A Hybrid Deep Learning Model with Bayesian Optimization Technique for Leaf Disease Classification

Detecting plant diseases on time is imperative to improve agricultural productivity and mitigate economic losses.  This study presents a novel artificial intelligence framework for classifying plant diseases, combining advanced deep learning technologies with a hyperparameter optimization strategy.  Specifically, we employed a hybrid architecture that concatenates two pre-trained models, MobileNetV2 and DenseNet201, enriched with custom layers developed by the researchers.  Bayesian Optimization was employed to enhance model performance, focusing on four critical hyperparameters: learning rate, number of units, optimizer, and dropout rate.  The methodology integrates data augmentation, transfer learning, and fine-tuning to enhance feature extraction and model robustness.  The results demonstrate remarkable performance, with training accuracy at 98.95%, validation accuracy at 99.83%, and testing accuracy at 99.51%.  These findings underscore the efficacy of sophisticated AI methodologies in automating the detection of plant diseases, indicating substantial progress in precision agriculture and contributing to sustainable food security.