This study explores the efficacy of various AI models in predicting crop diseases, with a particular focus
on fuzzy logic, a method renowned for its ability to handle uncertainty and imprecision in agricultural
data. By comparing fuzzy logic with other AI approaches, including Decision Trees, Random Forests,
Support Vector Machines (SVMs), and Convolutional Neural Networks (CNNs), we assess their
performance based on accuracy, precision, recall, F1 score, and AUC (Area Under the Curve). Our
experimental results indicate that the fuzzy logic model achieves an accuracy of 85.2%, with a robust
balance between precision (83.5%) and recall (87.0%), and an AUC of 0.88. While the fuzzy logic model
performs admirably, the Random Forest and CNN models surpass it, with Random Forest achieving the
highest accuracy (87.5%) and CNN the highest performance metrics overall, including an accuracy of
89.1% and an AUC of 0.92. This study highlights the strengths of fuzzy logic in managing imprecise data
and suggests that while it is a valuable tool for crop disease prediction, advanced models like CNNs
offer superior performance in handling complex prediction tasks.
