Challenges of Artificial Intelligence Irrigation System using WSN

Dr. Gowthami V1, Dr. A. Manimuthu2, B Shylaja 3

Assistant Professor, School of Sciences and Computer Studies, CMR University, Bengaluru, Karnataka1
Assistant Professor, Department of Data Science, Loyola College, Chennai, Tamilnadu2
Assistant Professor, BCA, Mahalashmi Women’s College of Arts & Science, Chennai, Tamilnadu3
[email protected], [email protected] [email protected]

Abstract

There is a growing need for readily available freshwater bases to meet the growing demand as the world's
population and economy expand quickly. But this has led to a number of problems, including the worldwide
water crisis, drought, and freshwater rebase constraint. Despite their high-water use, traditional irrigation
systems are used by many farmers globally to address this problem. Thus, it is necessary to increase the
efficiency of water use in irrigated agricultural. Better tracking and management of irrigated farming can be
accomplished by utilizing the Internet of Things and cutting-edge switch technology. The results of a
thorough literature learning of advanced switch systems and irrigation tracking are presented in this paper,
with an emphasis on recent research that has been published in the past four years. The most recent learning
on advanced switch techniques and precision irrigation tracking are highlighted. This learning intends to be a
useful tool for academics looking to stay current on the most recent advancements and pinpoint research
gaps that need attention, as well as for individuals interested in comprehending tracking and advanced switch
prospects in the context of irrigated agriculture.

1.Introduction

More than 70% of the world's freshwater rebases are currently used for agriculture as a result of growing
population levels and the resulting demand for increased food production [1]. Traditional irrigation
management is beset by issues such as low productivity and poor water-use efficiency [2]. Consequently,
climate change and global warming have a dynamic impact on the amount of precipitation that can be
applied to irrigate crops [3]. A vital first step in attaining food security is sustainable targeted irrigation,
which lessens the effects of drought-induced water shortages and rainfall fluctuations. Accurate irrigation
scheduling guarantees that water is given to plants exactly when and where it is needed in the right quantities
to compensate for water lost through evaporation, runoff, and deep percolation [4]. Controlling Irrigation
Systems Careful tracking and optimized management will optimize efficiency and save costs by conserving
water and the related indirect energy use [5, 6]. Through the integration of wireless sensor network (WSN)
technology and the Internet of Things, smart agriculture applications have successfully accomplished
controlled tracking of agricultural activities. Thanks to the quick successes of remote sensing, this has led to
a more profound understanding of the dynamic changes in weather, soil, and crop conditions during the
growing season. Examples of IoT-enabled sensors or equipment that can be used to continuously pool real-
time data from the desired area include satellites, sensors on unmArtificial Neural Networksed aerial
vehicles (UAVs) [7], and mobile irrigation platforms like lateral and center pivot moving machines [8].

Therefore, by utilizing the vast volumes of geographical data that fluctuate over time and may be collected
and stored in many cloud servers, ML models can be used to kind intelligent decisions [9]. A strong and
flexible framework for data-driven decision-making and in-depth system knowledge is offered by machine
learning. Big data technologies and edge cloud computing's capacity to learn without explicit programming
have combined to generate a new method for interpreting and extrapolating from the massive volumes of
data that sensors gather [10]. These technologies will kind it easier to transform unprocessed data into
information that can be used to decide on irrigation and take the necessary field or greenhouse operations.
Consequently, it improves energy and irrigation water efficiency, lowers tiredness, and saves money [11,
12]. Furthermore, farmers should be able to effortlessly monitor and analyse the various parameters on
smartphones or other computing systems to guide their decisions, either manually or intelligently, due to the
development of paradigms for calculating crop water needs that are based on climate and surroundings.
Furthermore, according to survey data, 90% of farmers want to use online and mobile apps to better regulate
their irrigation systems in order to increase agricultural output [13, 14]. The purpose of this learning is to
provide an overview of the applications of AI and wireless sensor networks in the irrigation sector. This
paper is organized as follows: An introduction is given in the present section. The categorization of AI
methods in irrigation systems is examined in the second section. The final segment examines earlier research
on artificial intelligence in irrigation. The use of IoT in irrigation is examined in the fourth section. The final
section discusses the drawbacks and difficulties of using AI and IoT in irrigation. A maturity appraisal is
presented in the sixth portion, and the paper is eventually closed in the seventh section.

2. Artificial Intelligence Classification for Irrigation Systems

At the Dartmouth Conference in 1956, John McCarthy coined the term "artificial intelligence" and defined it
as the engineering and technology of building intelligent machines or intelligent computer programs [15].
Artificial intelligence technology gives machines computational intelligence, which enables them to learn,
understand, and react correctly. Artificial intelligence includes machine learning (ML), fuzzy logic (FL),
natural language processing (NLP), swarm intelligence (SI), expert systems (ES), deep learning (DL), and
computer vision (CV). Numerous industries, including agriculture, are actively researching AI algorithms
[16, 17]. These days, two of the most widely employed cutting-edge technologies in agriculture are artificial
intelligence and the Internet of Things. The IoT-based smart farming system's sensors are designed to
monitor soil nutrients and moisture levels. Additionally, research is being done on the use of AI systems to
determine the ideal soil watering needments [18]. Additionally, farmers might learn how to employ
advanced technology to increase crop production and find answers to their issues. As a result, the two most
significant technologies in the agriculture industry will be AI and the Internet of Things [15, 19]. Here, we
revisit the AI algorithms that drove the research experiments described in this learning (refer to Fig. 1).

Fig 1: Architecture of AI and IoT

2.1 Algorithm for fuzzy logic

Formulating the mathematical equation that explains irrigation is difficult since it is a complex system with
inherent nonlinearities. Rather than using a mathematical formula, a fuzzy regulator model (FCM) can
employ rules in a "if-then-else" framework. The process expertise of specialists would serve as the
foundation for this approach [20]. The fuzzy logic irrigation switch method is a useful switch mechanism for
ensuring irrigation accuracy and showing water usage efficiency by accurately calculating the amount of
irrigation and managing the nonlinearity associated with the process [21]. The effectiveness and
dependability of the regulator are greatly enhanced by the designer's understanding of process (plant)
dynamics, which is essential for creating efficient fuzzy rules and showing their viability using long-term,
experimentally collected data [22].

2.2 An algorithm for artificial neural networks

The learning algorithms known as Artificial Neural Networks (ANNs) are based on the data analysis
methods of natural neural systems, such the human brain. In order to process information, the human brain's
billions of neurons are always in communication with one another [10]. Artificial Neural Networks artificial
neurons are functionally equivalent to the biological neurons in the human brain because of their nonlinearity
properties, input-to-output mapping capability, and capacity to anticipate many dependent variables [23].
Artificial Neural Networks-based regulators have been used in irrigation switch systems due to their ability
to learn and adjust to the shifting conditions affecting irrigation [24]. The difficulty of creating mathematical
models from basic concepts has also been successfully addressed by Artificial Neural Networks. However,
the accuracy of the Artificial Neural Networks-based prediction model or regulator depends on how well the
data input captures the behaviour of the system. A sufficient sample duration should be chosen, and
appropriate and high-quality sensors should be employed to collect data on the necessary parameters [22].

2.3 Algorithm for machine learning

A branch of artificial intelligence called Machine Learning (ML) allows machines to learn new skills without
direct instruction [25, 26]. By learning from experience, Machine Learning (ML) seeks to enable computers
to do tasks on par with human intelligence [27]. Through the effective use of machine learning and deep
learning models, effective intelligence-based decision support systems for the sustainable and fair use of
water bases in precision irrigation management have been proven. Farmers have traditionally used their
expertise and experience to determine whether or not to irrigate, but new developments in machine learning
have enabled them to include weather and soil conditions forecasts into irrigation decisions. Prediction is an
essential part of irrigation scheduling since it enables proactive reaction and better management by knowing
the water needs, yield, and soil moisture content beforehand [28]. By employing machine learning
approaches to automatically extract new information in the form of generalized decision rules, irrigation
activities can be made more precise. In order to tackle challenging issues like classification and prediction,
machine learning techniques such as federated learning, reinforcement learning, supervised learning, and
unsupervised learning have become increasingly popular in the field of precision irrigation management
[29].

One important advantage of DL is that in some situations, the model can handle the feature extraction task.
Agriculture is only one of the numerous industries and businesses that have benefited from DL models. DL
models are frequently used to process sounds and images in agriculture. With multiple hidden layers
positioned between the input and output layers, the majority of DL algorithms are ARTIFICIAL NEURAL
Networks. Long short-term memory (LSTMs), Recurrent Neural Networks (RNNs), and convolutional
neural networks (CNNs) are examples of supervised and unsupervised learning techniques that can aid in
irrigation decision management [30, 31].

Fish schooling behaviour and bird swarming serve as inspiration for the computational optimization method
known as particle swarm optimization (PSO). By reducing water waste and increasing crop output, PSO can
be applied in an irrigation system to optimize the water allocation process. PSO shows possible solutions to
the optimization problem by generating a particle swarm. The optimal solution for each particle and the best
solution for the swarm as a whole is taken into account while adjusting each particle's position and velocity.
The particles converge toward the ideal solution as a result of these updates. By calculating the optimal
amount of water to apply to each crop based on weather, soil moisture, and crop growth phase, PSO can
optimize the distribution of water rebases in an irrigation system. Increased crop output and better
management of water rebases are possible outcomes of using this technology [32].

2.4 Algorithm for an expert system

Expert System are computer-based tools that handle complicated issues in a particular field by applying rules
and knowledge. Based on regulations and information on the crop, soil, climate, and irrigation system [34],
an Expert System can offer suggestions for irrigation management in an irrigation system [33]. The
following phases are commonly included in an irrigation system's Expert System algorithm [35].

2.4.1 Acquiring knowledge:

Compile data from specialists, scientific learning, and other bases to generate a knowledge foundation of
guidelines and facts regarding the crop, soil, climate, and irrigation system.
2.4.2 Rule-based reasoning:

● Kind recommendations for irrigation management by analysing data gathered from sensors and other
tracking devices using rules and logical reasoning.
● Utilize an inference engine to apply the rules to the data and produce suggestions depending on the
crop and irrigation system's present conditions.
● Give farmers and irrigation managers an easy-to-use interface so they can communicate with the
system, enter data, and get suggestions.
● Feedback: Track the outcomes of irrigation management choices and utilize this data to gradually
improve the guidelines and knowledge base.

By giving farmers and irrigation managers precise and timely advice, the Expert System algorithm can aid in
bettering irrigation management [36]. The Expert System can contribute to lowering water waste, increasing
crop output, and advancing sustainable agricultural methods by streamlining irrigation switch. It should be
highlighted, therefore, that the Expert System 's efficacy might need to be adjusted to local conditions and
could be impacted by variables including data quality, rule accuracy, and system maintenance [37].

2.5 Algorithm for threshold values

It is a straightforward algorithm that can switch the irrigation process and keep an eye on a number of
irrigation-related variables. Modes are changed using a Single Pole Double Throw (SPDT) switch. In one
configuration, the tool is configured solely to monitor data pertaining to watering. The term "half-active
mode" refers to this condition. The utility keeps an eye on everything in other settings and switch watering
based on relative humidity. This phase is known as Full Active Mode. The system examines the weather
when it is first turned on. The gadget sleeps for around 30 minutes when it rains; if not, it will connect to the
closest open Wi-Fi network [38]. Fig. 2 displays the threshold value algorithm's general flowchart.

2.6 Algorithm of IrrSchedult

The (Crop Water Stress Index) CWSI is used by the irrigation scheduling algorithm IrrSchedult to determine
the optimal time and amount of water needed for a crop. In order to schedule irrigation events, the algorithm
uses infrared thermometry to track the crop's level of water stress. The four primary steps of the IrrSchedult
algorithm are as follows. First, use infrared thermometry to ascertain the crop's baseline temperature.
Second, use the following formula to get the Crop Water Stress Index and take regular measurements of the
crop's canopy temperature.

Where:

● TcT_cTc = Canopy temperature (the temperature of the crop canopy)

● TminT_{\text{min}}Tmin = Minimum temperature (typically the temperature of the environment or

the soil under non-stress conditions)

● TmaxT_{\text{max}}Tmax = Maximum temperature (typically the temperature under maximum

transpiration or ideal crop conditions)

The crop is deemed to be under water stress and irrigation is planned if the Crop Water Stress Index
increases beyond a set threshold. Fourth: Determine how much water should be applied by taking into
account the crop's rate of water consumption and the interval between irrigations. The IrrSchedult algorithm
can help optimize water use, minimize water waste, and increase agricultural production by scheduling
irrigation events using the Crop Water Stress Index. It should be mentioned, nonetheless, that the algorithm's
performance could need to be adjusted to local conditions and could be impacted by variables including soil
type, weather, and irrigation system efficiency. An illustration of the "IrrSchedule" irrigation scheduling
method is presented in Fig. 3 [39].
2.7 Algorithm for Decision Support Systems

By giving farmers and irrigation managers real-time information and suggestions, the Decision Support
System (DSS) algorithm can increase the efficacy and efficiency of irrigation management. The DSS can
assist in lowering water waste, increasing crop output, and advancing sustainable agricultural methods by
streamlining irrigation management. Basic constructs like "IF," "ELSE," and "IF-ELSE" are used by the
Decision Support System algorithm to accomplish its goal. Decisions are made using sensor data, which
kinds the code simpler and improves performance, efficiency, and softness [40]. A graph outlining the
Decision Support System algorithm's general structure is displayed in Figure 4.

Fig 2. Overall flowchart for threshold value algorithm

 Fig 3. Flowchart for IrrSchedult algorithm

Fig. 4. Overall assembly of Decision Support System (DSS) algorithm

3.Existing Work
This section of the learning looks at the latest developments in intelligent irrigation systems, with a focus on
learning conducted in the last four years. The most recent research can be arranged as follows using the
irrigation systems algorithm that has been adopted:

3.1 Artificial Neural Networks

Numerous recent learning and advancements based on the Artificial Neural Networks framework
demonstrate that the use of neural networks in irrigation systems improves crop yields and conserves rebases
by enabling more accurate and efficient water management. The coefficient of uniformity (CU) values for
the four sprinkler types—ZM22, ZK30, LUXOR, and AMBO—were determined [41] using a model. It is a
trustworthy indicator of water loss. A high-pressure electric pump, a water tank, a main pipe, regulator
valves, a bypass pipe, gauges, a volumetric flow meter, a spray stand, sprinklers, and containers for
collecting samples are all included in the recommended design. Artificial Neural Networks calculates CU
values based on average wind speed, sprinkler lateral spacing, and a coarseness index (nozzle diameters).
Results from experiments showed that the recommended approach reduces water loss. Nonetheless, there
were notable variations in the statistical indicator magnitudes of the models applied throughout the testing
phases. A low-cost smart irrigation system was developed that kinds use of the Internet of Things to
facilitate smooth communication and autonomous operation of the system's components [42].

Three units kind up the system: An irrigation unit is made up of a pipeline, a water pump, and a water
supply. The soil moisture sensor, temperature and moisture sensor, and Universal Sensor Pole (USP) are all
part of the switch unit. It manages the sensors, transmits information to the server, notifies the irrigation unit,
and receives feedback from it. Additionally, it uses the Artificial Neural Networks to determine the decision.
Module for remote tracking: It consists of an HTTP server for remote tracking and a Message Queuing
Telemetry Transport (MQTT) broker that receives the sensor data transmitted by USP. According to the
findings, the recommended technology uses 67% less water than conventional techniques. To generate an
irrigation schedule, the recommended system needs to manually enter the soil type and plant information.
The proposed combining computer vision techniques with artificial neural networks to increase the
efficiency of agricultural irrigation [43]. On a center pivot irrigation system, eight IP cameras are cabled to a
Digital Video Recorder (DVR), which is connected to a laptop with an active internet connection. To
increase irrigation efficiency, generate a database of optimal agricultural irrigation parameters and use neural
network techniques (such as layered artificial neural networks, pattern recognition, and convolutional neural
networks) to generate dynamic maps of irrigation prescriptions. There is statistical support for increased
irrigation water efficiency. However, their use is restricted because to the high expenses of implementation
and upkeep.
To assist agricultural workers, It generated the Agricultural Irrigation Recommendation and Alert System
(AIRA) [44]. By carrying out three main tasks, the technology is intended to assist agricultural engineers in
selecting the optimal irrigation option. The system uses a number of sensors to collect data from the field,
such as a wind speed and intensity sensor, a soil moisture sensor, and an air humidity and temperature
sensor. The collected data is then processed in a hybrid classifier known as k-N4, which blends Artificial
Neural Networks and the k-nearest neighbour (KNN) technique. A modified PSO algorithm based on gravity
and fuzzy clustering is applied to choose the best irrigation option, alert messages are generated when water
level and pressure are low, and the incoming data is categorized using the proposed KNN technique. The M-
RSA method, on the other hand, measures low water levels while encrypting important data. The results
showed that the recommended approach helps with future financial gains, improved data security, and
effective water management. Nevertheless, the recommended system used climate, water, and soil data
without any field plants.

3.2 Prior research on fuzzy switch

Numerous recent learning and developments based on fuzzy switch techniques demonstrate that integrating
fuzzy switch into irrigation systems facilitates intelligent and adaptive decision-making processes, leading to
optimal water allocation and increased agricultural yield. Using the appropriate software, [45] generated a
real-time (Irrigation Decision Support System) IDSS based on a fuzzy inference method. The Irrigation
Decision Support System was designed to assess how well it could predict when alfalfa would be harvested
and provide recommendations for real-time irrigation scheduling. The Irrigation Decision Support System
framework consists of three main parts: the alfalfa growth model, which has been used to predict when to
harvest alfalfa, is in charge of figuring out how alfalfa height and growth are influenced by temperature.
Second, the soil water model, which uses weather prediction data to estimate (Soil Water) SW and alfalfa
water use. Thirdly, the foggy inference system uses the discrepancy between the expected and observed
values of clover height and soil moisture to calculate the quantity of irrigation. Following data collection,
Irrigation Decision Support System generates the irrigation time and volume need for real-time water
scheduling using a fuzzy inference technique. Based on the findings, the Irrigation Decision Support System
calculated the ideal irrigation schedule and quantity need for the irrigation system to function well. However,
the development of Irrigation Decision Support System does not prioritize spatial variability, agricultural
productivity, or water savings.
A (Smart Watering System) SWS was proposed for small and medium-sized fields and gardens. It is
supported by the Android app [46]. It comes with sensors for air temperature and humidity, light intensity,
and soil moisture. The recommended SWS evaluates data and generates an irrigation plan using fuzzy logic
and blockchain. Smart Watering System activates the actuators to perform irrigation tasks, regularly turning
the water tunnels ON and OFF, following a fuzzy logic system's decision based on the values of the input
variables. The recommended system's outcomes demonstrate that it is a dependable and secure instrument
for managing plant irrigation. However, the farmer must manually function the system designed to irrigate
the plants. An automated irrigation regulator based on real-time fuzzy inference was presented [47]. Three
units kind up the sensor network, which is based on the fuzzy inference system and includes the water level
sensor, soil moisture sensor, air temperature sensor, humidity sensor, and switch unit. Web-logger and
GPRS-based communication module based on the LabVIEW platform (Laboratory Virtual Instrumentation
Engineering Workbench). The preset parameters of soil moisture, humidity, tank water level, and air
temperature are used by the fuzzy logic switch to calculate the percentage of valve opening. Scheduling
irrigation at a low-tariff time is another benefit of the (Availability-Based Tariff) ABT-based tariff system.
According to the findings, the recommended approach saves 50% on water usage when compared to earlier
research. Nevertheless, the recommended method is costly to implement for the first time.

An intelligent irrigation system that allows farmers to irrigate their crops was introduced [48] has the Global
System for Mobile Communication (GSM) in support. Signals of acknowledgment about the system's
operations, including soil moisture content, ambient temperature, and motor status with respect to mains or
solar energy, are provided. By determining input variables such soil moisture, temperature, and humidity, the
fuzzy logic regulator produces the motor state outputs. When rain is predicted, the system also turns off the
engine to save electricity. The proposed system was compared to drip irrigation and hand immersion. The
results of the comparison demonstrate that the recommended intelligent irrigation system uses less electricity
and water. Using a low-cost WSN, proposed an intelligent fuzzy-based irrigation scheduling technique [49].
The crop water stress index and soil moisture were taken into account in the recommended irrigation
scheduling technique. The system is based on two sensor complexes, one of which consists of an Arduino
Uno, soil moisture sensors, infrared temperature sensors, humidity sensors, temperature sensors, and light
sensors. The other sensor complex is based on wireless transmission of sensor data. The Arduino DUE,
pump drive unit, pump, and thermometer are all part of the second component, the switch unit. The
experimental findings demonstrated the accuracy and efficiency of the recommended irrigation scheduling
system with regard to energy and water consumption. Water use dropped by 59.61%, power use dropped by
67.36%, while agricultural production rose by 22.59%. Despite its potential, CWSI's practical application is
constrained by a number of problems.
This generated a low-cost, IoT-based smart network irrigation system based on zoning to cut down on
electricity and water use [50]. A sensor node comprising an Arduino nano micro-regulator, batteries, a soil
moisture sensor, a humidity sensor, a temperature sensor, a valve, and a data transceiver unit is installed in
each of the network's four areas. The data gathered by the network is sent to a Raspberry Pi server using
(Radio Frequency) RF connections. After processing this data, a Fuzzy Logic Regulator decides whether to
use irrigation. In order to kind it easier to monitor and regulate irrigation from any location at any time, a
Human Man Interface (HMI) has been developed under the Node-RED server. According to the findings, the
recommended solution reduced energy use by 65.25% and water usage by 26.45%. It should be mentioned,
nonetheless, that giving a precise improvement % is challenging because it must be assessed from a number
of angles. A Fuzzy Logic Regulator design was recommended in a learning [51] in order to improve the
watering procedure for rose plants. Two sensors are included in the system to measure temperature and air
humidity; the main switch variables are temperature and relative humidity.

In a home greenhouse with a collection of rose plants, the Fuzzy Logic Regulator and membership functions
were generated via the Mamdani technique and a programmable gate array (FPGA). The findings
demonstrated that, in comparison to conventional manual irrigation, water use was decreased to 0.3 Liters
per week or up to 10.5 Liters year. However, because only one plant species and particular variations were
employed, the recommended design is an example that could not be generalized. An inventive fuzzy logic
irrigation switch system was generated to automatically regulate water pumps in farms and greenhouses [52].
It is serially connected to a laptop and contains an Arduino, a soil moisture sensor, a DC pump, solar panels,
and sensors for air temperature and humidity. The Simulink model uses the data from these sensors and the
solar radiation measured by the solar panel's characteristics to regulate the water pump's speed and turn it on
and off. The findings demonstrated that the system decreased energy use, expenses, and water usage.
However, for a number of plants or soils, the irrigation procedure is not automated.

3.3 Adaptive Neuro-Fuzzy Inference Systems

As demonstrated by several recent learning and developments in Adaptive Neuro-Fuzzy Inference Systems
based research, the application of (Adaptive Neuro-Fuzzy Inference Systems) ANFIS in irrigation systems
provides a hybrid approach that combines the benefits of neural networks and fuzzy logic, resulting in
improved water management, higher crop yields, and sustainable agricultural practices. To decide whether to
speed up or slow down the central pivot to the crucial decision-making for precise watering, developed a
fuzzy inference system that takes into account the geographical variability of the field and uses sparse or ill-
defined information on the crop's pheno-phase from satellite photos [53]. The scheme complies with the
variable rate irrigation (VR) need. As soon as the speed changes by management zone, so does the amount of
water supplied. The pivot operation's potential effectiveness was demonstrated via experiments. However,
the volume of the water layer that will be applied is not taken into account by the rotation speed switch.
Where plant development varies, so too will the need for water.
The ANFIS-PEGASIS-based irrigation system at a WSN was developed using the IoT and consists of
various sensors for tracking environmental factors, such as a soil moisture sensor, a temperature and
humidity sensor, and a light intensity sensor [54].

The fuzzy inference system (FIS) method is used to select the optimal cluster head (CH). Data from
irrigation systems is gathered using the Sensor Information System (PEGASIS) power-efficient aggregation
mechanism, and the irrigation system uses an ANFIS-based decision-making technique. In terms of energy
consumption, packet delivery ratio, system life, throughput, and reduced water waste, the results showed the
benefits of the proposed method. However, as it has just performed simulations, it has not been used in real-
world systems with sensor parameters. An adaptive prediction technique was used to anticipate sprinkler
irrigation's droplet infiltration efficacy [55]. A fluid intensifier pump, charging regulator, solar cell panel,
storage battery, soil moisture sensors, irrigation pipe network, pressure valve, inverter, circuit regulator,
irrigation regulator, strainer, check valve, and main valve were among the many parts of the irrigation
system, which was implemented using an Adaptive Neuro-Fuzzy Inference Systems model. The results of
the learning show that optimal and stable effectiveness prediction quality may be achieved by maintaining a
jetting pressure of 255.3 kPa, an impinging angle of 42.6, a water flow rate of 0.68 kg/min, and a continuous
irrigation time of 32.5 min.

3.4 Deep Learning and Machine Learning

According to a number of recent research that have made use of deep learning techniques, integrating deep
learning into irrigation systems kinds it possible to extract intricate patterns from massive amounts of data,
enabling precise prediction and water allocation decision-making. A smart irrigation system utilizing deep
learning for precision agriculture (DLiSA) and the IoT was proposed [56]. The system is comprised of a data
router with Internet access, a rain gauge sensor, a soil moisture sensor, and a sensor to detect air temperature
and humidity. DLiSA uses a long-term memory network to forecast the volumetric soil moisture content,
irrigation schedule, and water distribution across a specific area for the following day. By modifying the
irrigation scheduling mechanism, the proposed DLiSA was calibrated and tested at three locations over the
course of a year and a half. According to the results, the recommended method can save up to 44.28% of
water, which is a fairly considerable amount. Nevertheless, there is currently no predictive irrigation strategy
that can use rainfall depths to predict rainfall and optimize water availability.

An intelligent system based on LSTM was developed [57] to deliver irrigation data using predictive
temperature, humidity, and soil moisture analysis. Additionally, this system detects whether a physical
sensor is broken or sending inaccurate data as a result of outside influences on the system. A Smart Irrigation
System (SIS) with physical sensors that send data on temperature, humidity, and soil moisture is presently
being tested with the recommended solution. A neural sensor is used in place of the physical sensors, and the
findings show that the recommended neural sensor can accurately forecast key SIS system values, assisting
with irrigation decisions and averting system failures. However, the need for sizable datasets for training is a
major drawback of the deep learning-based neural sensors generated in this learning. Furthermore, farmers
have limited access to datasets.

It was generated a smart system that automates irrigation in agricultural using WSN [58]. An Arduino Mega
2560, a breadboard, an ESP8266, a water pump, a relay, a tank, multiple cameras, a picture sensor, a
raindrop sensor, an ultrasonic sensor, a soil moisture sensor, a temperature and humidity sensor, and a light
sensor are all part of the system. The goal of the recommended system is to train computers to recognize and
comprehend data in a variety of mediums. The Internet of Multimedia Things and Digital Image Processing
(DIP) are used by the system to evaluate photos and decide when and where to apply irrigation. There were
two separate phases to the experiments. To find the pertinent features for analysis, a feature selection
procedure was first carried out. Out of the original set of eight features, the best three were chosen using the
CHI square feature selection method. Different classifiers were used to assess their classification
performance in the second phase. This involved the use of random forests, support vector machines, and
artificial neural networks. To solve the categorization challenge, a (Convolutional Neural Network) CNN
was also used. It was noteworthy that the Adaptive Neuro-Fuzzy Inference Systems outperformed the other
algorithms used in the learning, demonstrating how well it solved the classification problem. The results
show that the recommended approach reduces labour costs and water use. But the recommended model takes
a very long time. In order to facilitate farming in remote regions, [59] generated the Smart Irrigation System
for Precision Agriculture and Farming (SIS-PAF), a smart irrigation system that kinds use of the Internet of
Things and wireless sensor networks. The goal was to show off the precision and intelligence of the system's
components, which facilitate water management decision-making. An Arduino Uno, a humidity sensor, a
temperature sensor, a soil feed sensor, an ultrasonic sensor, a light-dependent resistor sensor, a transmitter,
an LCD, a relay, and a DC pump are all part of the recommended system.

The automated system works in two phases. In the first, the ML algorithm is used to analyse pre-loaded
parameters on the server and kind judgments about the water supply. Applications for smartphones and the
internet can also be used to manage the water pump. Although the recommended methodology has
demonstrated improved agricultural and water management performance in experimental settings, its
efficacy necessitates real-time field tracking. The “AREThOU5A” smart irrigation system was introduced
[60]. Its kinds effective use of water in a variety of agricultural contexts by utilizing cutting-edge
technology, such as the Internet of Things and machine learning algorithms. The proposed approach
integrates field data from wireless sensor networks using temperature and soil moisture sensors with satellite
data from the International Weather Forecast Services. The collected data is sent online to the user interface
subsystem, which utilizes it to kind irrigation decisions. The recommended approach to irrigated water
management in agriculture produced positive results. However, it needs to install a rectenna module in
several IoT nodes within an agricultural area in order to evaluate its efficacy.

3.5 Other Algorithm

Numerous recent learning and developments in this field demonstrate that applying different algorithms,
such as threshold-based methods, Kalman filtering, PSO, and more, in irrigation systems offers a variety of
approaches for effective water management, crop yield optimization, and sustainable agricultural practices.
Using the threshold value method, an IoT-based irrigation switch system that is lightweight, inexpensive,
and energy-efficient was developed. Utilizing a moisture sensor, a soil temperature sensor, and a moisture
and air temperature sensor to measure soil irrigation parameters. Additionally, cloud-based data tracking and
storage are free and open base, with the ESP-12F8266 serving as the main micro-regulator for irrigation
system tracking and administration. The solar energy is used to charge a 12-volt lithium-ion battery. The
findings demonstrate that, in comparison to conventional irrigation techniques, the recommended threshold
value algorithm increases energy efficiency while lowering water loss by as much as 65%. However, this
method was only applied during one growing season every year and was not applied in huge areas.

Using WSN, an Android app, and a long-range (LoRa)-based platform, a Decision Support System was
generated to automate environmental conditions in order to minimize water loss and yield the best crops
[40]. The key components of the proposed concept are a controlled fertilizer unit, a smart irrigation system,
and a smart sensor unit. A temperature sensor, a soil moisture sensor, a humidity sensor, a soil conductivity
sensor, a nutrient, phosphorous, potassium (NPK) sensor, and a pH sensor are all included in the smart
sensor module. Serial peripheral interface SPI-based communication (LoRa) over the Internet allows the data
to be sent to the cloud. Real-time smart device decision-making is now possible with precise field data. The
findings demonstrated that by increasing productivity and decreasing agricultural water waste, the system
contributed to the achievement of long-term economic objectives. However, the prototype could not extract
characteristics from encoder sensors and is only suitable in specific places with a limited range.

Using WSNs, the Efficient Scalable Data Collection Scheme (ESDCS) to calculate the amount of water a
crop will need for fertilization [61]. A data collection drone, a micro-regulator, storage, I/O interfaces,
communication modules (Zigbee, Wi-Fi, GSM), soil moisture sensors, air temperature sensors, air humidity
sensors, wind speed and sunlight sensors, and water pumps are some of the components that kind up the
smart irrigation system with fertilization. The results of the learning showed that the recommended method
only uses 25.09% of the water compared to the current irrigation system. system limitations on excessive
fertilizer use brought on by incorrect fertilizer location and application. An IoT-based smart irrigation system
was generated [39] in an effort to reduce irrigation-related labour, energy, and water consumption. In order
to collect data about agricultural fields and store it in the cloud for the purpose of determining irrigation
schedules, it is equipped with a number of sensors that detect wind speed, water, humidity, temperature, soil
moisture, and light. According to the findings, this approach might save up to 18.8% on labour expenses,
power, and water use. It is difficult to execute in a small agricultural region with a variety of crops.

An inventive hybrid approach to controlling irrigation system pump motors was introduced [62]. This
method's main goal is to reduce the amount of power needed to pump 1,000 cubic meters of fluid. Use an
Expert System, a computer software that can process vast volumes of high-quality data, to kind irrigation
decisions by simulating the decision-making process of a human expert. The hybrid solution, which has a
pumping array of five 160 kW pumps, was designed and constructed using MATLAB. According to the
findings, the recommended strategy is the most efficient way to switch irrigation systems while lowering
energy use. However, because the experimental station did not employ all five pumps during the field
measurements, the situation with all five pumps operating was not examined.

The Kalman filter-proportional integral derivative (KF-PID) regulator was shown to be useful for a
subsurface fiber capillary irrigation system [63]. Comparing their method to other irrigation techniques, a
significant reduction in water use was noted. An Internet of Things-based weather station, a water tank, a
pump, and an ultrasonic sensor to measure the water level in the tank are among the modules that kind up the
recommended method. Other modules include a soil moisture sensor, a water level sensor, a camera, a Node
MCU, and a Raspberry Pi for the sensor module. To kind irrigation decisions, the data gathered from these
modules is sent to the cloud. The findings showed that using the KF-PID regulator in the recommended
method increased production while saving 56.4% of water. However, the accumulation of salts in the
cultivation medium due to capillary water circulation via fibrous materials can raise the salinity of the soil.

4. Irrigation Systems using IoT

A network of interconnected devices that can gather and exchange data online is known as the IoT. IoT has
the potential to greatly boost crop productivity, cut down on water waste, and raise irrigation system
efficiency [64]. IoT can be applied to irrigation systems in the following ways. Soil Moisture Sensors: Real-
time soil moisture content tracking is possible with IoT-enabled soil moisture sensors [65,66]. This
minimizes water waste and lowers the possibility of overwatering, which can cause plant diseases and
stunted growth, by enabling farmers to apply water precisely when needed. Weather Stations: When
deciding when to irrigate crops, weather information is essential. IoT-enabled weather stations are able to
deliver precise, current data on temperature, humidity, wind speed, and precipitation. Farmers can use this
information to determine how much and when to irrigate their crops [67]. Irrigation systems that are
automated can save labour expenses and time thanks to the Internet of Things [68]. as certain criteria are
satisfied, like as soil moisture levels hit a particular threshold, an automated system can be set to turn on and
off at predetermined intervals. Remote Tracking: A computer or smartphone can be used to remotely
monitor and switch IoT-enabled irrigation systems [69]. Even when they are not on the farm, this enables
farmers to keep an eye on their crops and modify the irrigation system as necessary [70].

Predictive analytics: This technique forecasts agricultural water needments by using data gathered from
weather stations and Internet of Things sensors. This can assist farmers with water conservation and
irrigation schedule scheduling [66, 71].

5.Problems and constraints

The difficulties and limitations of applying WSN, AI, and IoT to irrigation applications will be enclosed in
this section.
5.1 Problems and limitations with WSN in irrigation.

Crop yields and water use efficiency could be greatly increased by integrating WSN into intelligent irrigation
systems [24, 72]. But putting such systems into place needs addressing a number of obstacles and constraints
[73,74]. These are a few of them. One of the most important elements influencing the WSN-based irrigation
system's performance is sensor deployment. Accurate data collection and interpretation depend on sensors
being positioned and calibrated correctly. Energy constraints include the need for a power base for wireless
sensors and the short lifespan of batteries. Limited access to a reliable power supply might be problematic in
agricultural environments.
Communication Difficulties- Obstacles like trees, hills, and other environmental elements can kind
communication difficult in agricultural settings. The system's performance may suffer as a result of
communication lags or data loss.

5.1.1 Accuracy and Maintenance of Sensors:

These tasks might take a lot of time and need certain expertise. Accurate data collection needs constant
sensor calibration, which can be costly and challenging to accomplish in large-scale systems.
5.1.2 Data processing and analysis:

Gathering information from several sensors can provide a large volume of data that needs immediate
processing and analysis. Implementing robust AI algorithms and computing infrastructure in distant
agricultural settings can be costly and difficult.
5.1.3 System Complexity:

In rural agricultural areas, it may be challenging to locate the expertise needed to implement a WSN-based
irrigation system because it needs knowledge of both fields. Additionally, the system must be easy for
farmers to use and maintain.

5.1.4 Cost:

Setting up a WSN-based irrigation system can be costly, particularly for small-scale farmers. Adoption may
be seriously hampered by the price of sensors, computer power, and communication infrastructure.

5.1.5 Compatibility with current irrigation infrastructure:

WSN-based systems frequently need to be integrated with current irrigation infrastructure. Because of the
various protocols and technologies employed in the systems, this can be difficult.

5.2 Limitations and difficulties using AI in irrigation

AI has the ability to increase irrigation systems' efficacy and efficiency [75]. To successfully apply AI in
irrigation, a number of obstacles and constraints must be overcome [76, 77]. These are a few of them.

5.2.1 Data availability:

In order for AI algorithms to learn and produce precise predictions, they need a lot of data. The accuracy of
the forecasts may be impacted by the lack of or unreliability of data on crop growth, weather patterns, and
soil moisture in many areas.
5.2.2 Reliability of sensors:

Sensors gather information on environmental variables such as soil moisture. However, temperature,
humidity, and electromagnetic interference can all have an impact on a sensor's accuracy, and installing and
maintaining a sensor can be costly.
5.2.3 Power supply:

A lot of irrigation systems are situated in isolated locations with little or no electricity. For AI-powered
irrigation systems to function properly, a steady and dependable power base is necessary.

5.2.4 Cost:

Installing an AI-powered irrigation system can be costly, and small-scale farmers may find it difficult to
justify the initial outlay.
5.2.5 Limited technical expertise:

The adoption of AI-powered irrigation systems may be limited if farmers lack the technical know-how
needed to function and maintain them.
5.2.6 Unexpected challenges:

The accuracy and efficacy of AI systems may be impacted by unanticipated occurrences like pests or
unusual weather patterns.
5.2.7 Concerns about privacy and security:

AI-powered irrigation systems may gather sensitive data, and there are issues with how this data is handled,
shared, and preserved. Cyberattacks are another possibility that could jeopardize the security of the system.

For AI to be successfully implemented in irrigation systems, several obstacles and limitations must be
addressed.

5.3 Limitations and difficulties with IoT in irrigation

Using IoT in irrigation systems comes with a number of limitations and difficulties [78,79]. A few of them
are
5.3.1 Data Security:

Due to their internet connectivity, IoT devices are susceptible to cyberattacks, which may jeopardize the
security of the information gathered. For farmers who depend on IoT devices to switch irrigation, this is a
serious concern [80].

5.3.2 High Initial Cost:

Some farmers may be discouraged from implementing IoT technology due to the potentially high initial cost
of installing these devices. It is important to remember, nevertheless, that the long-term advantages of IoT in
irrigation may exceed the initial expense [81].

5.3.3 Technical Complexity:

IoT device setup and maintenance can be technically challenging, requiring specific expertise and abilities.
Farmers may find this difficult because they lack the necessary technological know-how.

5.3.4 Poor Connectivity:

It can be difficult to use IoT devices efficiently in some rural regions due to poor or inconsistent internet
connectivity. Data Overload - It might be challenging to comprehend and utilize the vast amount of data
produced by IoT devices. To extract valuable insights from the data, sophisticated analytics technologies
must be used.
5.3.5 Power Supply:

In order for IoT devices to function well, they need a constant power base, which might be difficult to find in
places with a scarce or unstable power supply.

6. Maturity assessment

In order to support the sustainable future of irrigated agriculture, this learning attempts to present a thorough
review and analysis of the current state of knowledge surrounding the performance evaluation of intelligent
irrigation systems. The ideas, methods, and approaches used to evaluate the efficacy of intelligent irrigation
projects are the main topics of the essay. The development of concepts for assessing the efficacy of irrigation
and the several models employed for this goal are discussed. The effectiveness of intelligent irrigation
systems has been measured and analysed using a variety of methods, including FL, NN, ML, ES, and
ANFIS, all of which are enclosed in detail. However, there isn't a single, cohesive way to compare the
efficacy of various intelligent irrigation systems, even though the literature offers a wide range of criteria for
defining performance evaluation. Therefore, choosing the right assessment framework and methodology
needs careful consideration of variables such irrigation systems, soil types, plant species, and climate.
7. Conclusion

The necessity of having an efficient water management system is highlighted by the fact that Iraq is one of
the nations experiencing acute water shortages. One of the most urgent issues with water waste is
agriculture, which uses a lot of water. Implementing water management technology to guarantee a sufficient
supply of water for agricultural use has been discussed in response to climate change. Many learning has
concentrated on finding solutions to the problem of irrigation water waste. The purpose of this learning is to
shed light on IoT irrigation systems for the farming industry. The most widely used wireless technologies
and nodes for implementing IoT systems and WSNs in agricultural irrigation, as well as the most prevalent
irrigation water quality, soil, and climate parameters, are listed here. Furthermore, we have looked at the
most widely used AI algorithms in irrigation management scheduling throughout the previous four years.
The ultimate objective is to generate an intelligent, effective irrigation system that uses less energy and
water.

Reference

[1] Y. Oladosu, M. Y. Rafii, F. Arolu, S. C. Chukwu, M. A. Salisu, I. K. Fagbohun, T. K. Muftaudeen, S. Swaray, and B. S. Haliru,
"Superabsorbent polymer hydrogels for sustainable agriculture: A review," Horticulturae, vol. 8, p. 605, 2022.

[2] H. Afzaal, A. A. Farooque, F. Abbas, B. Acharya, and T. Esau, "Precision Irrigation Strategies for Sustainable Water Budgeting of Potato
Crop in Prince Edward Island," Sustainability, vol. 12, 2020.
[3] R. Pereira, S. Lopes, A. Caldeira, and V. Fonte, "Optimized Planning of Different Crops in a Field Using Optimal Control in Portugal,"
Sustainability, vol. 10, 2018.

[4] Z. Gu, Z. Qi, R. Burghate, S. Yuan, X. Jiao, and J. Xu, "Irrigation Scheduling Approaches and Applications: A Review," Journal of Irrigation
and Drainage Engineering, vol. 146, 2020.

[5] K. H. Anabi, R. Nordin, and N. F. Abdullah, "Database-Assisted Television White Space Technology: Challenges, Trends, and Future
Research Directions," IEEE Access, vol. 4, pp. 8162-8183, 2016.
[6] G. Cáceres, P. Millán, M. Pereira, and D. Lozano, "Smart Farm Irrigation: Model Predictive Control for Economic Optimal Irrigation in
Agriculture," Agronomy, vol. 11, 2021.

[7] N. Islam, M. M. Rashid, F. Pasandideh, B. Ray, S. Moore, and R. Kadel, "A review of applications and communication technologies for
internet of things (Iot) and unmanned aerial vehicle (uav) based sustainable smart farming," Sustainability, vol. 13, p. 1821, 2021.

[8] I. Fernández García, S. Lecina, M. C. Ruiz-Sánchez, J. Vera, W. Conejero, M. R. Conesa, A. Domínguez, J. J. Pardo, B. C. Léllis, and P.
Montesinos, "Trends and Challenges in Irrigation Scheduling in the Semi-Arid Area of Spain," Water, vol. 12, 2020.

[9] J. Zinkernagel, J. F. Maestre-Valero, S. Y. Seresti, and D. S. Intrigliolo, "New technologies and practical approaches to improve irrigation
management of open field vegetable crops," Agricultural Water Management, vol. 242, 2020.

[10] K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, "Machine Learning in Agriculture: A Review," Sensors (Basel), vol. 18,
Aug 14 2018.

[11] A. Goap, D. Sharma, A. K. Shukla, and C. Rama Krishna, "An IoT based smart irrigation management system using Machine learning and
open source technologies," Computers and Electronics in Agriculture, vol. 155, pp. 41-49, 2018.

[12] R. Koech and P. Langat, "Improving Irrigation Water Use Efficiency: A Review of Advances, Challenges and Opportunities in the
Australian Context," Water, vol. 10, 2018.

[13] H. Jaafar and S. A. Kharroubi, "Views, practices and knowledge of farmers regarding smart irrigation apps: A national cross-sectional
study in Lebanon," Agricultural Water Management, vol. 248, 2021.
[14] H. Jaafar and S. A. Kharroubi, "Views, practices and knowledge of farmers regarding smart irrigation apps: A national cross-sectional

study in Lebanon," Agricultural Water Management, vol. 248, p. 106759, 2021.

[15] A. Sharma, A. Jain, P. Gupta, and V. Chowdary, "Machine Learning Applications for Precision Agriculture: A Comprehensive Review,"
IEEE Access, vol. 9, pp. 4843-4873, 2021.

[16] M. A. Chougule and A. S. Mashalkar, "A comprehensive review of agriculture irrigation using artificial intelligence for crop production,"
Computational Intelligence in Manufacturing, pp. 187-200, 2022.

[17] V. Kakani, V. H. Nguyen, B. P. Kumar, H. Kim, and V. R. Pasupuleti, "A critical review on computer vision and artificial intelligence in food
industry," Journal of Agriculture and Food Research, vol. 2, p. 100033, 2020.

[18] T. Talaviya, D. Shah, N. Patel, H. Yagnik, and M. Shah, "Implementation of artificial intelligence in agriculture for optimisation of
irrigation and application of pesticides and herbicides," Artificial Intelligence in Agriculture, vol. 4, pp. 58-73, 2020.

[19] G. Singh, A. Singh, and G. Kaur, "Role of artificial intelligence and the internet of things in agriculture," in Artificial Intelligence to Solve
Pervasive Internet of Things Issues, ed: Elsevier, 2021, pp. 317-330.

[20] L. Ramli, Z. Mohamed, A. M. Abdullahi, H. I. Jaafar, and I. M. Lazim, "Control strategies for crane systems: A comprehensive review,"
Mechanical Systems and Signal Processing, vol. 95, pp. 1-23, 2017.

[21] J. Xie, Y. Chen, P. Gao, D. Sun, X. Xue, D. Yin, Y. Han, and W. Wang, "Smart fuzzy irrigation system for litchi orchards," Computers and
 Electronics in Agriculture, vol. 201, p. 107287, 2022.

[22] E. A. Abioye, M. S. Z. Abidin, M. S. A. Mahmud, S. Buyamin, M. H. I. Ishak, M. K. I. A. Rahman, A. O. Otuoze, P. Onotu, and M. S. A.
Ramli, "A review on monitoring and advanced control strategies for precision irrigation," Computers and Electronics in Agriculture, vol.
173, 2020.

[23] S. W. Tsang and C. Y. Jim, "Applying artificial intelligence modeling to optimize green roof irrigation," Energy and Buildings, vol. 127, pp.
360-369, 2016.

[24] E. Bwambale, F. K. Abagale, and G. K. Anornu, "Smart irrigation monitoring and control strategies for improving water use efficiency in
precision agriculture: A review," Agricultural Water Management, vol. 260, p. 107324, 2022.

[25] M. Pathan, N. Patel, H. Yagnik, and M. Shah, "Artificial cognition for applications in smart agriculture: A comprehensive review,"
Artificial Intelligence in Agriculture, vol. 4, pp. 81-95, 2020.

[26] A. R. Fersht, "AlphaFold–A personal perspective on the impact of machine learning," Journal of molecular biology, vol. 433, p. 167088,
2021.

[27] Y. Mekonnen, S. Namuduri, L. Burton, A. Sarwat, and S. Bhansali, "Review—Machine Learning Techniques in Wireless Sensor Network
Based Precision Agriculture," Journal of The Electrochemical Society, vol. 167, 2019.

[28] E. A. Abioye, O. Hensel, T. J. Esau, O. Elijah, M. S. Z. Abidin, A. S. Ayobami, O. Yerima, and A. Nasirahmadi, "Precision Irrigation
Management Using Machine Learning and Digital Farming Solutions," AgriEngineering, vol. 4, pp. 70-103, 2022.
[29] S. Sayari, A. Mahdavi-Meymand, and M. Zounemat-Kermani, "Irrigation water infiltration modeling using machine learning,"
Computers and Electronics in Agriculture, vol. 180, p. 105921, 2021.
[30] A.-F. Jimenez, B. V. Ortiz, L. Bondesan, G. Morata, and D. Damianidis, "Long Short-Term Memory Neural Network for irrigation
management: a case study from Southern Alabama, USA," Precision Agriculture, vol. 22, pp. 475-492, 2020.

[31] R. Kanmani, S. Muthulakshmi, K. S. Subitcha, M. Sriranjani, R. Radhapoorani, and N. Suagnya, "Modern Irrigation System using
Convolutional Neural Network," presented at the 2021 7th International Conference on Advanced Computing and Communication
Systems (ICACCS), 2021.

[32] D. Wang, D. Tan, and L. Liu, "Particle swarm optimization algorithm: an overview," Soft Computing, vol. 22, pp. 387-408, 2017.

[33] M. Lezoche, J. E. Hernandez, M. d. M. E. A. Díaz, H. Panetto, and J. Kacprzyk, "Agri-food 4.0: A survey of the supply chains and
technologies for the future agriculture," Computers in industry, vol. 117, p. 103187, 2020.

[34] E. Pazouki, "A practical surface irrigation design based on fuzzy logic and meta-heuristic algorithms," Agricultural Water Management,
vol. 256, p. 107069, 2021.

[35] C. Cao, M. Xu, P. Kamsing, S. Boonprong, P. Yomwan, A. Saokarn, C. Cao, M. Xu, P. Kamsing, and S. Boonprong, "Application of
Surveillance of Communicable Disease Risk Using Expert Systems," Environmental Remote Sensing in Flooding Areas: A Case Study of
Ayutthaya, Thailand, pp. 135-143, 2021.

[36] H. Tian, T. Wang, Y. Liu, X. Qiao, and Y. Li, "Computer vision technology in agricultural automation—A review," Information Processing
in Agriculture, vol. 7, pp. 1-19, 2020.

[37] X. J. Tan, W. L. Cheor, K. S. Yeo, and W. Z. Leow, "Expert systems in oil palm precision agriculture: A decade systematic review," Journal
of King Saud University - Computer and Information Sciences, vol. 34, pp. 1569-1594, 2022.
[38] S. Borah, R. Kumar, and S. Mukherjee, "Low-cost IoT framework for irrigation monitoring and control," International Journal of
Intelligent Unmanned Systems, vol. 9, pp. 63-79, 2020.
[39] M. Mannan J, K. S. S, D. M, and P. T, "Smart scheduling on cloud for IoT-based sprinkler irrigation," International Journal of Pervasive
Computing and Communications, vol. 17, pp. 3-19, 2020.

[40] J. Arshad, M. Aziz, A. A. Al-Huqail, M. H. u. Zaman, M. Husnain, A. U. Rehman, and M. Shafiq, "Implementation of a LoRaWAN Based
Smart Agriculture Decision Support System for Optimum Crop Yield," Sustainability, vol. 14, 2022.

[41] S. Maroufpoor, J. Shiri, and E. Maroufpoor, "Modeling the sprinkler water distribution uniformity by data-driven methods based on
effective variables," Agricultural Water Management, vol. 215, pp. 63-73, 2019.

[42] N. K. Nawandar and V. R. Satpute, "IoT based low cost and intelligent module for smart irrigation system," Computers and Electronics
in Agriculture, vol. 162, pp. 979-990, 2019.

[43] G. Kamyshova, A. Osipov, S. Gataullin, S. Korchagin, S. Ignar, T. Gataullin, N. Terekhova, and S. Suvorov, "Artificial Neural Networks and
Computer Vision’s-Based Phytoindication Systems for Variable Rate Irrigation Improving," IEEE Access, vol. 10, pp. 8577-8589, 2022.
[44] R. Veerachamy and R. Ramar, "Agricultural Irrigation Recommendation and Alert (AIRA) system using optimization and machine
learning in Hadoop for sustainable agriculture," Environ Sci Pollut Res Int, vol. 29, pp. 19955-19974, Mar 2022.

[45] M. Li, R. Sui, Y. Meng, and H. Yan, "A real-time fuzzy decision support system for alfalfa irrigation," Computers and Electronics in
Agriculture, vol. 163, 2019.

[46] M. S. Munir, I. S. Bajwa, and S. M. Cheema, "An intelligent and secure smart watering system using fuzzy logic and blockchain,"
Computers & Electrical Engineering, vol. 77, pp. 109-119, 2019.

[47] S. Jaiswal and M. S. Ballal, "Fuzzy inference based irrigation controller for agricultural demand side management," Computers and
Electronics in Agriculture, vol. 175, 2020.
[48] R. S. Krishnan, E. G. Julie, Y. H. Robinson, S. Raja, R. Kumar, P. H. Thong, and L. H. Son, "Fuzzy Logic based Smart Irrigation System using
Internet of Things," Journal of Cleaner Production, vol. 252, 2020.

[49] C. Jamroen, P. Komkum, C. Fongkerd, and W. Krongpha, "An Intelligent Irrigation Scheduling System Using Low-Cost Wireless Sensor
Network Toward Sustainable and Precision Agriculture," IEEE Access, vol. 8, pp. 172756-172769, 2020.

[50] H. Benyezza, M. Bouhedda, and S. Rebouh, "Zoning irrigation smart system based on fuzzy control technology and IoT for water and
energy saving," Journal of Cleaner Production, vol. 302, 2021.

[51] R. Urbieta Parrazales, M. T. Zagaceta Álvarez, K. A. Aguilar Cruz, R. Palma Orozco, and J. L. Fernández Muñoz, "Implementation of a
Fuzzy Logic Controller for the Irrigation of Rose Cultivation in Mexico," Agriculture, vol. 11, 2021.

[52] A. K. Singh, T. Tariq, M. F. Ahmer, G. Sharma, P. N. Bokoro, and T. Shongwe, "Intelligent Control of Irrigation Systems Using Fuzzy Logic
Controller," Energies, vol. 15, 2022.

[53] W. R. Mendes, F. M. U. Araújo, R. Dutta, and D. M. Heeren, "Fuzzy control system for variable rate irrigation using remote sensing,"
Expert Systems with Applications, vol. 124, pp. 13-24, 2019.

[54] K. A. Kumar and K. Jayaraman, "Irrigation control system-data gathering in WSN using IOT," International Journal of Communication
Systems, 2020.

[55] Z. Liang, X. Liu, T. Zou, and J. Xiao, "Adaptive prediction of water droplet infiltration effectiveness of sprinkler irrigation using
regularized sparse autoencoder–adaptive network-based fuzzy inference system (rsae–anfis)," Water, vol. 13, p. 791, 2021.
[56] P. K. Kashyap, S. Kumar, A. Jaiswal, M. Prasad, and A. H. Gandomi, "Towards Precision Agriculture: IoT-Enabled Intelligent Irrigation
Systems Using Deep Learning Neural Network," IEEE Sensors Journal, vol. 21, pp. 17479-17491, 2021.

[57] M. Sami, S. Q. Khan, M. Khurram, M. U. Farooq, R. Anjum, S. Aziz, R. Qureshi, and F. Sadak, "A Deep Learning-Based Sensor Modeling
for Smart Irrigation System," Agronomy, vol. 12, 2022.

[58] S. AlZu’bi, B. Hawashin, M. Mujahed, Y. Jararweh, and B. B. Gupta, "An efficient employment of internet of multimedia things in smart
and future agriculture," Multimedia Tools and Applications, vol. 78, pp. 29581-29605, 2019.

[59] P. Sanjeevi, S. Prasanna, B. Siva Kumar, G. Gunasekaran, I. Alagiri, and R. Vijay Anand, "Precision agriculture and farming using Internet
of Things based on wireless sensor network," Transactions on Emerging Telecommunications Technologies, vol. 31, 2020.
[60] A. D. Boursianis, M. S. Papadopoulou, A. Gotsis, S. Wan, P. Sarigiannidis, S. Nikolaidis, and S. K. Goudos, "Smart Irrigation System for
Precision Agriculture—The AREThOU5A IoT Platform," IEEE Sensors Journal, vol. 21, pp. 17539-17547, 2021.

[61] K. Karunanithy and B. Velusamy, "Energy efficient cluster and travelling salesman problem based data collection using WSNs for
Intelligent water irrigation and fertigation," Measurement, vol. 161, 2020.

[62] F. Scarlatache, G. Grigoras, V.-A. Scarlatache, B.-C. Neagu, and O. Ivanov, "A Hybrid Methodology Based on Smart Management Energy
Consumption in Irrigation Systems," Electronics, vol. 10, 2021.

[63] E. A. Abioye, M. S. Z. Abidin, M. S. A. Mahmud, S. Buyamin, O. D. Ijike, A. O. Otuoze, A. A. Afis, and O. M. Olajide, "A data-driven Kalman
filter-PID controller for fibrous capillary irrigation," Smart Agricultural Technology, vol. 3, 2023.

[64] H. Azarmdel, A. Jahanbakhshi, S. S. Mohtasebi, and A. R. Muñoz, "Evaluation of image processing technique as an expert system in
mulberry fruit grading based on ripeness level using artificial neural networks (ANNs) and support vector machine (SVM)," Postharvest
Biology and Technology, vol. 166, p. 111201, 2020.
[65] A. Kumar, V. Singh, S. Kumar, S. P. Jaiswal, and V. S. Bhadoria, "IoT enabled system to monitor and control greenhouse," Materials
Today: Proceedings, vol. 49, pp. 3137-3141, 2022.
[66] J. H. Yousif and K. Abdalgader, "Experimental and mathematical models for real-time monitoring and auto watering using IoT
architecture," Computers, vol. 11, p. 7, 2022.

[67] P. Shirsath, S. Vyas, P. Aggarwal, and K. N. Rao, "Designing weather index insurance of crops for the increased satisfaction of farmers,
industry and the government," Climate Risk Management, vol. 25, p. 100189, 2019.

[68] A. Shufian, M. R. Haider, and M. Hasibuzzaman, "Results of a simulation to propose an automated irrigation & monitoring system in
crop production using fast charging & solar charge controller," Cleaner Engineering and Technology, vol. 4, p. 100165, 2021.

[69] R. K. Jain, B. Gupta, M. Ansari, and P. P. Ray, "IOT enabled smart drip irrigation system using web/android applications," in 2020 11th
International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2020, pp. 1-6.

[70] R. M. Ramli and W. A. Jabbar, "Design and implementation of solar-powered with IoT-Enabled portable irrigation system," Internet of
Things and Cyber-Physical Systems, 2022.

[71] P. Majumdar, S. Mitra, and D. Bhattacharya, "IoT for promoting agriculture 4.0: a review from the perspective of weather monitoring,
yield prediction, security of WSN protocols, and hardware cost analysis," Journal of Biosystems Engineering, vol. 46, pp. 440-461, 2021.

[72] G. Oussama, A. Rami, F. Tarek, A. S. Alanazi, and M. Abid, "Fast and intelligent irrigation system based on WSN," Computational
Intelligence and Neuroscience, vol. 2022, 2022.

[73] V. Gowthami and G. Murugaboopathi “Safety Cubic Dimension Acoustic and Routing in Acoustic Sensor Network” Journal of Ambient
Intelligent and Humanized Computing– Vol No. 12, Issue No. 7, Page No. 7225 - 7234, ISSN 1868-5137,
http://doi.org/10.1007/s12652-020-02397-x
[74] Dr. Gowthami V and Dr. Krishna Prasad, “DSGARS: Alphanumeric Sign-based Secured Ananymous Routing in Wireless Sensor Network”.
Computer Research and Development, ISSN No.: 1000 – 1239, Vol. 24, Issue No.: 9, 2024.

[75] K. Obaideen, B. A. Yousef, M. N. AlMallahi, Y. C. Tan, M. Mahmoud, H. Jaber, and M. Ramadan, "An overview of smart irrigation
systems using IoT," Energy Nexus, p. 100124, 2022.

[76] A. Villa-Henriksen, G. T. Edwards, L. A. Pesonen, O. Green, and C. A. G. Sørensen, "Internet of Things in arable farming: Implementation,
applications, challenges and potential," Biosystems engineering, vol. 191, pp. 60-84, 2020.

[77] M. Javaid, A. Haleem, I. H. Khan, and R. Suman, "Understanding the potential applications of Artificial Intelligence in Agriculture
Sector," Advanced Agrochem, vol. 2, pp. 15-30, 2023.

[78] M. T. Linaza, J. Posada, J. Bund, P. Eisert, M. Quartulli, J. Döllner, A. Pagani, I. G. Olaizola, A. Barriguinha, and T. Moysiadis, "Data- driven
artificial intelligence applications for sustainable precision agriculture," Agronomy, vol. 11, p. 1227, 2021.
[79] S. A. Bhat and N.-F. Huang, "Big data and ai revolution in precision agriculture: Survey and challenges," IEEE Access, vol. 9, pp. 110209-
110222, 2021.

[80] W. Li, M. Awais, W. Ru, W. Shi, M. Ajmal, S. Uddin, and C. Liu, "Review of sensor network-based irrigation systems using IoT and
remote sensing," Advances in Meteorology, vol. 2020, pp. 1-14, 2020.

[81] K. Bhanu, H. Jasmine, and H. Mahadevaswamy, "Machine learning implementation in IoT based intelligent system for agriculture," in
International Conference for Emerging Technology (INCET), 2020, pp. 1-5.