Machine Learning based Disease and Pest detection in Agricultural Crops

ABSTRACT Agriculture is a critical sector in India, supporting the majority of the population and contributing significantly to the economy. However, challenges such as crop diseases, pests, and the anticipated reduction of farmland due to population growth threaten future food security. This paper presents a machine learning based system designed to predict crop diseases and pests, with a focus on the chilli crop as a case study. The system integrates multiple classifiers, including Random Forest, AdaBoost, K-Nearest Neighbors, and Logistic Regression. Performance evaluation using accuracy, Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) demonstrates that the proposed approach achieves an accuracy of 0.90, MSE of 0.37, MAE of 0.15, and RMSE of 0.61. The Random Forest Classifier was identified as the most effective model. The system provides timely alerts to farmers, aiding in proactive crop management and improving agricultural productivity.