In the realm of modern agriculture, the timely detection and classification of plant diseases and pests have emerged as pivotal challenges, with profound implications for crop yields, economic stability, and global food security. While traditional diagnostic methods, such as visual inspections by experts or basic imaging systems, have proven inadequate due to subjectivity, inconsistent accuracy, and limited scalability, particularly in large-scale farming contexts, the advent of deep learning (DL) techniques offers a promising solution. This research delves into the development and implementation of a DL-based vision system, leveraging the ResNet architecture, to address the critical need for accurate and timely diagnosis in precision agriculture. The proposed system, trained on a diverse dataset of apple plant images, achieves remarkable accuracy in detecting and classifying various diseases affecting leaves, stems, and fruits. Furthermore, the integration of model explainability techniques, specifically SHapley Additive exPlanations (SHAP), provides valuable insights into the decision-making process of the model, enhancing its interpretability and trustworthiness. This study not only showcases the potential of DL in revolutionizing agricultural practices but also underscores its alignment with the United Nations' Sustainable Development Goals (SDGs), particularly in promoting zero hunger, responsible consumption and production, climate action, and life on land. By enabling early and accurate disease detection, the proposed system contributes to sustainable crop management, reducing the reliance on chemical pesticides, and enhancing agricultural resilience. The research also highlights the importance of real-world applicability, emphasizing the need for further validation under diverse, uncontrolled agricultural conditions to ensure the robustness and generalizability of DL models. The findings presented herein offer a compelling case for the adoption of DL technologies in agriculture, with the potential to transform food systems and contribute to a more sustainable and resilient future.
