracked when infected at an immature stage. Apple scab
infections occur during wetting periods when moisture stimulates the pathogen spores
to germinate and penetrate plant tissue. For this we did literature survey related to
the crop and the factors affecting its growth. We did a local survey to find data
regarding the factors on which we were going to work on. So, for this purpose we
went to SKUAST (Sher-e-Kashmir University of Agriculture Sciences and Technol-
 Precision Agriculture using IoT Data Analytics and Machine Learning 15

Fig. 3.3. Unsafe zone

ogy, Srinagar, Kashmir )and visited departments of Soil and Pathology to gather the
relevant data. Therein, certain information regarding the Apple Scab disease was
collected. At SKAUST we came to know about the factors affecting the growth of
Apple crop. We analyzed the collected data to verify the factors which actually affect
the production and occurrence of diseases. Studying the R-Squared values, we see
factors like pH, P(Phosphorous) and K(Potassium) play a very important role in the
overall production of crop as shown in table 3.2 OC(Organic content) is a slightly less
important factor while nitrogen plays the least important role. Based on these values,
we designed some prediction models as shown in figure 3.1. Factors like pH, K, P
and OC together are crucial for a quality crop as is evident from its R-Squared value
0.788. The scab prediction table given here can be used to determine whether or not
conditions have been sufficient for infection so that appropriate spray decisions can be
made. Based on a certain combination of temperature and hours of leaf wetness, we
can identify whether that region is safe (no chance of apple scab occurring) or unsafe
(higher probability of the disease occurring with less incubation days) [78, 79]. From
the data following two graphs have been drawn see figure 3.2. Safe zone where there
is 0% chances of apple scab while figure 3.3 shows the unsafe zone where there is no
chance to stop apple scab.

3.1. Framework. The main aim of this study was to predict the apple scab
that is the most common disease of apple crop. In this problem we used the real time
data of wireless sensor/IoT nodes as input for linear regression model. In this an
application is developed for farmers which is simple and user friendly to inform them
about the status of their apple orchards on real time basis. The framework consists
of a number of WSN/IoT nodes scattered in the orchards of the apple with nearby
gateway for collection of the data from the mesh of the nodes While performing the
research on the said problem various steps have come in the way that forms the basis
of our study. These steps are shown in the figure 3.4. The nodes are deployed in
the apple orchard for data collection. A network is established between the nodes,
data acquisition is done by nearby gateway or a fog node from prefixed number of
nodes in the network. The data analysis is done on the real time basis for each
location /orchard for quick action if needed. In this work data is collected from many
16 Ravesa Akhter and Shabir Ahmad Sofi

Sensors Wireless Sensor

Data Aquisition Analytics Results
Assembled Network Setup

Fig. 3.4. Block Diagram:Steps involved throughout the process

orchards of the Kashmir Valley using the same models as discussed above. The results
are shown in section 3.6. The detailed framework is explained below:
3.2. Sensors Assembled. In precision agriculture IoT plays an important role.
IoT are the embedded systems which have the capability to sense and share infor-
mation related to any field in any application. IoT devices and its services play an
important role in wireless world as they can provide users all required services at any-
where at any time. Diverse number of sensors related to agriculture like plant sensors,
soil sensors, environmental sensors etc. collect the real time data respectively. This
data is very helpful in predict the crop diseases. In our prediction model we required
to monitor two parameters temperature and hours of wetness in a field.The sensors
comprised of an IRIS mote and MTS420 sensor board. The IRIS is a 2.4GHz mod-
ule used for enabling low power, wireless sensor networks. MTS420 offer five basic
environmental sensing parameters and an optional GPS (global positioning system).
The five basic environmental sensors included in MTS420 are temperature, humidity,
barometric pressure, ambient light sensor and dual-axis accelerometer. Among these
we are interested in temperature and Leaf wetness hours only. For this DHT22 sensor
is used which is embed on MTS420, gives us temperature and humidity. Leaf wetness
hours are then calculated using humidity.
3.3. Sensor/IoT Network Setup. This step involves setting up of the WSN
for capturing the data. We created a WSN of several sensors and a gateway. Six sen-
sors have been used to cover the particular area of an orchard. Each sensor comprises
of a IRIS fitted with a MTS 420 sensor board. The gateway is incorporated in WSN
that provides connectivity back to the wired world and distributed nodes using Zigbee
module. The IRIS needs to be programmed to be able to act as a sensor with sensor
board. Six such sensors were developed which are enough to cover the length of an av-
erage apple farm. For the gateway, MIB 520 fitted with an IRIS is used. Here the IRIS
is programmed to act as the gateway in order to communicate with the computer. For
programming of IRIS and MIB 520 MoteConfig Application is used. MoteConfig is a
Windows-based GUI utility for programming Motes. This utility provides an interface
for configuring and downloading pre-compiled XMesh/TinyOS firmware applications
onto Motes. MoteConfig allows us to configure the Mote ID, Group ID, RF channel
and RF power. We can also enable the over-the-air-programming feature present on
all XMesh - based firmware. High-power and low-power XMesh applications are avail-
able for each sensor board and platform. The Local Program tab is used to upload
firmware onto the Motes via a gateway. To program motes correctly, we set up the
hardware as follows:
• The gateway(in this case the MIB 520) should be powered and connected to
the PC via a serial, USB or Ethernet port.
• The motes should be firmly attached to the gateway.
• The motes should be turned off before the programming.
Next Click on Settings followed by Interface Board, to select the correct gateway and
port settings. Since we are using MIB 520 we’ll select that one. To program the IRIS
as a gateway for all the other sensors we have to upload XMESH file over it. To
 Precision Agriculture using IoT Data Analytics and Machine Learning 17

Fig. 3.5. MoteConfig programming successful

Fig. 3.6. MTS 420 Sensor programming successful

program the IRIS as a MTS 420 sensor mote we select XMTS420-M2110-hp file for
the sensor board as shown in figure 3.5 and 3.6.
After the sensors were successfully programmed, these sensors were carefully
placed throughout in each field and the gateway was connected to the system. Topol-
18 Ravesa Akhter and Shabir Ahmad Sofi

ogy used for WSN is mesh in the proposed work. Main advantage of using mesh
topology is that it covers the maximum area of the orchard, it reduces loss of the data
and there is not any single point failure problem. The WSN thus deployed is highly
scalable and reliable.
3.4. Data Acquisition. Next step is to collect the data from various parts of the
Kashmir Valley. Data collection is one of the basic and fundamental task while doing
data analysis. To collect data, we selected three districts of Kashmir: Zakura Area
of district Srinagar, Pinpora area of district Kulgam and Kanelwan area of district
Anantnag, spread over a area of 4-5 kanals, 7-8 kanals, and 6-8 kanals respectively.
The system was kept in place for over 12 hours to collect a single days data. Care
was taken to ensured that the motes weren’t damaged by water leading to wrong
readings. To note any variation sensors were kept 100 meters apart, so that whole
data from the field can be collected. MOTE-VIEW monitoring software was used as
an interface between user and the deployed WSN. It provides the tools that simplifies
the deployment and monitoring of WSN. It helps in data collection into the database.
We used PostgreSQL database for it, this resides on our personal computer system
(acts as a localhost), a remote server.
3.5. Analytics. After the WSN was deployed, the sensors logged their data in
a Postgres database. Next step was to analyse this data and find a prediction model
fitting the data captured. The data from the database table first extracted in the
form of a .CSV file.
Data pre-processing. The .CSV file contains certain extra columns which are not
required by us. These columns are dropped first. Next we need to take care of the
anomalous values such as a high peak in temperature which is impractical. This kind
of thing happens only few times but can harm our results. Hence are removed.
Analysis using linear regression. We applied the machine learning on the same
data and predicted the status and requirements of the disease treatment in advance
by applying simple linear regression model. We analysed the captured data and
found the prediction model fitting that data. In our prediction model using linear
regression we have three variables. T, W, and I are respectively the temperature,
duration of wetness of leaf and incubation period of the infection causing pathogen.
So we have analyzed the collected data and found a prediction model fitting the data
captured. Our model has three variables as such. The first of these is the temperature
(T), second is the duration of wetness (W) and the final is the incubation period of
the infection causing pathogen (I). The main purpose was to find a relationship which
makes I as a function of W and T. Later on this equation is found to be useful in finding
the vulnerability of some specific combination of wetness duration and temperature
with respect to an attack of infection. In a simple linear regression model, a single
response measurement is related to a single predictor (covariate, regressor) X for
each observation. The critical assumption of the model is that the conditional mean
function is linear as shown in equation 3.1:

E = aX (3.1)
In most problems, multiple number of predictor variables may be available. This will
result in the following ”multiple-regression” mean function as shown in equation 3.2:

E = a + b 1 X 1 + b2 X 2 + . . . (3.2)
 Precision Agriculture using IoT Data Analytics and Machine Learning 19
Table 3.3
Table of Results

Coefficient Estimated Value Standard Error True Value

Intercept 37.774 9.3111 4.057
Average Temperature -0.3328 0.1308 -2.545
Wetting Duration -0.886 0.1755 -4.563

Where a is called the intercept and the b are slopes or coefficients of X variables.
Keeping the other predictors constant, each coefficient estimates the change in the
mean response per unit increase in X. The equation that we found out is shown in
equation 3.3:
I = 37.774 – 0.3328T – 0.886W (3.3)
The equation 3.3 we obtained using linear regression model shows the incubation
period is being predicted by the temperature value and the value of wetting period.
The negative coefficients (-0.3328 and -0.886) indicates inverse relationship between
incubation period with the temperature and wetting duration. In other words we can
say that with decreasing in the values of temperature and wetting period there is an
increase in the value of I.
3.6. Results. Table 3.3 shows the table of results obtained by using linear re-
gression and shows the Estimated Value, Standard Error, True Value of Intercept,
Average Temperature and Wetting Duration. The equation 3.3 thus obtained using
linear regression model shown above indicates that the incubation period is being
predicted by the temperature value and the value of wetting period. With decreasing
in the values of temperature T and wetting period W there is an increase in the value
of incubation I. The algorithm 1 shows the various steps used in order the get the
correct results.

Algorithm 1: Apple scab prediction using IoT and Data Analytics

Input : Real time data of temperature and leaf wetness hours
Output: Apple Scab Prediction
1 i← 1 to n;
2 Deploy W SNi in Crop Field CFi ;
3 for W SNi do
4 Deploy 6 Sensors S1 , S2 , S3 , S4 , S5 , S6 ;
5 Deploy Gateway Gi ;
6 while Time ≤ 12 do
7 Collect Dataseti in the PostGreSQL Database;
8 T ime = T ime + 1;
9 end
10 foreach Dataseti do
11 Apply Data Preprocessing;
12 Do Data Analysis;
13 Get Results;
14 end
15 end

The results showed the incubation period of the areas based on safe and unsafe-
20 Ravesa Akhter and Shabir Ahmad Sofi

Fig. 3.7. Residuals vs. fitted

zones. The incubation period for Kulgam was 5 days and for Anantnag district it
was 3 days. Hence Kulgam and Anantnag were categorized as unsafe zones while as
Srinagar was categorized as safer zone under the present climatic conditions. The
system was proved to be useful for the local farmers and hence we got our results
attested. In figure 3.7 the residuals vs. fitted is a scatter plot of residuals on the y
axis and fitted values (estimated responses) on the x axis. The scatter plot is used
to detect unequal error variances, non-linearity, and outliers. Any data point that
falls directly on the estimated regression line has a residual of 0 i.e. no error in
the predicted value. If we compare the previous work done with the proposed work,
wherein they have not used the real time data for prediction of apple scab disease
hence time to respond to the disease is more but by time we come to know about the
disease the response time has already elapsed and the crop will be affected. In our
approach using the IoT for disease prediction the delay is minimised to the extent
that if a corrective mechanism like temperature control, spray of chemicals, pesticides,
watering etc for real time precise agriculture can be used. Although we may need to
increase the number of parameters for disease prediction in our proposed mechanism
in future but this work can give us a platform, architecture and algorithm to move
ahead.
4. Challenges in IoT Adoption for traditional farmers. Precision agri-
culture is a powerful technology to meet the challenges of the increasing needs from
scarce resources. Besides the advantages there are number of challenges which agri-
culturalists, farmers, researchers and scientists are facing while adopting it. For this
purpose a local survey was conducted to know what the regional people think about
it.
4.1. Survey Setup.
Site Description:. Jammu and Kashmir Union Territory is the northernmost ge-
ographical region of the Indian Subcontinent. Kashmir lies between latitudes 32◦ and
36◦ N, and longitudes 74◦ and 80◦ E. It has a different climate for every region owing
 Precision Agriculture using IoT Data Analytics and Machine Learning 21
Table 4.1
Survey of Farmers

Survey Site Duration Farmers Selected Respondents

Anantnag July2020-Sep2020 400 110
Kulgam May2020-Oct2020 300 130
Srinagar June2020-Aug2020 400 90
Total 1100 330

Table 4.2
Questions and Responses

Questions % of Farmers % of Farmers

Do you have knowledge on: Yes No
yield monitoring? 5 95
soil mapping techniques? 6 94
variable rate technology(VRT)? 3 97
precision agriculture? 7 93
data Analytics in precision agriculture? 2 98
internt of things (IoT)? 5 95

to the great variation of the level of the altitude. Wheat, maize and rice crops grown
in about 250,000 hectares 210,000 hectares and 110,000 hectares area respectively are
the major cereal crops of Jammu and Kashmir division. Apple is the valuable cash
crop of Kashmir Valley.
In India, agricultural risks are provoked by variety of factors, like climatic vari-
ability/change, extreme weather events, crop management practices and soil fertility
status etc. which ultimately leads to uncertainties in yields and prices of the grain.
We did the local survey in Kashmir Valley by using precision agriculture in the crop
fields using Information and Communication Technologies (ICT) like IoT, Machine
learning, Data analytics etc. The populations of this study are small scale farmers
to large scale farmer using simple technologies and mostly traditional ways in their
apple orchards for agricultural information to improve their productivity. In order to
bridge the gap of knowledge and skill regarding agriculture in this area, we asked some
questions through interview to know its basic causes. 1100 people were selected who
were engaged in these from three districts Kulgam, Srinagar and Anantnag where we
have deployed our proposed system . Random sampling technique was used and 330
respondents (33% from the total frame) were interviewed in study area based on the
population intensity. Table 4.1 shows the survey site, number of farmers selected in
each site and number of respondent in the sample. While this survey various ques-
tions were asked to the farmers. Most of them were uneducated, some of them were
educated, few of them have the knowledge of IoT and other technologies. In order to
know their views various questions were asked to them either through questionnaire or
by interview. Table 4.2 shows the various questions and the percentage of correspond-
ing responses in terms of yes or no. The positive (yes) response was mostly received
from those farmers who were either educated, or whose field was under investigation.

4.2. Results. From the last decade, overall amount of funds for the agronomy
area has developed enormous nearly 80%. In accordance with the experts of the
22 Ravesa Akhter and Shabir Ahmad Sofi

Challenges and Open Issues

Commercial Sectorial Technical Data Analytics

Fig. 4.1. Challenges of Adopting Precision Agriculture

agronomy sector smart agriculture is capable to take on an important role in attaining

the proliferating demands of food of the increasing population throughout the globe.
The financial worth of the worldwide smart aggie marketplace is approximately $4.6
billion with CAGR (Compound Annual Growth Rate) between 2015 and 2020 being
just a touch under 12% [80] mentioned in a fresh report. It has been predicted
in many foreign countries especially in United States alone agriculture software will
nearly increase around more than 14% between current and 2022. From the above it is
expected that development and propagation of precision farming should be vigorous,
efficient, etc. But like other technology based applications precision agriculture also
faces number of challenges as we have seen in the local survey in Jammu and Kashmir
that there are number of challenges. The challenges faced are mentioned in figure 4.1
and are discussed below:

4.2.1. Challenges based on Commercial. Due to the tremendous advantages

of the current technologies like Internet of things, wireless sensors, actuators, today’s
farmers are would be interested in business models. Using IoT technologies, they will
accumulate the data from their farms to support their revenue. The data provided by
the farmers are exploited by the most of the existing IoT platforms service providers.
They provide unrestricted limited services and full services with diverse level of sub-
scriptions. This becomes the part of argument for farmers to supervise their owned
data.
Budget. While developing any solution for smart agriculture, cost analysis should
be done. As we know in IoT, the initial costs are very high due to the variety of
sensors, gateways, base station infrastructure [81]. After this maintenance is also an
important part of cost analysis. Here the researcher’s goal should always remain such
that increasing the production while decreasing the cost requirement.
Unawareness of Information and Technology era. As we know most of the agri-
cultural working is happening in rural areas where farmers are not well educated.
They are unable to accept the new trends and technologies early. This is the reason
of slowing IoT in rural areas. So in order to overcome this issue, we need to educate
farmers in order to generate best results [8, 81].
Loss of manual employment. Around 60-70% of the workforce are working in
the primary sector globally. The number is high particularly in Asia, Africa and
Oceania. As the agricultural practices become automated and mechanized -a very
great percentage of the agronomy workforce will lose their employment. It will make
 Precision Agriculture using IoT Data Analytics and Machine Learning 23

it necessary to accommodate these employs in other employable sectors. This will be

only possible if these sectors are able to absorb such a very huge volume of unemployed
people. But due to the poverty in most of the developing countries particularly in
India it is hardly possible. So besides the large-scale benefits the precision agriculture
lead but a massive displacement of labors may cause discontent and disappointment
among populace.
Benefits not immediately apparent. While developing any system in any field,
QoS is very important. In big IoT data and machine learning used in precision
agriculture QoS should be highlighted at each layer so that system will give best
results at end [82, 83]. There are number of challenges especially while transferring
data from one layer to another QoS is usually compromised. Hence there is a need to
do more research work by providing a solution that will guarantee QoS throughout
the network system at each layer.
4.2.2. Challenges based on Sectorial. There are number of parameters that
need to considered for distribution of IoT systems. One of the main factor is the abil-
ity of an IoT device to place anywhere for perfect operation and remain connected
globally. This means the ability to connect anywhere at anytime with least configu-
ration. Other features are ability to support roaming and provide reliability to the
system for proper results. We need to consider the IoT technology infrastructure for
the static IoT devices
Size of individual management zones. Production function refers to the quantity
and quality of output keeping the land area under cultivation same. But the pro-
duction function varies for most of the crops, in different zones of field etc. [80]. But
unfortunately farmers are not aware about it. Precision agriculture cannot be opti-
mized unless and until farmers become aware about varying production function e.g.
excessive or moderate use of fertilizers, pesticides etc. will lead to crop damage.
Interoperability. It refers to the capability of a device, product, service, system to
be operated with others reciprocally. With the growing Original Equipment Manufac-
turers (OEM) approaching with innovative and advanced precision agronomy equip-
ments, devices, platforms, etc., interoperability becomes the most important point
of concern [80]. This involves number of issues related to the technical, semantic,
syntactic and organization interoperability [84–87]. So in order to overcome this issue
researchers should focus on building the farmer friendly platforms which are holistic
instead of smart standalone devices, gateways or other smart appliance.
Supervisory challenges. Organizing, managing and permissible foundation con-
cerning the authority and proprietorship of field data between the owners of the fields
and the data companies is required to sort out. Regulations like data privacy, data
security, technical issues, available resources like bandwidth, etc. differ from coun-
try to country. Differing these supervisory features affect the use cases related to
the agriculture. Hence due to the heterogeneity of supervising techniques becomes a
challenge for most of the farmers.
4.2.3. Challenges based on Technicality. Technology make jobs easy. Every
work based on technology becomes automated using IoT and other mechanized ways.
This increases the dependence of health, traffic, home and other related jobs on the
technology. It can be very dangerous at times even if any individual subsystem of
the system will stop working. Hence can become the cause of loss. If we take the
example of the precision agriculture as in our case most of the hardware units are
exposed to the outside environment. This makes it more possible that the sensors
may get destroyed due the the various reasons like, rain, wind, snow etc. So in short
24 Ravesa Akhter and Shabir Ahmad Sofi

we can say that we cannot meet the food safety. Compromising the food safety means
system is useless. Sometimes the downtime can be caused by power failure. Hence
we need to make sure we are keeping the backups for everything in order to meet the
requirement. Single point failure can never lead to success.
Internet Connectivity. In rural areas across the globe particularly in developing
countries like India high speed and reliable internet connectivity is absent [80]. Due to
the wireless communication various issues like multipath propagation, which occurs
due to the buildings trees etc. the IoT system is not able to work consistently. So
there is a need to develop most robust and reliable technologies [36].
Security Factor. It refers when the said system is compromised to restore personal
information. It is one of the most important issues in every field of study. In our case
of Big IoT Data and machine learning it may compromise any sort of information at
any layer lower or higher [8]. The main focus of Researchers remain to secure the cus-
tomers data. With the innovations and technological revolutions each and everything
has become dependent on cloud computing, IoT, Big data Machine Learning. But
unfortunately these systems don’t provide solid Service Level Agreements (SLA) [8].
Although there are number of ways to enforce data security like encryption, temporary
identification, etc. But decisions should be made based on moral factors that is what
to adopt, when to adopt, where to adopt, how to adopt and why to adopt? [8, 88].
There are number of existing solutions which are not pertinent [8]. They provide
solutions which are applicable for static data sets. But the in our case of big IoT
data have dynamic nature [8]. In precision agriculture we cannot use the complex
and sophisticated algorithms due to limited resources like memory, processing, power
communication capabilities etc. In precision agriculture and farming the IoT sensing
devices are most defenseless especially to environmental tempering like attacks by
animals, thieves, and alteration of physical address [89, 90]. The IoT system when
used in agriculture are mostly targeted by device capture attacks [89, 91], the higher
layers are then targeted by Dos attacks [84]. The farmers usually prefer the devices
which are cheap but they are not supported by security and privacy related features.
Hence to make Internet of things more acceptable for every kind of farmer there is a
necessity of strict security and endowment policies for precision agriculture [80].
Absence of Scalability and configuration. IoT system includes billions of devices
which are developed and deployed across the globe over different locations. Existing
systems and protocols should have the ability of support this large number of IoT
nodes e.g. Sigfox gateway, Lora and Ingenu can support up to 106 ,104 and 104 nodes
respectively [84]. This requires proper management system for each device and unique
identification numbers.
Reliability. IoT sensing devices are mostly distributed in outdoor surrounding to
sense the environmental conditions. This exposes IoT system to harsh environmental
conditions which in turn destroys the sensors, gateways, etc. and hence creates the
communication failures [84]. Hence physical safety of these devices should be ensured
so that big IoT data precision system for agriculture will be properly developed.
Selection of technology. Number of challenges arises while developing a smart
precision agriculture system using IoT and big data. It is due to the fact that all the
devices which exist at the perception layer are directly exposed to harsh environmental
conditions such as high or low temperature, extreme humidity, storm, rain and many
other possible dangers which destroy electronic circuits and devices [81]. In precision
agriculture to maintain the system working in open fields is a challenging task. It is
the responsibility of researchers to address these issues.
 Precision Agriculture using IoT Data Analytics and Machine Learning 25

Optimization of scarce resources. To determine the requirement of resources so

that profit margins can be known in advance but due to the varying nature of farm
sizes and different types of sensor requirement this is a challenging task [84]. In order
to know the requirement of resources precisely there is a need to develop complex
algorithm and mathematical models. Again the resources are limited in IoT system,
e.g. Precision agriculture advantages have already been discussed. However, the need
of powerful gateways, smart sensors, data centers and other IoT related gadgets can
lead to a higher consumption of energy [80]. Hence it is very important to determine
optimal resource allocation while maximizing agricultural products and profits and
minimizing the cost.

4.2.4. Data Analytics. Todays world is running every business and organiza-
tion to get more profit using the data analytics. Same is the case with the smart
agriculture. To deal wit the data , researchers face number of challenges which are
mentioned under data analytics challenge category.
Integration. It refers to combine the data coming from different sources of differ-
ent formats into a uniform view [92]. Good information is achieved from good data
which is achieved through proper integration [93]. But it is a challenging task to inte-
grate data from diverse sources [94]. To adjust the structure in semi-structured and
unstructured data is again an issue to be addressed [95,96]. In [96] novel data mining
methodologies have been investigated for IoT scenario with respect edge computing
using two types of K-Means clustering algorithm ; distributed and centralized. Per-
formance analysis helps to choose the best among these two versions based on their
computation, energy consumption and communication requirements. There is a need
to develop solutions for integrating data from multiple sources efficiently.
Knowledge Mining. It refers to generate efficient and best fitting descriptive and
predictive solutions for big IoT data which in turn can be generalized for new data
items [8, 97]. Information extraction and data exploration are the challenges which
were evolved due to big data and cloud computing platforms [8, 98]. Due to nature of
big IoT data every task related to data mining becomes a challenge like heterogeneous
communication, integration, exploration and extraction process, cleansing, reduction,
transmission [99–102]. The researchers are trying to find solutions to these issues.
They have brought in sequential programming models,parallel programming models
and proposed diverse algorithms to deal with big IoT data. Big data is increasing
making precision agriculture data driven; this will become helpful only when we make
sense of it using technology.
Visualization. It is an important part in IoT data especially while handling IoT
related systems in which data is produced enormously [8]. Again it is a very challeng-
ing task while dealing with big IoT data due to the structured, semi-structured and
unstructured nature of it. So we did not get good and clear results. Cloud computing
platforms enriched with GUI facilities help us to find good insights [103]. Dimension-
ality reduction techniques are very helpful to deal with the big IoT data [104]. Again
if we try to use parallelization techniques to deal with small manageable tasks is again
a challenge in precision agriculture big IoT data [105].

5. Conclusion and Future Work. The arable land is reducing slowly due to
constructions (houses, dams, factories, industries, etc.), natural shrinking of arable
land (floods, earthquakes, landslides etc.). Hence, the emphasis on superior and pro-
ficient crop disease approaches is prerequisite so that increasing food demand of the
growing population can be fulfilled. The paper has given an extensive literature survey
26 Ravesa Akhter and Shabir Ahmad Sofi

on the precision agriculture using IoT data analytics and machine learning. Further-
more, the applications of these technologies in precision agriculture are highlighted.
Moreover the paper tried to address one of the problems faced in apple crop in re-
gions like Kashmir. Since the apple growers are still using the classical approaches
of disease prediction without any technological intervention like IoT/ WSN. One of
the major advantages of the proposed approach will be real time measures against
any possible disease like scab if predicted precisely and in a timely manner. Results
from a case study on adoption of apple scab disease prediction in the orchards of
Kashmir has shown improvement in terms of dissemination of information regarding
the factors/parameters responsible for the disease aforementioned. Finally, the paper
highlighted the issues faced while developing and deploying such applications in real
time, for this a local survey was conducted to know what are the views of people
regarding precision agriculture.
Although many challenges are ahead before implementing the proposed framework
at large scale. These include initial cost of implementation, deployment, training,
weather conditions and other parameters. But once the aforementioned limitations
are overwhelmed, the profits will turn into visible and workable form. The work
shall be extended in future to include more parameters influencing the crop. The
paper generalize that precision Aggie is stand on four stakes; Appropriate source,
Appropriate place, Appropriate quantity and Appropriate time.

REFERENCES

[1] K. Bhargava, A. Kashyap, T. A. Gonsalves, Wireless sensor network based advisory system for
apple scab prevention, in: 2014 Twentieth national conference on communications (NCC),
IEEE, 2014, pp. 1–6.
[2] S. S. Shinde, M. Kulkarni, Review paper on prediction of crop disease using iot and ma-
chine learning, in: 2017 International Conference on Transforming Engineering Education
(ICTEE), IEEE, 2017, pp. 1–4.
[3] E. Oerke, Crop losses to pests, The Journal of Agricultural Science 144 (2006) 31.
[4] S. Savary, A. Ficke, J.-N. Aubertot, C. Hollier, Crop losses due to diseases and their implica-
tions for global food production losses and food security (2012).
[5] R. Buyya, A. V. Dastjerdi, Internet of Things: Principles and paradigms, Elsevier, 2016.
[6] K. Ashton, et al., That ‘internet of things’ thing, RFID journal 22 (7) (2009) 97–114.
[7] M. R. Abdmeziem, D. Tandjaoui, I. Romdhani, Architecting the internet of things: state of
the art, in: Robots and Sensor Clouds, Springer, 2016, pp. 55–75.
[8] M. Marjani, F. Nasaruddin, A. Gani, A. Karim, I. A. T. Hashem, A. Siddiqa, I. Yaqoob, Big
iot data analytics: architecture, opportunities, and open research challenges, IEEE Access
5 (2017) 5247–5261.
[9] S. C. Fortino, Giancarlo, G. Spezzano, M. Zhou, Internet of things as system of systems: A
review of methodologies, frameworks, platforms, and tools, IEEE Transactions on Systems,
Man, and Cybernetics: Systems.
[10] H. M. Jawad, R. Nordin, S. K. Gharghan, A. M. Jawad, M. Ismail, Energy-efficient wireless
sensor networks for precision agriculture: A review, Sensors 17 (8) (2017) 1781.
[11] H.-N. Dai, R. C.-W. Wong, H. Wang, Z. Zheng, A. V. Vasilakos, Big data analytics for large-
scale wireless networks: Challenges and opportunities, ACM Computing Surveys (CSUR)
52 (5) (2019) 1–36.
[12] R. Mital, J. Coughlin, M. Canaday, Using big data technologies and analytics to predict sensor
anomalies, amos (2015) 84.
[13] J. R. Saura, B. R. Herráez, A. Reyes-Menendez, Comparing a traditional approach for financial
brand communication analysis with a big data analytics technique, IEEE Access 7 (2019)
37100–37108.
[14] Y.-D. Kim, Y.-M. Yang, W.-S. Kang, D.-K. Kim, On the design of beacon based wireless sensor
network for agricultural emergency monitoring systems, Computer standards & interfaces
36 (2) (2014) 288–299.
[15] I. Jawhar, N. Mohamed, J. Al-Jaroodi, S. Zhang, A framework for using unmanned aerial
 Precision Agriculture using IoT Data Analytics and Machine Learning 27

vehicles for data collection in linear wireless sensor networks, Journal of Intelligent &
Robotic Systems 74 (1-2) (2014) 437–453.
[16] M. Ayaz, M. Ammad-Uddin, Z. Sharif, A. Mansour, E.-H. M. Aggoune, Internet-of-things (iot)-
based smart agriculture: Toward making the fields talk, IEEE Access 7 (2019) 129551–
129583.
[17] J. Xia, Z. Tang, X. Shi, L. Fan, H. Li, An environment monitoring system for precise agriculture
based on wireless sensor networks, in: 2011 Seventh International Conference on Mobile
Ad-hoc and Sensor Networks, IEEE, 2011, pp. 28–35.
[18] P. Russom, et al., Big data analytics, TDWI best practices report, fourth quarter 19 (4) (2011)
1–34.
[19] S. Oswal, S. Koul, Big data analytic and visualization on mobile devices, in: Proc. Nat. Conf.
New Horizons IT-NCNHIT, 2013, p. 223.
[20] B. Suksawat, P. Komkum, Pineapple quality grading using image processing and fuzzy logic
based on thai agriculture standards, in: 2015 International Conference on Control, Au-
tomation and Robotics, IEEE, 2015, pp. 218–222.
[21] P. Tripicchio, M. Satler, G. Dabisias, E. Ruffaldi, C. A. Avizzano, Towards smart farming
and sustainable agriculture with drones, in: 2015 International Conference on Intelligent
Environments, IEEE, 2015, pp. 140–143.
[22] M. Jhuria, A. Kumar, R. Borse, Image processing for smart farming: Detection of disease
and fruit grading, in: 2013 IEEE Second International Conference on Image Information
Processing (ICIIP-2013), IEEE, 2013, pp. 521–526.
[23] A. Kapoor, S. I. Bhat, S. Shidnal, A. Mehra, Implementation of iot (internet of things) and
image processing in smart agriculture, in: 2016 International Conference on Computation
System and Information Technology for Sustainable Solutions (CSITSS), IEEE, 2016, pp.
21–26.
[24] M. Roopaei, P. Rad, K.-K. R. Choo, Cloud of things in smart agriculture: Intelligent irrigation
monitoring by thermal imaging, IEEE Cloud computing 4 (1) (2017) 10–15.
[25] C. Cambra, S. Sendra, J. Lloret, L. Garcia, An iot service-oriented system for agriculture
monitoring, in: 2017 IEEE International Conference on Communications (ICC), IEEE,
2017, pp. 1–6.
[26] M. Bendre, R. Thool, V. Thool, Big data in precision agriculture: Weather forecasting for
future farming, in: 2015 1st International Conference on Next Generation Computing
Technologies (NGCT), IEEE, 2015, pp. 744–750.
[27] N. Ahmed, D. De, I. Hussain, Internet of things (iot) for smart precision agriculture and
farming in rural areas, IEEE Internet of Things Journal 5 (6) (2018) 4890–4899.
[28] J. Muangprathub, N. Boonnam, S. Kajornkasirat, N. Lekbangpong, A. Wanichsombat, P. Nil-
laor, Iot and agriculture data analysis for smart farm, Computers and electronics in agri-
culture 156 (2019) 467–474.
[29] F. Fonthal, et al., Design and implementation of wsn and iot for precision agriculture in tomato
crops, in: 2018 IEEE ANDESCON, IEEE, 2018, pp. 1–5.
[30] S. Trilles Oliver, J. Torres-Sospedra, O. Belmonte, F. J. Zarazaga-Soria, A. González Pérez,
J. Huerta, Development of an open sensorized platform in a smart agriculture context: A
vineyard support system for monitoring mildew disease.
[31] D. Sikeridis, E. E. Tsiropoulou, M. Devetsikiotis, S. Papavassiliou, Wireless powered public
safety iot: A uav-assisted adaptive-learning approach towards energy efficiency, Journal of
Network and Computer Applications 123 (2018) 69–79.
[32] T.-C. Hsu, H. Yang, Y.-C. Chung, C.-H. Hsu, A creative iot agriculture platform for cloud fog
computing, Sustainable Computing: Informatics and Systems (2018) 100285.
[33] G. Lavanya, C. Rani, P. Ganeshkumar, An automated low cost iot based fertilizer intimation
system for smart agriculture, Sustainable Computing: Informatics and Systems.
[34] A. Khanna, S. Kaur, Evolution of internet of things (iot) and its significant impact in the field
of precision agriculture, Computers and electronics in agriculture 157 (2019) 218–231.
[35] P. Sethi, S. R. Sarangi, Internet of things: architectures, protocols, and applications, Journal
of Electrical and Computer Engineering 2017.
[36] T. Ojha, S. Misra, N. S. Raghuwanshi, Wireless sensor networks for agriculture: The state-of-
the-art in practice and future challenges, Computers and Electronics in Agriculture 118
(2015) 66–84.
[37] J.-c. Zhao, J.-f. Zhang, Y. Feng, J.-x. Guo, The study and application of the iot technology in
agriculture, in: 2010 3rd International Conference on Computer Science and Information
Technology, Vol. 2, IEEE, 2010, pp. 462–465.
[38] G. N. Balaji, V. Nandhini, S. Mithra, N. Priya, R. Naveena, Iot based smart crop monitoring
in farm land, Imperial Journal of Interdisciplinary Research (IJIR) Vol 4 (2018) 88–92.
28 Ravesa Akhter and Shabir Ahmad Sofi

[39] P. P. Jayaraman, A. Yavari, D. Georgakopoulos, A. Morshed, A. Zaslavsky, Internet of things

platform for smart farming: Experiences and lessons learnt, Sensors 16 (11) (2016) 1884.
[40] M. Paustian, L. Theuvsen, Adoption of precision agriculture technologies by german crop
farmers, Precision agriculture 18 (5) (2017) 701–716.
[41] T. Rumpf, A.-K. Mahlein, U. Steiner, E.-C. Oerke, H.-W. Dehne, L. Plümer, Early detection
and classification of plant diseases with support vector machines based on hyperspectral
reflectance, Computers and electronics in agriculture 74 (1) (2010) 91–99.
[42] S. Singh, S. Gupta, Digital image processing techniques for early detection and classification
of different diseased plants, International Journal of Bio-Science and Bio-Technology 8 (4)
(2016) 61–66.
[43] S. Singh, S. Gupta, Apple scab and marsonina coronaria diseases detection in apple leaves
using machine learning, International Journal of Pure and Applied Mathematics 118 (2018)
1151–1166.
[44] X.-L. Huang, X. Ma, F. Hu, Machine learning and intelligent communications, Mobile Networks
and Applications 23 (1) (2018) 68–70.
[45] M. Geetha, Application of classification technique in data mining for agricultural land, IJAR-
CCE (2015) 352–355.
[46] A. Aggelopoulou, D. Bochtis, S. Fountas, K. C. Swain, T. Gemtos, G. Nanos, Yield prediction
in apple orchards based on image processing, Precision Agriculture 12 (3) (2011) 448–456.
[47] I. M. MAZILU, R. TRANDAFIR, Pomosat-‘an orchard system for monitoring and model-
ing apple scab (venturia inaequalis)’, Romica TRANDAFIR Technical University of Civil
Engineering, Bucharest.
[48] B. Cetişli, E. Büyükçingir, Time series prediction of apple scab using meteorological measure-
ments, African Journal of Biotechnology 12 (35).
[49] K. Foughali, K. Fathallah, A. Frihida, Using cloud iot for disease prevention in precision
agriculture, Procedia computer science 130 (2018) 575–582.
[50] F. Balducci, D. Impedovo, G. Pirlo, Machine learning applications on agricultural datasets for
smart farm enhancement, Machines 6 (3) (2018) 38.
[51] M. A. Hamad, M. E. S. Eltahir, A. E. M. Ali, A. M. Hamdan, Efficiency of using smart-mobile
phones in accessing agricultural information by smallholder farmers in north kordofan–
sudan, Available at SSRN 3240758.
[52] J. Maha Kavya Sri, V. Narendra, V. Pai, Implementing and testing of iot technology in agricul-
ture, International Journal of Recent Technology and Engineering 7 (65) (2019) 848–852.
[53] S. Manna, S. S. Bhunia, N. Mukherjee, Vehicular pollution monitoring using iot, in: Inter-
national Conference on Recent Advances and Innovations in Engineering (ICRAIE-2014),
IEEE, 2014, pp. 1–5.
[54] C. Dinkins, C. Jones, Interpretation of soil test reports for agriculture (April 2019).
URL https://www.agrocares.com/en/products/lab-in-the-box/
[55] P. V. Santhi, N. Kapileswar, V. K. Chenchela, C. V. S. Prasad, Sensor and vision based
autonomous agribot for sowing seeds, in: 2017 International Conference on Energy, Com-
munication, Data Analytics and Soft Computing (ICECDS), IEEE, 2017, pp. 242–245.
[56] Ice, snow, and glaciers and the water cycle (October 2020).
URL https://water.usgs.gov/edu/watercycleice.html
[57] What percent of earth is water? (October 2020).
URL https://phys.org/news/2014-12-percent-earth.html
[58] Water facts–worldwide water supply. (September 2020).
URL https://www.usbr.gov/mp/arwec/water-facts-ww-water-sup.html
[59] Water for sustainable food and agriculture by fao (september 2020).
URL https://www.fao.org/3/a-i7959e.pdf
[60] M. Motoshita, Y. Ono, S. Pfister, A.-M. Boulay, M. Berger, K. Nansai, K. Tahara, N. Itsubo,
A. Inaba, Consistent characterisation factors at midpoint and endpoint relevant to agri-
cultural water scarcity arising from freshwater consumption, The International Journal of
Life Cycle Assessment 23 (12) (2018) 2276–2287.
[61] L. Zhang, I. K. Dabipi, W. L. Brown Jr, Internet of things applications for agriculture, Internet
of Things A to Z: Technologies and Applications (2018) 507–528.
[62] Irrigation & water use (september 2020).
URL https://www.ers.usda.gov/topics/farm-practicesmanagement/
irrigationwateruse/
[63] P. Benincasa, S. Antognelli, L. Brunetti, C. A. Fabbri, A. Natale, V. Sartoretti, G. Modeo,
M. Guiducci, F. Tei, M. Vizzari, Reliability of ndvi derived by high resolution satellite and
uav compared to in-field methods for the evaluation of early crop n status and grain yield
in wheat, Experimental Agriculture 54 (4) (2018) 604–622.
 Precision Agriculture using IoT Data Analytics and Machine Learning 29

[64] H. Liu, X. Wang, J. Bing-kun, Study on ndvi optimization of corn variable fertilizer applicator.,
INMATEH-Agricultural Engineering 56 (3).
[65] A. Colaço, J. Molin, Variable rate fertilization in citrus: A long term study, Precision Agricul-
ture 18 (2) (2017) 169–191.
[66] B. Basso, B. Dumont, D. Cammarano, A. Pezzuolo, F. Marinello, L. Sartori, Environmental
and economic benefits of variable rate nitrogen fertilization in a nitrate vulnerable zone,
Science of the total environment 545 (2016) 227–235.
[67] N. Khan, G. Medlock, S. Graves, S. Anwar, Gps guided autonomous navigation of a small
agricultural robot with automated fertilizing system, Tech. rep., SAE Technical Paper
(2018).
[68] S. Suradhaniwar, S. Kar, R. Nandan, R. Raj, A. Jagarlapudi, Geo-icdts: Principles and appli-
cations in agriculture, in: Geospatial Technologies in Land Resources Mapping, Monitoring
and Management, Springer, 2018, pp. 75–99.
[69] J. Shi, X. Yuan, Y. Cai, G. Wang, Gps real-time precise point positioning for aerial triangula-
tion, GPS solutions 21 (2) (2017) 405–414.
[70] Keeping plant pests and diseases at bay: Experts focus on global measures. (October 2020).
URL http://www.fao.org/news/story/en/item/280489/icode/
[71] R. Oberti, M. Marchi, P. Tirelli, A. Calcante, M. Iriti, E. Tona, M. Hočevar, J. Baur, J. Pfaff,
C. Schütz, et al., Selective spraying of grapevines for disease control using a modular
agricultural robot, Biosystems engineering 146 (2016) 203–215.
[72] S. Kim, M. Lee, C. Shin, Iot-based strawberry disease prediction system for smart farming,
Sensors 18 (11) (2018) 4051.
[73] R. Venkatesan, G. J. W. Kathrine, K. Ramalakshmi, Internet of things based pest management
using natural pesticides for small scale organic gardens, Journal of Computational and
Theoretical Nanoscience 15 (9-10) (2018) 2742–2747.
[74] A. Wietzke, C. Westphal, P. Gras, M. Kraft, K. Pfohl, P. Karlovsky, E. Pawelzik, T. Tscharn-
tke, I. Smit, Insect pollination as a key factor for strawberry physiology and marketable
fruit quality, Agriculture, Ecosystems & Environment 258 (2018) 197–204.
[75] S.-O. Chung, M.-C. Choi, K.-H. Lee, Y.-J. Kim, S.-J. Hong, M. Li, et al., Sensing technologies
for grain crop yield monitoring systems: A review, Journal of Biosystems Engineering
41 (4) (2016) 408–417.
[76] S. Gholami, Z. K. Pishva, G. H. Talaei, M. Amini, Effects of biological and chemical fertilizers
nitrogen on yield and yield components in cumin (cuminum cyminum l.), International
Journal of Biosciences (IJB) 4 (12) (2014) 93–99.
[77] P. Udomkun, M. Nagle, D. Argyropoulos, B. Mahayothee, J. Müller, Multi-sensor approach to
improve optical monitoring of papaya shrinkage during drying, Journal of Food Engineering
189 (2016) 82–89.
[78] W. E. MacHardy, D. M. Gadoury, et al., A revision of mills’ s criteria for predicting apple scab
infection periods., Phytopathology 79 (3) (1989) 304–310.
[79] T. Belete, N. Boyraz, Critical review on apple scab (venturia inaequalis) biology, epidemiology,
economic importance, management and defense mechanisms to the causal agent, Journal
of Plant Physiology and Pathology 5 (2) (2017) 2.
[80] H. Fakhruddin, “precision agriculture: Top 15 challenges and issues,” (September 2020).
URL https://plagiarismdetector.net/teks.co.in/site/blog/
precision-agriculture-top-15challenges-and-issues
[81] M. S. Farooq, S. Riaz, A. Abid, K. Abid, M. A. Naeem, A survey on the role of iot in agriculture
for the implementation of smart farming, IEEE Access 7 (2019) 156237–156271.
[82] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, M. Ayyash, Internet of things:
A survey on enabling technologies, protocols, and applications, IEEE communications
surveys & tutorials 17 (4) (2015) 2347–2376.
[83] Y. Huang, C. Zhou, N. Cao, L. Zhou, Research on application of local fruit e-commerce based
on internet of things, in: 2017 IEEE International Conference on Computational Science
and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous
Computing (EUC), Vol. 2, IEEE, 2017, pp. 191–194.
[84] O. Elijah, T. A. Rahman, I. Orikumhi, C. Y. Leow, M. N. Hindia, An overview of internet of
things (iot) and data analytics in agriculture: Benefits and challenges, IEEE Internet of
Things Journal 5 (5) (2018) 3758–3773.
[85] C. Brewster, I. Roussaki, N. Kalatzis, K. Doolin, K. Ellis, Iot in agriculture: Designing a
europe-wide large-scale pilot, IEEE communications magazine 55 (9) (2017) 26–33.
[86] O. Vermesan, European research cluster on the internet of things-outlook of iot activities in
europe.
[87] V. M. Tayur, R. Suchithra, Review of interoperability approaches in application layer of inter-
30 Ravesa Akhter and Shabir Ahmad Sofi

net of things, in: 2017 International Conference on Innovative Mechanisms for Industry
Applications (ICIMIA), IEEE, 2017, pp. 322–326.
[88] C.-W. Tsai, C.-F. Lai, H.-C. Chao, A. V. Vasilakos, Big data analytics: a survey, Journal of
Big data 2 (1) (2015) 1–32.
[89] P. Varga, S. Plosz, G. Soos, C. Hegedus, Security threats and issues in automation iot, in: 2017
IEEE 13th International Workshop on Factory Communication Systems (WFCS), IEEE,
2017, pp. 1–6.
[90] J. Duan, D. Gao, D. Yang, C. H. Foh, H.-H. Chen, An energy-aware trust derivation scheme
with game theoretic approach in wireless sensor networks for iot applications, IEEE Inter-
net of Things Journal 1 (1) (2014) 58–69.
[91] A. Newell, H. Yao, A. Ryker, T. Ho, C. Nita-Rotaru, Node-capture resilient key establishment
in sensor networks: Design space and new protocols, ACM Computing Surveys (CSUR)
47 (2) (2014) 1–34.
[92] B. B. Ahamed, T. Ramkumar, S. Hariharan, Data integration progression in large data source
using mapping affinity, in: 2014 7th International Conference on Advanced Software En-
gineering and Its Applications, IEEE, 2014, pp. 16–21.
[93] J. Liu, X. Zhang, Data integration in fuzzy xml documents, Information Sciences 280 (2014)
82–97.
[94] A. Ma’ayan, A. D. Rouillard, N. R. Clark, Z. Wang, Q. Duan, Y. Kou, Lean big data integration
in systems biology and systems pharmacology, Trends in pharmacological sciences 35 (9)
(2014) 450–460.
[95] F. Chen, P. Deng, J. Wan, D. Zhang, A. V. Vasilakos, X. Rong, Data mining for the internet
of things: literature review and challenges, International Journal of Distributed Sensor
Networks 11 (8) (2015) 431047.
[96] C. Savaglio, P. Gerace, G. Di Fatta, G. Fortino, Data mining at the iot edge, in: 2019 28th
International Conference on Computer Communication and Networks (ICCCN), IEEE,
2019, pp. 1–6.
[97] A. Mukhopadhyay, U. Maulik, S. Bandyopadhyay, C. A. C. Coello, A survey of multiobjec-
tive evolutionary algorithms for data mining: Part i, IEEE Transactions on Evolutionary
Computation 18 (1) (2013) 4–19.
[98] T. Hu, H. Chen, L. Huang, X. Zhu, A survey of mass data mining based on cloud-computing,
in: Anti-counterfeiting, Security, and Identification, IEEE, 2012, pp. 1–4.
[99] P. Lerdsuwan, P. Phunchongharn, An energy-efficient transmission framework for iot monitor-
ing systems in precision agriculture, in: International Conference on Information Science
and Applications, Springer, 2017, pp. 714–721.
[100] A. Khattab, A. Abdelgawad, K. Yelmarthi, Design and implementation of a cloud-based iot
scheme for precision agriculture, in: 2016 28th International Conference on Microelectron-
ics (ICM), IEEE, 2016, pp. 201–204.
[101] H. Liu, Z. Meng, S. Cui, A wireless sensor network prototype for environmental monitoring in
greenhouses, in: 2007 International Conference on Wireless Communications, Networking
and Mobile Computing, IEEE, 2007, pp. 2344–2347.
[102] N. Ahmed, H. Rahman, M. I. Hussain, A comparison of 802.11 ah and 802.15. 4 for iot, Ict
Express 2 (3) (2016) 100–102.
[103] L. Wang, G. Wang, C. A. Alexander, Big data and visualization: methods, challenges and
technology progress, Digital Technologies 1 (1) (2015) 33–38.
[104] A. T. Azar, A. E. Hassanien, Dimensionality reduction of medical big data using neural-fuzzy
classifier, Soft computing 19 (4) (2015) 1115–1127.
[105] H. Childs, B. Geveci, W. Schroeder, J. Meredith, K. Moreland, C. Sewell, T. Kuhlen, E. W.
Bethel, Research challenges for visualization software, Computer 46 (5) (2013) 34–42.