Optimizing Chilli Crop Disease Classification Models through Hybrid Differential Evolution and Simulated Annealing

Crop diseases caused by chillies are a serious threat to food security and agricultural production. Timely intervention and mitigation efforts are contingent upon an accurate categorization of these disorders. Here, we provide a new method that combines the methods of Simulated Annealing (SA) and Differential Evolution (DE) to improve classification models for illnesses affecting chilli crops. Our hybrid strategy seeks to improve illness classification models' performance and efficiency by using the advantages of both optimization methods. We conducted experiments on a comprehensive dataset comprising diverse chilli crop disease instances. Results show that replacement of either optimization demonstrates greater accuracy and robustness of classification models than either method individually. Additionally, our approach is promising for applications in precision agriculture, giving farmers useful information for proactive disease management and crop protection in the real world. This research progresses the field of agricultural decision support systems by establishing a sound framework for optimizing chilli crop disease classification models with reliability, ensuring sustainable farming practices, and food security globally.