Classification of the Severity Levels of Apple Rot Disease: A Hybrid Dual CNN and LSTM Deep Learning Approach

The fruit industry experiences significant economic losses due to various diseases affecting apple crops annually. Early diagnosis of these diseases is crucial to prevent the intensity of the disease and to ensure the production of healthy crops. In this study, we propose a novel hybrid model for the multi-class classification of apple illnesses that blends convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. The proposed model was trained and evaluated on a dataset of images of apple fruit images exhibiting different severity degrees of black rot disease. Experimental results depict the hybrid model outperformed traditional single-model approaches, achieving an overall accuracy of 96.5% classification of the disease. This demonstrates the potential of combining CNNs and LSTMs to achieve high accuracy in complex image classification tasks, particularly in the field of plant disease diagnosis. Our proposed model can provide a valuable tool for apple farmers, researchers, and extension workers in the early detection and management of apple diseases, thereby improving crop yields and minimizing economic losses.