AI-Integrated Smart Agriculture System Using Autonomous Rover for Precision and Sustainable Farming

AI-Integrated Smart Agriculture System Using Autonomous Rover for Precision and Sustainable Farming

Dharshan K Department of Electronics and Communication Engineering

Sri Krishna College of technology Coimbatore, India 727822tuec028@skct.edu.in

Dr.K.Bagyalakshmi Department of Electronics and Communication Engineering

Sri Krishna College of technology Coimbatore, India bagyalakshmi.k@skct.edu.in

Boobalan S Department of Electronics and Communication Engineering

Sri Krishna College of technology Coimbatore, India 727822tuec021@skct.edu.in

Akash V A

Department of Electronics and Communication Engineering

Sri Krishna College of technology Coimbatore, India 727822tuec001@skct.edu.in

Abstract— The goal of AI-driven Smart Agriculture through Fully Automated Agricultural Machines (AI-Integrated SMART Agriculture System Using Autonomous Rover for Precision and Sustainable Farming), is to increase yield in traditional agriculture by using integrated technology (AI) and advanced sensors connected to the internet, with the ability to move freely without human operators. By equipping a multi- sensor rover with multiple sensors (moisture, ph, DHT11 temperature, humidity, colour, and many others) and a high- resolution camera module, it will be possible to capture current field conditions, and accurately monitor soil quality, crop growth, and environmental conditions in real-time. The data collected through the rover will give the farmer a complete record of their agricultural activities, which will include the analysis of soil quality, crops' growth and environmental conditions over a period of time. Through the use of a CNN- based (Convolutional Neural network) model, each crop will have its own “leaf disease” detection and stress assessment model to find out if there is an infection and/or nutrient deficiency in the crop as soon as possible, so the farmer can take preventative action before too much time has passed. A K- Nearest Neighbors (KNN)-based and/or many other machine learning models will be used to classify and predict crop yield. In addition to the above, a LLM (Large Language Model)-based advisory system will be integrated to provide the farmer with a summary report of all the information received from the rover, and a recommendation for the most efficient methods of managing their resources (water and nutrients), as well as other general information related to the efficient and sustainable use of water, fertilizers, pesticides, and natural resources in the agricultural environment. In order to guarantee spatial precision and effective field coverage, data can be collected from several zones thanks to the autonomous rover's independent field navigation. This project creates a comprehensive precision agriculture framework that improves decision-making, decreases manual labor, conserves natural resources, and increases overall crop productivity by fusing AI-driven analytics, IoT-enabled sensing, computer vision, and autonomous navigation. This advances sustainable and technology-driven farming.

Keywords— Precision Agriculture, Autonomous Rover, Machine Learning, IoT Sensors