Transforming Agriculture with IoT and AI: A Comprehensive Crop

Monitoring and Management System

B. Marikumar, M. Arjun, A. Arul Thiraviam, K. Gowtham Sidharth, G. Vasunthraa

and S. Roshini

Department of Computer Science and Engineering, V.S.B College of Engineering Technical Campus,

Kinathukadavu, Coimbatore, Tamil Nadu, India

Keywords: Blockchain Technology, Smart Technology Integration, Real-Time Decision Making, Machine Learning

Algorithms, Edge Computing Analyses, Soil Moisture, Temperature, Humidity, Light Intensity.

Abstract: Agriculture remains crucial for food production; however, it is continuously impacted by climate change,

limited water supply, pest infestation, and poor management of resources. Farming practices of the past are

no longer sufficient, requiring new approaches. In this paper, I present and, in this paper, I discuss the

development and deployment of an intelligent Internet of Things (IoT)-based agricultural crop monitoring

and control system that automates farming through smart technology integration. Smart sensors form a

network for monitoring environmental factors including soil moisture, temperature, humidity, light intensity,

and soil ph. Drones offer fully automated aerial imaging for remote sensing to monitor crop health, while

edge computing analyses data close to the source for real-time decision making. The cloud serves as the

system's repository and the machine learning algorithms provide predictive analysis, which enables farmers

to take proactive measures against pest infestation and bad weather. Furthermore, blockchain technology

guarantees security, transparency, and traceability of products in an agricultural supply chain. Farmers can

access real-time concrete guidance through the mobile app or the web app, enabling them to make informed

decisions such as conserving water, fertilizers, and pesticides.

1 INTRODUCTION

The agricultural sector remains crucial to world food

security but struggles with climate change, water and

pest management, and poor resource mobilization.

Efforts toward modern service industrialization have

made traditional farming, which depends on manual

labour and simple agricultural tools, unfit to meet

contemporary requirements. This project seeks to

solve these problems by implementing sophisticated

technologies so that they can assist farmers in

overcoming challenges by developing an advanced

IoT-based crop monitoring system. The system is

designed to optimize agrotechnology’s, improve

productivity, and foster sustainable agricultural

practices. The integration of IoT, edge computing,

drone technology, machine learning, and blockchain

delivers a holistic approach to farmers of all scales,

allowing for data-driven approaches to move farming

away from guesswork towards enhanced production

and lowered repercussions on the ecosystem.

1.1 System Overview

The modules included in the system are as follows:

• Smart Sensor Network: Keeps track of

environmental factors like soil moisture,

temperature, humidity, light intensity, and

soil PH.

• Edge Computing Unit: Analyses

information on site to decrease latency and

improve responsiveness.

• Drone Surveillance: Takes overhead pictures

of the fields to check the health of the crops

and identify pest issues.

• Cloud Based Platform: Uses the data and

applies machine learning for data analysis

and information storage as well as predictive

analytics.

• Blockchain Framework: Guarantees the

traceability and transparency of the

agricultural supply chain data.

238

Marikumar, B., Arjun, M., Thiraviam, A. A., Sidharth, K. G., Vasunthraa, G. and Roshini, S.

Transforming Agriculture with IoT and AI: A Comprehensive Crop Monitoring and Management System.

DOI: 10.5220/0013925800004919

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st Inter national Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) - Volume 5, pages

238-242

ISBN: 978-989-758-777-1

• Controlled Systems: Controls the sensors

and actuators for irrigation, fertilization, and

pest control in conjunction with real-time

data.

• Community Knowledge-Sharing Platform:

Promotes interaction and creativity among

farmers.

1.2 Before IoT System

1.2.1 Smart Sensor Network

A network of smart sensors is deployed over

agricultural fields to monitor vital environmental

parameters. These sensors report text messages for

soil moisture content, temperature, humidity, light

intensity, and soil ph in real time. The data is

processed locally with edge computations to ensure

timely responses to critical changes, such as sudden

drops in soil moisture or temperature spikes.

1.3 Edge Computing Unit

The edge unit does local data processing to eliminate

response latency. This ensures prompt protective

interventions to maintain crop health. The processed

information is relayed to a central microcontroller

which fuses the data and uploads it to a cloud platform

for detailed processing. Figure 1 shows the

Representation of before IoT Invention in Agriculture

field. Figure 2 shows the Representation of after IoT

Invention in Agriculture field.

Figure 1: Representation of before IoT Invention in Agriculture field.

1.3.1 After IoT System

Figure 2: Representation of after IoT Invention in Agriculture field.

Transforming Agriculture with IoT and AI: A Comprehensive Crop Monitoring and Management System

239

1.4 Drone Surveillance

Farms are surveyed using drones that have high

resolution cameras and multispectral sensors to take

pictures of the fields. This sensor provides high aerial

data and when combined with ground data captures,

help the farmers acquire better understanding of their

fields and more articulation in the necessary

adjustments.

1.5 Cloud-Based Platform

This cloud platform is the systems brain where data is

stored and visualized using sophisticated mobile and

web applications interfaces. Advanced machine

learning analyses the information to create predictive

analytics of greatly potential problems such us pest

infestation, disease outbreak or we

1.6 Blockchain Structure

The data management framework utilizes blockchain

technology to maintain an unalterable record of

agricultural activities. This improves accountability

and traceability in the supply chain while satisfying

regulatory needs and consumer expectations.

1.7 Self-Regulating Control

Mechanisms

Real-time sensor data triggers automated irrigation,

fertilization, and pest control systems. For instance, if

soil moisture is recorded below a specific value, crops

are watered as the system initiates irrigation.

1.8 Farmers’ Innovative Practices

Community Platform

The platform features a community-based innovative

practices sharing platform where farmers share

knowledge, strategies, and solutions relevant to local

constraints. This improves collaborative innovation

as farmers support each other and respond to

variability more effectively.

2 A SYSTEM DEVELOPMENT

AND DEPLOYMENT

2.1 Intelligent Sensor System

• Parts: pH, light, temperature, humidity, and

soil moisture sensors.

• Operation: Captures information on

environmental conditions and sends it to the

edge computing unit for further processing.

2.2 Edge Computing Unit

• Parts: Edge computing module,

microcontroller.

• Operation: Controls the captured data

locally to decrease latency and enable

quicker responses.

2.3 Drone Surveillance

• Componentry: Drones with high resolution

cameras and multispectral sensors.

• Operational: Takes aerial photographs to

assess plant health and identify potential

pests.

2.4 Cloud Based Platform

• Componentry: Cloud server, machine

learning, mobile and web applications.

• Operational: Data storage and analysis,

predictive modelling, and insight generation

to farmers.

2.5 Blockchain Framework

• Componentry: Blockchain network and QR

codes.

• Operational: Principally guarantees

visibility and traceability within the

agriculture supply chain.

2.6 Automated Control Systems

• Componentry: Automated irrigation,

fertilization, and pest control systems.

• Operational: Carried out automated

processes dependent on real-time sensor

information.

2.7 Community Knowledge Sharing

Platform

• Componentry: Online platform, professional

consultation, published research papers,

training documentation.

• Operational: Enable farmers to collaborate

and enhance productivity through

innovation.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

240

3 LITERATURE REVIEW

3.1 Current Systems and Their

Challenges

• Excessively Expensive: Sensors, drones, and

other hardware IoT-based systems come

with high costs that are typically out of reach

for small-scale farmers.

• Rural areas have unreliable internet

coverage which obstructs real-time data

streaming and analytics.

• Farmers who do not have sufficient training

and experience using IoT systems have a

tough time trying to understand and interpret

the hundreds of data points IoT-enabled

systems generate.

• Remote and off-grid farming areas are prone

to unreliable power sources which poses a

problem for many IoT devices that need

constant power.

• Smart sensors and drones have to undergo

routine maintenance and recalibrations that

many farmers find difficult to perform due to

the level of skill required.

• The current smart systems available are not

designed to accommodate businesses of

different sizes, making it more difficult for

larger operations to scale.

• IoT systems are open to cyberattack without

strong encryption, risking data security and

privacy.

• The lack of sufficient historical data and

localized variable consideration results in

reduced predicted accuracy from machine

learning models.

• Different manufacturers’ devices and

platforms are often incompatible with each

other, leading to less efficient work

processes.

4 RESEARCH DESIGN

4.1 System Architecture

The system is made up of these parts:

• Smart Sensor Network: It gathers real-time

info about things like soil, weather, and

crops.

• Edge Computing Unit: It processes data

right where it’s collected to make things

faster.

• Drone Surveillance: Drones take pictures

from the air to check how healthy the crops

are.

• Cloud-Based Platform: It stores all the data

and uses smart tools to analyse it.

• Blockchain Framework: It keeps

everything clear and traceable, so you can

track where stuff comes from.

• Automated Control Systems: It handles

watering, adding fertilizers, and dealing with

pests automatically.

• Community Knowledge-Sharing

Platform: A place where farmers can share

tips, ideas, and work together to improve

farming. Figure 3 illustrates the Impact of

IoT on Farming Efficiency over Time.

5 RESULTS AND DISCUSSION

Figure 3: Impact of IoT on Farming Efficiency over Time.

Month 1 Month 2 Month 3 Month 4

IoT System for Precision Farming and

Resource Efficiency

Before IOT After IOT

Transforming Agriculture with IoT and AI: A Comprehensive Crop Monitoring and Management System

241

6 CONCLUSIONS

This IoT crop monitoring system is a huge step

forward for smart farming. It uses high-tech tools to

give farmers real-time updates, smart guesses about

what’s coming, and automatic controls to help them

use water, fertilizer, and other stuff more efficiently

and grow more crops. It’s easy to use, works for small

or big farms, and is good for both the planet and the

wallet. This system is a great way to solve today’s

farming problems and create a future where food is

more sustainable and reliable.

REFERENCES

Christodoulou, A., Christidis, P., and Bissel ink, B., 2020.

Forecasting the impacts of climate change on inland

waterways. Transportation Research Part D: Transport

and Environment, 82: 102159.

Weng, C.N., 2005. Sustainable management of rivers in

Malaysia: Involving all stakeholders. International

Journal of River Basin Management, 3(3): 147-162.

Tori man, M.E., Hassan, A.J., Gazim, M.B., Mokhtar, M.,

SA, S.M., Jaafar, O., and Aziz, N.A.A., 2009.

Integration of 1-d hydrodynamic model and GIS

approach in flood management study in Malaysia.

Research Journal of Earth Sciences, 1(1): 22-27.

Kamarudin, M.K.A., Tori man, M.E., Wahab, N.A., Rosli,

H., Ata, F.M., and Faudzi, M.N.M., 2017.

Sedimentation study on upstream reach of selected

rivers in Pahang River Basin, Malaysia. International

Journal on Advanced Science, Engineering and

Information Technology, 7(1): 35-41.

Adhiharto, R., and Komara, F.A., 2018. Perancangan

Konstruksi Trash Bucket Conveyor (Tbc) Sebagai

Mekanisme Pembersih Sampah Di Sungai.

Khekare, G.S., Dhanre, U.T., Dhanre, G.T., and Yede, S.S.,

2019. Design of Optimized and Innovative Remotely

Operated Machine for Water Surface Garbage

Assortment. International Journal of Computer

Sciences and Engineering, 7(1): 113-117.

Othman, H., Petra, M.I., De Silva, L.C., and Caesarendra,

W., 2020. Automated trash collector design. In Journal

of Physics: Conference Series, 1444(1): 012040.

Kader, A.S.A., Saleh, M.K.M., Jalal, M.R., Sulaiman, O.O.,

and Shamsuri, W.N.W., 2015. Design of rubbish

collecting system for inland waterways. Journal of

Transport System Engineering, 2(2): 1-13.

Akib, A., Tasnim, F., Biswas, D., Hashem, M.B., Rahman,

K., Bhattacharjee, A., and Fattah, S. A., 2019.

Unmanned Floating Waste Collecting Robot. In

TENCON 2019-2019 IEEE Region 10 Conference

(TENCON), 2645-2650.

Balasuthagar, C., Shanmugam, D., and Vigneshwaran, K.,

2020. Design and fabrication of beach cleaning

machine. In IOP Conference Series: Materials Science

and Engineering, 912(2): 022048.

Kong, S., Tian, M., Qiu, C., Wu, Z., and Yu, J., 2020.

IWSCR: An intelligent water surface cleaner robot for

collecting floating garbage. IEEE Transactions on

Systems, Man, and Cybernetics: Systems, 1-11.

Lindquist, A., 2016. Baltimore’s Mr. Trash Wheel. The

Journal of Ocean Technology, 11(12): 35-37.

Geraeds, M., van Emmerik, T., de Vries, R., and bin Ab

Razak, M.S., 2019. Riverine plastic litter monitoring

using unmanned aerial vehicles (UAVs). Remote

Sensing, 11(17): 2045.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

242