Advancing Plant Disease Classification Through Multi-Spectral Imaging and Artificial Intelligence: Methods, Models, and Applications

Plant disease classification is crucial for effective agricultural management, enabling early detection and mitigation of crop diseases.This research assesses deep learning models for plant disease classification using multi-spectral imaging data.The study explores models such as Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs), utilizing optimization techniques like ADAM, SGD, and RMSPROP.The methodology includes dataset curation, preprocessing, and thorough model evaluation based on accuracy, precision, recall, and F1-score.Results indicate the strengths and limitations of each approach, providing key insights for advancing agricultural technology.The developed models are also integrated into a web application for easy access by agricultural stakeholders.This research underscores the potential of combining multispectral imaging and AI to promote sustainable crop management and address practical agricultural challenges.