Efficient Diagnosis of Diseases in Rice Crop Using Machine Learning

Efficient Diagnosis of Diseases in Rice Crop Using Machine Learning

GOUNI KALPANA, M SADVIK REDDY, B SAMPATH TEJA, M ADITHYA SINGH, L NAGENDER KUMAR

1.  MS. GOUNI Kalpana, Student, CSE, JBREC, Hyderabad

2.  Mr. M SADVIK Reddy, Student, CSE, JBREC, Hyderabad

3.  Mr. B SAMPATH TEJA, Student, CSE, JBREC, Hyderabad

4.  Mr. M ADITHYA SINGH, Student, CSE, JBREC, Hyderabad

5. Mr. L NAGENDER KUMAR, Assistant Professor, CSE, JBREC, Hyderabad

Abstract

Rice is a staple food for over half of the global population, making its cultivation crucial for food security. However, rice crops are highly susceptible to various diseases that can significantly reduce yields and affect quality. Early detection and accurate diagnosis of these diseases are essential for effective crop management. Traditional methods of disease diagnosis rely heavily on visual inspections and expert knowledge, which can be time-consuming and prone to error. This paper explores the application of machine learning (ML) techniques to automate and enhance the diagnosis of diseases in rice crops. By utilizing image processing and pattern recognition algorithms, the study demonstrates how ML models can classify and identify diseases based on symptoms observed in leaves, stems, and grains. A variety of ML algorithms, including convolutional neural networks (CNNs) and decision trees, are trained using a dataset of labeled rice images. The results show that ML-based diagnosis offers a more efficient, accurate, and scalable solution for disease management. Moreover, this approach significantly reduces the need for manual intervention and expert input, allowing farmers to adopt a proactive and data-driven approach to crop health monitoring. The integration of ML techniques into precision agriculture paves the way for more sustainable rice production and improved food security.