International Research Journal of Engineering and Technology (IRJET) Volume: 11 Issue: 08 | Aug 2024
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
Enhanced Rice Crop Management through Machine Learning-Based Disease Detection B.Srinadh Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundation Guntur,India
B.Praveen Kumar
K.Lokesh Chowdary
Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundation Guntur,India
Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundation Guntur,India
G.Yathin Sai Teja Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundation Guntur,India
-------------------------------------------------------------------------***-----------------------------------------------------------------------Abstract— Agriculture is an essential part of every person's daily existence. In order to uncover ailments that impair a product's ability to be created, 75 out of 100 people working in the technology business are switching from manual product analysis to automated workflow solutions. Rice crops throughout the world are at risk from Bacterial Leaf Blight (BLB), a lethal disease that can reduce production in half. This threatens the stability of the world's food supply because other rice-related illnesses also severely reduce yield. Consequently, BLB is not solely to blame. Mitigating the threat to global food security posed by rice infections throughout their development stage requires early identification.
growers, and while pesticides can increase yields, their high cost places a financial strain on farmers. The necessity for technology solutions is further highlighted by outdated diagnostic methods. This study suggests evaluating rice crops in-depth and providing helpful recommendations for raising productivity by leveraging cutting-edge data processing techniques including deep learning, artificial intelligence, and machine learning. Significance of the Research Problem Understanding and effectively combating rice diseases is of paramount significance. This research problem has practical implications across various domains:
Convolutional Neural Network (CNN) model, which is wellknown for its effectiveness in picture classification tasks, is the suggested approach for this study. Various classification techniques, including Support Vector Machine (SVM) and Comparative Analysis methods, are employed to differentiate between different disease types by analyzing data and images comprising the dataset.
1.
Enhancing Crop Management: By accurately diagnosing diseases like leaf smut, bacterial blight, and brown spots, farmers can take timely and appropriate measures to treat affected plants, ultimately improving crop health and yield.
2.
Reducing Financial Burden: Technological solutions can reduce reliance on expensive pesticides, offering more cost-effective disease management strategies that can ease the financial burden on farmers.
3.
Improving Food Security: Since rice is a staple food for a large section of the world's population, steady and expanded rice production is ensured by effective disease management, which directly contributes to food security.
4.
Advancing Agricultural Technology: New and improved approaches to crop monitoring and management are produced as a result of the application and development of sophisticated machine learning and deep learning algorithms for
To find the shortcomings in the existing method and improve the algorithms, a sizable dataset is needed. This could end up in a disease detection system that proves more accurate, particularly for rice harvests. Keywords— Rice Leaf Disease Detection, Machine Learning, CNN, SVM, Deep Learning.
1. INTRODUCTION AND OVERVIEW Rice, a vital cereal that feeds billions worldwide, faces a significant production decline, estimated at 123.8 million metric tons (Ministry of Agriculture and Farmers Welfare). Crop diseases, particularly those affecting the stems and leaves of rice plants, are a major contributing factor. Diagnosing and treating these diseases is challenging for
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 40