This paper addresses the classification of potato leaf diseases, specifically early blight and late blight, which are significant threats to potato yield and quality. The study utilizes a detailed database of over 4000 records of weather conditions, including temperature, humidity, wind speed, and atmospheric pressure, to analyze their correlations with disease prevalence. Advanced analysis techniques such as K-means clustering, PCA, and copula analysis are employed to identify these relationships. Various machine learning (ML) models, including logistic regression, gradient boosting, multilayer perceptron (MLP), support vector machine (SVM), and K-nearest neighbor (KNN) models, are tested, both with and without feature selection. Feature selection methods, such as binary Greylag Goose Optimization (bGGO), are applied to enhance model performance. The results show that the MLP model with feature selection achieves an accuracy of 98.3%, highlighting the importance of feature selection in improving model accuracy. The findings underscore the potential of optimized ML models in proactive agricultural disease management, aiming to minimize crop loss and promote sustainable farming practices.This paper addresses the classification of potato leaf diseases, specifically early blight and late blight, which are significant threats to potato yield and quality. The study utilizes a detailed database of over 4000 records of weather conditions, including temperature, humidity, wind speed, and atmospheric pressure, to analyze their correlations with disease prevalence. Advanced analysis techniques such as K-means clustering, PCA, and copula analysis are employed to identify these relationships. Various machine learning (ML) models, including logistic regression, gradient boosting, multilayer perceptron (MLP), support vector machine (SVM), and K-nearest neighbor (KNN) models, are tested, both with and without feature selection. Feature selection methods, such as binary Greylag Goose Optimization (bGGO), are applied to enhance model performance. The results show that the MLP model with feature selection achieves an accuracy of 98.3%, highlighting the importance of feature selection in improving model accuracy. The findings underscore the potential of optimized ML models in proactive agricultural disease management, aiming to minimize crop loss and promote sustainable farming practices.