Deep learning models for enhancing potato leaf disease prediction: Implementation of transfer learning based stacking ensemble model

MotivationCrop diseases pose a critical threat to global food security, causing substantial agricultural yield losses. Manual disease identification is labor-intensive and requires expertise, hindering timely and accurate detection.Problem GapTraditional methods for identifying plant diseases are time-consuming and demand specialized knowledge. The need for a more efficient, automated, and accurate approach is evident to minimize crop losses and ensure food security.ContributionThis research paper addresses the challenge of plant disease detection by proposing a novel approach that combines image processing and deep learning techniques. The primary contribution is a sophisticated deep neural network ensemble model, which integrates Residual Network, MobileNet, and Inception models. This ensemble architecture is designed to maximize accuracy and robustness in disease classification. The model is trained on an extensive dataset containing images of both healthy and infected potato leaves. It accomplishes the precise categorization of leaves into three classes: healthy potato leaves, infected potato leaves (two classes). The model's proficiency lies in its ability to discern intricate leaf features, colors, and types, enabling it to differentiate between healthy and potentially diseased leaves. This research makes a significant contribution to the development of automated disease detection systems. By bridging the gap between manual identification and advanced technology, it presents a promising solution for early disease detection and prevention. Ultimately, this approach can foster increased agricultural productivity, ensuring enhanced food security on a global scale.ResultsResults demonstrate the proposed model's effectiveness, achieving an impressive overall accuracy of 98.86%. This high accuracy attests to the model's competence in precisely detecting and classifying potato diseases. By harnessing the potential of ensemble-based deep learning and image processing, this research introduces an innovative tool for agriculturalists and researchers.