Benchmarking ML and DL Models for Mango Leaf Disease Detection: A Comparative Analysis

Mango leaf diseases can have detrimental effects on the productivity and health of mango trees, leading to significant economic losses. Early and accurate detection of these diseases is crucial for enabling timely interventions and enhancing crop management strategies. In this study, we conduct a comprehensive comparison of various ML and DL models to effectively detect and classify common mango leaf diseases, as well as to differentiate between healthy and diseased leaves, using a custom dataset of mango leaf images. Our investigation encompasses traditional ML models, such as RandomForestClassifier and k-Nearest Neighbors, in addition to advanced DL models, including AlexNet, EfficientNet-B0, DenseNet121, and ResNet50. The primary objective of this comparative study is to highlight the advantages and limitations of each model, pinpoint the optimal model for mango leaf disease detection and classification, and evaluate the influence of data preprocessing, feature extraction, and hyperparameter optimization on model performance. By systematically comparing a diverse range of ML and DL models, our research aims to contribute to the development of efficient, reliable, and robust methodologies for the early detection and accurate classification of mango leaf diseases. The results of this study have the potential to assist farmers and agricultural experts in making well-informed decisions pertaining to crop management and disease control, thereby promoting sustainable and productive mango cultivation practices.