Prediction Of Paddy Crop Blast Disease Using An Enhanced Machine Learning Techniques

Abstract

Paddy crop blast disease, caused by Magnaporthe oryzae, is one of the most destructive fungal diseases affecting rice production worldwide. Early detection and forecasting of this disease are crucial for minimizing yield losses and ensuring sustainable agricultural practices. This study presents an enhanced machine learning–based approach for forecasting paddy blast disease using integrated environmental, climatic, and crop-related parameters. Various algorithms such as Random Forest, Support Vector Machine (SVM), and Gradient Boosting were compared, and an optimized hybrid ensemble model was developed to improve prediction accuracy. The model utilizes real-time meteorological data, including temperature, humidity, and rainfall, along with soil characteristics and historical disease occurrence patterns. Experimental results demonstrate that the proposed enhanced machine learning model outperforms conventional prediction techniques in terms of accuracy, precision, and recall. The findings indicate that the system can serve as an effective decision-support tool for farmers and agricultural authorities to implement timely preventive measures, thereby reducing crop loss and improving productivity.