2024 3rd IEEE International Conference on Artificial Intelligence for Internet of Things (AIIoT 2024)

IoT and Cloud based Automated Irrigation System

Mr. Anandha Jothi K G Mr. Vignesh T A Mr. Gokul Nittin A
Author Co-author Co-author
School of Electronics Engineering, School of Electronics Engineering, School of Electronics Engineering,
Vellore Institute of Technology, Vellore Institute of Technology, Vellore Institute of Technology,
2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT) | 979-8-3503-7212-0/24/$31.00 ©2024 IEEE | DOI: 10.1109/AIIoT58432.2024.10574611

Vellore, India Vellore, India Vellore, India

[email protected] [email protected] [email protected]

Mr. Vinoth M Ms. Janani Shruthi B Mr. Abhishek V

Co-author Co-author Co-Author
VIT School of Agricultural Innovations School of Electronics Engineering, School of Electronics Engineering,
and Advanced Learning, Vellore Institute of Technology, Vellore Institute of Technology,
Vellore Institute of Technology, Vellore, India Vellore, India
Vellore, India [email protected] [email protected]
[email protected]

Mr. Neeraj Srinivasan Dr K Govardhan*

Co-Author School of Electronics Engineering,
School of Electronics Engineering, Vellore Institute of Technology,
Vellore Institute of Technology, Vellore, India
Vellore, India [email protected]
[email protected]

Abstract— Agriculture is the most important sector in our economical hardware such as ESP32 and seamless software
country, employing more than 50% of our population and integration, the system ensures precise monitoring of crucial
always necessitating innovative solutions for resource utilization parameters like soil moisture, water level, and precipitation.
and enhanced productivity. In this novel agricultural project, By integrating cloud services, especially Adafruit IO, and a
we introduce a versatile and intelligent IoT-based irrigation
user-friendly mobile app developed on Flutter, farmers can
system. By integrating soil moisture sensors, water level
detectors, and weather prediction APIs, our system empowers remotely supervise and manage the irrigation process.
farmers with real-time insights and automated control over Moreover, the system utilizes real-time weather predictions
irrigation processes. A key aspect of our strategy is obtained through API requests to dynamically adjust
incorporating cloud services, where all data collected by the watering schedules, optimizing plant growth conditions.
sensors are sent and analyzed. With a user-friendly mobile app
built on Flutter, users can easily supervise and manage the Through the implementation of artificial intelligence
watering system from a distance. Additionally, by utilizing algorithms, the system customizes irrigation strategies based
weather predictions obtained through API requests, the system on specific crop requirements, thereby maximizing resource
automatically adjusts watering times, ensuring the best efficiency and promoting climate-resilient cropping
conditions for plant growth. One notable feature of our system practices. Moreover, our project incorporates proactive
is its ability to adjust to different types of crops. By employing measures to mitigate the impact of extreme weather events,
artificial intelligence algorithms, the system intelligently such as heavy rainfall, on agricultural landscapes. By
determines the specific water needs for each crop chosen by the integrating water level sensors and intelligent pump control
farmer. This personalized technique not only optimizes resource
usage but also boosts crop production.
mechanisms, our system can autonomously manage excess
water accumulation during periods of intense precipitation,
In summary, this project offers a practical solution for thereby preventing waterlogging and soil erosion.
automatic crop irrigation by considering real-time weather This research paper presents a comprehensive approach
forecasts. The proposed device improves irrigation performance towards automatic crop irrigation, emphasizing the
and promotes climate-resistant cropping by combining climate significance of real-time weather forecasting and intelligent
monitoring, weather forecasting, and automatic pumping. irrigation management in contemporary farming.

Keywords— Soil moisture sensors, Water level detectors, IoT, II. COMPONENTS USED
cloud services, API, Flutter, Weather prediction, and Artificial
intelligence. A. ESP-32 Microcontroller
ESP32-DevKitC V4 is a small-sized ESP32-based
I. INTRODUCTION development board produced by Espressif. It features a dual-
The adoption of advanced technologies in agriculture has core processor. Also, it has built-in Wi-Fi and Bluetooth and
revolutionised traditional farming methods, offering has a wide range of applications. Most of the I/O pins are
innovative solutions to enhance crop yield and mitigate broken out to the pin headers on both sides for easy
challenges posed by the environment. At the forefront of this interfacing. Developers can either connect peripherals with
jumper wires or mount ESP32-DevKitC V4 on a breadboard.
technological revolution lies the development and
implementation of IoT-based systems. With this research, we Here the ESP-32 acts as a mediator that collects the inputs
introduce a novel IoT-based irrigation system. Leveraging from the Sensors that are placed along with the crops,

979-8-3503-7212-0/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: VIT University. Downloaded on December 11,2024 at 10:07:35 UTC from IEEE Xplore. Restrictions apply.
 2024 3rd IEEE International Conference on Artificial Intelligence for Internet of Things (AIIoT 2024)
processes those inputs according to the pre-set commands, is a version 4.0 module for transmitting the sensor data from
simultaneously gathers the weather forecast details from the the Arduino Nano to the Esp32 module from where the sensor
web source, and controls the valves of pumps and motors and data are send to the Adafruit IO webserver. We use the HM-
other associated sensors according to the threshold value that 10 Bluetooth module which is a Bluetooth version 4.0 module
we set in-prior, according to the crop type selected by the that can transfer data between modules at the rate of up to
farmer through the mobile app. 25Mbps while consuming less power. It is used for
B. Resistive Soil Moisture Sensor transmitting the sensor data from the Arduino Nano to the
Esp32 module from where the sensor data are sent to the
The Resistive Soil moisture sensor determines the
moisture content in the soil by calculating the conductivity of Adafruit IO webserver.
the soil. The sensor measures the resistance between its III. LITERATURE REVIEW
probes, this resistance is affected by the conductivity of the
soil, which in turn is influenced by the amount of moisture With the ever-growing population, the demand for basic
present. Resistance changes inversely to the moisture content amenities such as food increases, leading to a higher
in the soil. Additionally, it has a voltage regulator which helps requirement for water in agricultural activities.
us to manually adjust the threshold value of the sensor Consequently, addressing water scarcity in agriculture has
according to our need. The data acquired helps us to water the become a popular topic for research, focusing on adopting
plants dynamically according to the current conditions in the holistic approaches that consider population growth,
field. sustainable water management practices, and technological
innovations to enhance water efficiency in farming. Climate
C. Resistive Water Level Sensor discrepancies, such as changing rainfall patterns, increased
The Resistive water level sensor measures the resistance temperatures, and droughts, can also significantly impact
between its conductive strips. As the water level rises, the irrigation practices.
resistance between the strips which run along the length of Though traditional irrigation practices such as strip
the sensor, decreases. This allows us to determine the water irrigation, Moat (pulley system), Rahat (lever system), and
level in the crop field. The data acquired helps us to pump out chain pump are cheap, they are a time-consuming and labor-
the excess water during heavy rainfall and maintain the intensive process and involve a substantial amount of water
correct water level in the field. wastage [1,2]. Therefore, over the years it has been gradually
replaced by modern irrigation practices such as drip
irrigation, sprinkler system, etc., which mitigates the wastage
D. Relays by a considerable amount. However, these modern practices
Relays are electromagnetic switches that are controlled by could not bridge the gap in mitigating the potential risks of
trigger signals from a microcontroller or any other control over-irrigation, high power consumption and complexities of
system. It is used to connect different circuits and operate maintenance. This prompted the need for an optimal solution,
them depending on our use case. We use a 4-channel relay leading to automated irrigation.
which is generally used to control 4 different circuits SMART irrigation is an emerging field utilising data-
independently, and in our project, it is used to control and intensive approaches to enhance agricultural yields while
power the motors and pumps. It works on the principle of reducing environmental consequences. SMART irrigation
Electromagnetism where the switches are controlled by system consists of sensors for data acquisition, irrigation
changing the electromagnetic behavior of the electromagnet control, wireless communication, data processing and fault
present in the relay by applying electric current as trigger the detection using IoT [3]. IoT irrigation systems offer both 3-
signal from the microcontroller. layered and 5-layered architectural options. Typically, the
lower layer consists of sensor nodes and actuators, while the
middle layer involves a gateway facilitating data
D. GPS Module transmission. Finally, the third layer handles the data storage
GPS stands for Global Positioning System. A GPS module and analysis, commonly featuring cloud services, databases,
helps us determine the location of a particular area. The GPS or applications [1]. Its operations include gathering data from
module calculates its position by measuring the time it takes a variety of sensors, resulting in an improved comprehension
for signals from multiple satellites to reach it. By knowing of both the operational environment and activities. This leads
the exact position of each satellite and the time it took for its to more accurate and efficient decision making which
signals to arrive, the module can determine its position ultimately enables us to achieve our intended goals of
through a process called trilateration. In our project, we use optimizing resources and reducing manual labor [4,5].
the NEO-6M GPS module which helps us identify the The lower layer includes physical devices such as sensors
location of each sensor in different areas of the field. With and actuators. The data acquired from sensors reflects the
this data, we can map the entire field into different zones, thus real-time status of the plants and soil and is essential for an
watering it separately. efficient monitoring system that has a direct impact on the
development of plants. These are highly essential in
designing an effective irrigation control system to enhance
F. Bluetooth Module
the production of food with minimal water consumption [6].
Bluetooth modules are electronic components that enable Sensors that are widely used are soil moisture sensor, water
wireless communication between devices over short level sensor, soil pH sensor, water flow and soil temperature
distances. They utilize Bluetooth technology, which is a sensor. Among them, the most commonly used sensor is the
wireless communication standard for exchanging data over Soil moisture sensor, which is used to measure the moisture
short distances. We use the HM-10 Bluetooth module which content in the soil [7]. There are two types of Soil moisture

Authorized licensed use limited to: VIT University. Downloaded on December 11,2024 at 10:07:35 UTC from IEEE Xplore. Restrictions apply.
 2024 3rd IEEE International Conference on Artificial Intelligence for Internet of Things (AIIoT 2024)
sensor-based systems: One type is the suspended cycle information and to get valuable insights. Users can often take
irrigation system, which operates similarly to a timer actions based on the presented data, either manually or
controller. It includes predefined schedules for watering, their automatically, depending on the situation [7].
duration, and start and end times. It automatically stops the
next scheduled irrigation if the soil has enough moisture. The Artificial intelligence (AI) is presently the technology that
second type is the water-on-demand irrigation system, which holds the greatest potential for several fields, serving diverse
does not require any pre-programming. In this method, the objectives. In irrigation, AI applications focus on optimizing
user sets a threshold that triggers the irrigation process only resources like water, fertilizers, and energy, as well as
when the soil moisture falls below the necessary levels [1,8]. gathering crop-related data such as disease detection or
ensuring proper plant growth for various crops [7].
The other components of the lower layer are actuators.
The data from sensors is also fed into actuators like sound Embedded with sensors, smart objects facilitate
emitters that alarm the farmers and act as an inhibitory interaction with both the physical and digital realms, in
measure to prevent the entry of animals or intruders into the accordance with the principles of the Internet of Things (IoT).
farming lands [7,9]. Other actuators that are commonly used This paper presents a system proposal grounded in IoT,
are Artificial lighting systems that are utilized for generating leveraging real-time input data. The system in question
pertains to an intelligent agricultural irrigation solution that
artificial photoperiods to enhance productivity and fans that
modify the atmospheric conditions according to the relies on an Android smartphone to enable remote monitoring
requirements [7,10]. and control of irrigation drips via a wireless sensor network
(WSN). This project aims to process the data and deliver the
The middle layer consists of interfaces that enable them optimum solution for every use case using an artificial
to connect with other devices to transmit the monitored data intelligence-backed system for the backend of the
and response actions between the devices. The devices used application.
for transmission are of two types: devices that serve as nodes
that transmit small amounts of data at short distances (up to Implementing improvements in irrigation systems is
100 meters) and have low energy consumption and devices crucial for water-use efficiency and works as a contributor to
that can transmit large amounts of data over long distances (a Sustainable Development Goals (SDGs) under the United
few kilometers) and have high energy consumption. Another Nations, specifically Goal 6 and Target 6.4. This paper aims
classification method can be based on the communication to highlight the contribution of SMART irrigation using the
technology employed such as Ethernet or cable, Wi-Fi and Internet of Things (IoT) and sensory systems in relation to the
WAN technologies. Wi-Fi is the most commonly used SDGs [1]. This prototype aims at saving water, labor and time
communication technology due to its easier accessibility. and avoiding constant vigilance. It contributes to water
Low-cost IoT devices commonly support Wi-Fi, which, conservation by automatically providing water to the
despite its limited range for the average farm size, could still plants/gardens depending on their water requirements.
offer adequate wireless coverage for small farms through the IV. METHODS
deployment of multiple affordable devices. Other widely
spread wireless technologies are GSM (Global System for Our project aims to significantly enhance existing
Mobile Communication) which provides long-range farming practices more cost-effectively, ensuring that every
communication at the cost of a mobile plan of the service farmer, regardless of their economic status, can access and
provider and ZigBee which offers low energy consumption utilize the best available technology to improve productivity.
and has lower data rates than other technologies as it allows This will bolster the nation's capacity for self-sustainability
implementing networks with up to 65000 nodes. MQTT is in all climatic and economic conditions.
another popular technology that has lower power Through this project, we seek to elevate the quality of
consumption. It is efficient as it requires minimal resources farming practices, particularly irrigation, which often
and is reliable due to its ability to connect over networks with requires frequent intervention and labour-intensive tasks. By
lower bandwidths [7]. automating the process, we reduce the need for manual
The final layer serves the purpose of data storage and data intervention and labour costs, while optimising water usage.
analysis and provides services such as data management, This approach also fosters adaptability and configurability,
security and applications. Two main storage systems that are enabling us to extend automation to various other farming
used in these irrigation systems are traditional databases and practices.
Cloud databases [7]. Middleware is the software that The methodologies and techniques involved in the
facilitates communication and data management between IoT implementation of our project include the following key
devices and cloud services. It plays a crucial role in ensuring components.
efficient and seamless interaction between the distributed IoT 1. Hardware setup
devices and the centralized cloud infrastructure, enabling 2. Weather API
scalable and reliable IoT deployments [11]. In the cloud, the 3. Data Acquisition
data collected from sensors is stored and processed and the 4. Storing and Retrieval of Data from the Cloud
end-users view all the information by connecting to the cloud. 5. Mobile Application
The most preferred platform is Thingspeak, which is intuitive 6. Irrigation Algorithm
and provides both free and paid options for storing, analyzing 7. AI Algorithm
and displaying data on different devices.
A. Hardware Setup
To execute tasks such as device discovery, device control,
or data analysis, services may also be required. Applications In the proposed system as shown in figure 1, we utilize soil
facilitate user interaction with the system, allowing users to moisture sensors, water level sensors, Bluetooth modules,
visualize both real-time monitoring data and processed Arduino Nano, relays, GPS modules, and pumps to optimize

Authorized licensed use limited to: VIT University. Downloaded on December 11,2024 at 10:07:35 UTC from IEEE Xplore. Restrictions apply.
 2024 3rd IEEE International Conference on Artificial Intelligence for Internet of Things (AIIoT 2024)
the irrigation process. All these components are connected to not feasible in an agricultural environment. We receive the
an ESP-32 module, which acts as the heart and brain of our analogue data from the sensors which usually ranges from 0
system. The ESP-32 collects and sends data from the sensors to 1023.As the sensors’ output would be voltage variations
and the cloud database. ranging from 0 to 5 volt, the Analog to Digital Converter in
During the implementation of our system in the actual farm, the microcontroller represents the voltage variation in terms
we divide the farm area into different zones. Each zone has a of 10-bit range which is 0 to 1023. We receive the analogue
separate set of sensors accompanied by a low-power Arduino data from the sensors which usually ranges from 0 to 1023.As
Nano module, a Bluetooth module, and a GPS module. These the sensors’ output would be voltage variations ranging from
modules gather sensor data and location information and 0 to 5 volt, the Analog to Digital Converter represents the
transmit them via Bluetooth to the main ESP-32 module, voltage variation in terms of 10- bit range which is 0 to 1023.
which then sends the data to the cloud database for further These analogue values are mapped to the appropriate
processing as shown in figure 2. percentage values so that it will be easy to work with the
All sensor data processing is handled by the Arduino Nano values.
module, which is directly connected to the sensors. There is The data acquired through the weather API service includes
a local network of Arduino Nano boards, all connected to the precipitation, temperature, humidity, pressure and wind
main ESP-32 module through Bluetooth. speed which are embedded in the JSON file received from the
The Pump and Relay are connected to the main ESP-32 web source.
module which runs the irrigation algorithm, and waters the We identify sensors from each zone in the field through its
crops appropriately, according to the sensor data received latitude and longitude values that are sent to the ESP-32
from the Arduino nano through Bluetooth, we use a self- module through the GPS module and with this data we map
sustaining power supply which includes solar panels and the entire field into different zones and irrigate each zone
rechargeable batteries for the sensors, Arduino Nano module, separately.
Bluetooth modules, and GPS modules in each zone
separately. The main power supply is used for the motors,
pumps, and the ESP-32 module. Additionally, the ESP-32
module is backed up with a backup power supply in case of a
power outage.

Fig. 2. Flow of Data

D. Storing and Retrieval of Data from the Cloud

We use Adafruit IO as our cloud database for storing data
from the ESP-32 and retrieving data for the mobile
application. Sensor values from the ESP-32 and weather
details received from the API service provider are sent to the
Adafruit IO feed using the MQTT protocol. Additionally, we
update the pump status to allow viewing and controlling the
pump status from Adafruit IO.
The stored data is retrieved for our mobile application, which
serves as the interface for anyone using the system. All stored
Fig. 1. Prototype Model
data is displayed in the app via the MQTT protocol, and the
pump status can be updated directly from the app, enabling
B. Weather API
control of the pumps in the field. Figure 3 depicts the Adafruit
We acquire real-time weather data from Weather API which io dashboard, where all our sensor data is being stored.
is a free weather API service. It is an intermediary, enabling
software applications to access real-time, forecasted, and
historical weather information. Weather data is used to make
informed decisions about planting, harvesting, and irrigation.
Using HTTP protocol, we receive the weather data from the
API service provider, and it is received in the JSON format,
which is an open standard file format for data interchange
between web servers. It contains the weather details in key-
value pairs which can be decoded and used according to our
needs.
C. Data Acquisition
Changes in the environment are detected using various sensor
modules. Data from the sensors are sent to the ESP-32 Fig. 3. Adafruit io Dashboard
module through Bluetooth connectivity as conventional data
transmission between the sensors and the microcontroller is

Authorized licensed use limited to: VIT University. Downloaded on December 11,2024 at 10:07:35 UTC from IEEE Xplore. Restrictions apply.
 2024 3rd IEEE International Conference on Artificial Intelligence for Internet of Things (AIIoT 2024)
for each zone is individually controlled thus dynamically
E. Mobile Application
adjusting the irrigation of each zone according to the soil-
Our mobile application, developed using Google's Flutter moisture level of each zone, however, if there is a forecast of
framework, serves as the central hub for managing precipitation, irrigation is postponed to conserve water
agricultural irrigation processes. Leveraging Flutter's resources even when the soil-moisture is below the threshold
versatility, we've crafted an intuitive user interface that level. Users can manually activate the pump via the mobile
empowers farmers to efficiently oversee and control their application, with a temporary override of the moisture
irrigation systems from anywhere in the world. condition for the user-set timings. After this period, the
Through the application, users input crucial data such as override is deactivated, and the algorithm resumes normal
location details, farm area, and crop type. We've implemented operation based on sensor data and weather forecasts.
a sophisticated algorithm that dynamically adjusts irrigation
parameters based on crop-specific thresholds for soil G. AI Algorithm
moisture levels. This ensures optimal water usage and crop 1) Long Short-Term Memory (LSTM) Networks:
health. LSTM networks are particularly suitable for our project due
Upon completing the initial setup, users are greeted with a to their ability to capture long-term dependencies and patterns
comprehensive dashboard as shown in figure 4. Here, they in sequential data. In our context, LSTM is employed to
can access real-time updates on rainfall forecasts, soil analyze historical climate data (such as rainfall, temperature,
moisture levels, water levels in the crop field, and pump humidity) and field data (including soil moisture and crop
status as shown in the figure provided below. With just a growth). This enables the model to discern complex
single tap users can take immediate action to regulate pump relationships between various environmental factors and crop
operations directly from the app. water requirements over time. By training the LSTM network
In addition to the dashboard, our application offers detailed on data collected from sensors deployed in agricultural fields
insights into sensor and module statuses, along with finding and stored in a Google Firestore database, we can generate
exact locations using GPS coordinates sent from the GPS accurate predictions of future irrigation needs based on
module. Weather forecasts are prominently displayed on a evolving weather conditions and crop growth stages.
separate page, enabling users to make informed decisions 2) Gradient Boosting Technique:
regarding irrigation schedules. In our project, we adopt the gradient boosting technique to
Furthermore, users can easily access information on crop enhance the predictive power of our irrigation model. By
water requirements and monitor water consumption from iteratively combining multiple decision trees, gradient
their water source. This holistic approach not only optimizes boosting effectively learns from past errors and refines its
irrigation practices but also promotes sustainable water predictions over time. Specifically, we utilize ridge
management. regression to define the loss function and adjust the weights
In summary, our mobile application acts as a sophisticated of each layer in the model, thereby improving its performance
interface, providing farmers with a seamless experience for in predicting optimal irrigation amounts. The granularity of
managing irrigation processes and enhancing crop data provided by this technique allows us to pinpoint areas
productivity in an increasingly connected agricultural where the model's accuracy can be further enhanced, leading
landscape. to more precise irrigation recommendations tailored to
specific field conditions.
3) XGBoost (Extreme Gradient Boosting):
XGBoost serves as a critical component of our irrigation
model, offering several advantages that align with the
requirements of our project. By leveraging XGBoost, we
address challenges such as missing data and scalability for
large datasets, common in agricultural applications.
Moreover, the algorithm's ability to capture complex
interactions between climate and field variables allows for
more accurate predictions of irrigation requirements. This
ensures that our model can adapt to diverse environmental
conditions and provide reliable recommendations for
optimizing water usage and maximizing crop yield.
Fig. 4. Application Dashboard 4) Autoregressive Integrated Moving Average (ARIMA):
ARIMA analysis plays a pivotal role in our project by
F. Irrigation Algorithm providing insights into historical irrigation patterns and
The irrigation algorithm plays a crucial role in determining identifying trends and seasonal variations in crop water
when to water crops based on soil moisture levels and requirements. By analyzing past irrigation amounts, crop
anticipated precipitation. When soil moisture falls below a yields, and climate data, ARIMA enables us to establish
pre-set threshold that depends upon the crop type selected by baseline irrigation schedules and detect deviations caused by
the user through the mobile app, the pump is activated by the changing weather patterns. This information is invaluable for
ESP-32 to irrigate crops. However, there may be situations proactive irrigation management, allowing farmers to adjust
where some zones in the field do not need to be irrigated their practices in response to evolving environmental
where their soil-moisture level could be greater than the conditions and ensure optimal crop health and productivity.
threshold, in that case, the pump is switched on and the valve

Authorized licensed use limited to: VIT University. Downloaded on December 11,2024 at 10:07:35 UTC from IEEE Xplore. Restrictions apply.
 2024 3rd IEEE International Conference on Artificial Intelligence for Internet of Things (AIIoT 2024)
CONCLUSION [5] N. Tantalaki, S. Souravlas, and M. Roumeliotis, "Data-Driven
Decision Making in Precision Agriculture: The Rise of Big Data in
Through continuous innovation and technological Agricultural Systems," Journal of Agricultural & Food Information,
advancements, this system is versatile and adaptable to future vol. 20, no. 4, pp. 344–380, doi:
https://doi.org/10.1080/10496505.2019.1638264
changes. We can add other IOT devices to the hardware and
have this as an AIO in our farms. This project fosters
[6] B. Keswani, A. G. Mohapatra, A. Mohanty, A. Khanna, J. J. P. C.
efficiency over traditional methods of agriculture which is Rodrigues, D. Gupta, and V. H. C. de Albuquerque, "Adapting weather
prevalent in most parts of the world, especially in India. The conditions based IoT enabled smart irrigation technique in precision
research proposes an IoT-based irrigation system for agriculture mechanisms," Neural Computing and Applications, vol. 31,
sustainable agriculture. no. S1, pp. 277–292, doi: https://doi.org/10.1007/s00521-018-3737-1

It utilizes sensors to monitor soil moisture, water levels, and [7] L. García, L. Parra, J. M. Jimenez, J. Lloret, and P. Lorenz, "IoT-Based
Smart Irrigation Systems: An Overview on the Recent Trends on
weather conditions. By integrating AI and real-time weather Sensors and IoT Systems for Irrigation in Precision Agriculture,"
data, the system automatically adjusts watering schedules to Sensors, vol. 20, no. 4, p. 1042, 2020, doi:
optimize water usage and crop growth. A mobile application https://doi.org/10.3390/s20041042
allows farmers to remotely monitor and manage the system,
further enhancing efficiency and productivity. This system [8] S. Koduru, V. G. D. P. R. Padala, and P. Padala, "Smart Irrigation
offers a cost-effective solution for farmers to improve System Using Cloud and Internet of Things," in Proceedings of 2nd
International Conference on Communication, Computing and
irrigation practices and promote water conservation. Networking, 2018, doi: https://doi.org/10.1007/978-981-13-1217-
5_20
ACKNOWLEDGMENT
We would like to express our deepest gratitude to [9] G. Arvind, V. G. Athira, H. Haripriya, R. A. Rani, and S. Aravind,
the Dean, HOD, and Sense School department for their "Automated irrigation with advanced seed germination and pest
control," IEEE Xplore, doi:
unwavering support and guidance throughout our research https://doi.org/10.1109/TIAR.2017.8273687
project. Their encouragement, expertise, and provision of
necessary resources and facilities have been instrumental in [10] A. T. Abagissa, A. Behura, and S. K. Pani, "IoT Based Smart
shaping our understanding of the subject matter and in Agricultural Device Controlling System," in 2018 Second International
helping us to produce a high-quality research paper. We are Conference on Inventive Communication and Computational
particularly grateful to the Dean for fostering a vibrant Technologies (ICICCT), 2018, doi:
https://doi.org/10.1109/icicct.2018.8473126
research environment at Sense School and to the HOD for
their invaluable mentorship. Finally, we thank the Sense
[11] S. Bandyopadhyay, M. Sengupta, S. Maiti, and S. Dutta, "Role Of
School department for creating a supportive and stimulating Middleware For Internet Of Things: A Study," International Journal of
research atmosphere. Computer Science & Engineering Survey, vol. 2, no. 3, pp. 94–105,
2011, doi: https://doi.org/10.5121/ijcses.2011.2307
REFERENCES
[1] K. Obaideen, B. A. 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, vol. 7, p. 100124, 2022,
doi: https://doi.org/10.1016/j.nexus.2022.100124

[2] K. Jha, A. Doshi, P. Patel, and M. Shah, "A comprehensive review on

automation in agriculture using artificial intelligence," Artificial
Intelligence in Agriculture, vol. 2, no. 2, pp. 1–12, doi:
https://doi.org/10.1016/j.aiia.2019.05.004

[3] M. Ayaz, M. Ammad-Uddin, Z. Sharif, A. Mansour, and E. H. M.

Aggoune, "Internet-of-Things (IoT)-based smart agriculture: toward
making the fields talk," IEEE Access, vol. 7, pp. 129551–129583,
2019, doi: https://doi.org/10.1109/ACCESS.2019.2932609

[4] O. Elijah, T. A. Rahman, I. Orikumhi, C. Y. Leow, and M. N. Hindia,

"An Overview of Internet of Things (IoT) and Data Analytics in
Agriculture: Benefits and Challenges," IEEE Internet of Things
Journal, vol. 5, no. 5, pp. 3758–3773, doi:
https://doi.org/10.1109/jiot.2018.2844296

Authorized licensed use limited to: VIT University. Downloaded on December 11,2024 at 10:07:35 UTC from IEEE Xplore. Restrictions apply.