Wheat Crop Disease Detection Using Machine Learning And Hybrid Metaheuristic Techniques

Abstract

Wheat is a staple food for many people around the world, and detecting diseases affecting wheat plants is crucial to maintain food security and sustainable agriculture practices. Wheat leaf diseases are the most crucial ones that affect crop production, and a method for efficient identification and classification of these diseases is important. Early diagnosis and precise classification of these diseases are critical in applying appropriate management strategies and maintaining crop health. Nevertheless, available techniques to identify and categorize disease typically tend to fall short due to issues with data deficit and computational pressure. To tackle these problems, this study proposes a hybridization of the machine learning models with the metaheuristic optimization models to enhance the performance of the existing algorithms. This new framework implements some well-known ML approaches such as Support Vector Macine(SVM), Random Forest(RF), and K-Nearest Neighbors(K-NN) together with metaheuristic optimization methods such as Ant Colony Optimization (ACO), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). Through feature engineering and advanced parameter tuning, this framework aims to improve the accuracy, precision, and efficiency of wheat disease classification systems, enabling more effective disease management strategies.