This paper presents an analysis of machine learning (ML) models for predicting potato leaf diseases, specifically early blight and late blight, using a comprehensive database of over 4000 weather records. The study investigates key factors such as temperature, humidity, wind speed, and atmospheric pressure, which are correlated with disease prevalence. Advanced analytical techniques like K-means clustering, principal component analysis (PCA), and copula analysis were used to identify data relationships. Several ML models, including logistic regression, gradient boosting, multilayer perceptron (MLP), support vector machine (SVM), and K-nearest neighbor (KNN), were evaluated. Feature selection methods, such as binary Greylag Goose Optimization (bGGO), were applied to enhance model performance by identifying relevant features. The MLP model with feature selection achieved an accuracy of 98.3%, highlighting the importance of feature selection in improving model performance. The study emphasizes the role of optimized ML models in proactive agricultural disease management, aiming to minimize crop loss and promote sustainable farming practices. Potatoes, a major non-cereal food crop, are vulnerable to diseases like early and late blight, which can severely impact yield and quality. Traditional disease management methods are labor-intensive and may cause environmental degradation. Recent efforts have integrated artificial intelligence (AI) into agricultural practices to manage crop diseases more effectively. AI models are used for predicting disease outbreaks, optimizing treatment plans, and reducing chemical usage. However, the relationship between weather conditions and potato diseases remains underexplored. This research focuses on a complete dataset that includes weather parameters and disease records, using AI and audio-visual techniques to create a model for predicting disease outbreaks based on changing weather conditions. Establishing such a predictive model would help refine agricultural processes by enabling rapid responses to prevent crop deterioration and reduce chemical use. Optimizing these AI models is crucial for improving their predictive accuracy, effectiveness, and reliability. This optimization involves fine-tuning weather parameters, improving AI algorithms, and testing models against actual disease manifestations. The models should be integrated with existing agricultural management systems, considering geographical and climatic conditions. The study also highlights that agricultural staff do not necessarily need professional AI knowledge to use these models effectively.This paper presents an analysis of machine learning (ML) models for predicting potato leaf diseases, specifically early blight and late blight, using a comprehensive database of over 4000 weather records. The study investigates key factors such as temperature, humidity, wind speed, and atmospheric pressure, which are correlated with disease prevalence. Advanced analytical techniques like K-means clustering, principal component analysis (PCA), and copula analysis were used to identify data relationships. Several ML models, including logistic regression, gradient boosting, multilayer perceptron (MLP), support vector machine (SVM), and K-nearest neighbor (KNN), were evaluated. Feature selection methods, such as binary Greylag Goose Optimization (bGGO), were applied to enhance model performance by identifying relevant features. The MLP model with feature selection achieved an accuracy of 98.3%, highlighting the importance of feature selection in improving model performance. The study emphasizes the role of optimized ML models in proactive agricultural disease management, aiming to minimize crop loss and promote sustainable farming practices. Potatoes, a major non-cereal food crop, are vulnerable to diseases like early and late blight, which can severely impact yield and quality. Traditional disease management methods are labor-intensive and may cause environmental degradation. Recent efforts have integrated artificial intelligence (AI) into agricultural practices to manage crop diseases more effectively. AI models are used for predicting disease outbreaks, optimizing treatment plans, and reducing chemical usage. However, the relationship between weather conditions and potato diseases remains underexplored. This research focuses on a complete dataset that includes weather parameters and disease records, using AI and audio-visual techniques to create a model for predicting disease outbreaks based on changing weather conditions. Establishing such a predictive model would help refine agricultural processes by enabling rapid responses to prevent crop deterioration and reduce chemical use. Optimizing these AI models is crucial for improving their predictive accuracy, effectiveness, and reliability. This optimization involves fine-tuning weather parameters, improving AI algorithms, and testing models against actual disease manifestations. The models should be integrated with existing agricultural management systems, considering geographical and climatic conditions. The study also highlights that agricultural staff do not necessarily need professional AI knowledge to use these models effectively.