A Hierarchical Deep Learning Framework for Coffee Leaf Disease Detection and Visible Severity Classification Under Saudi Arabian Field Conditions

Saudi Arabia is expanding its domestic coffee sector under Vision 2030, yet coffee farming remains vulnerable to leaf diseases and pest damage. Image-based artificial intelligence studies conducted under Saudi field conditions remain limited, particularly in relation to assessing image-based visible disease severity. This study designs a hierarchical deep learning framework for screening coffee leaf diseases using field-collected images of Saudi coffee leaves. Three tasks were addressed: binary health status classification, four-class disease or pest damage identification, and binary visible severity classification. A dataset of 550 RGB images was collected from Al-Dayer Governorate, Jazan, under natural field conditions. ResNet50, DenseNet121, and EfficientNet-B0 were evaluated via transfer learning in two phases: a Saudi-only phase and an integrated phase that combined Saudi data with selected JMuBEN and JMuBEN2 samples. In the Saudi-only phase, ResNet50 achieved 96.47% accuracy for binary classification, while DenseNet121 achieved 68.66% and 78.12% for disease and visible severity classification, respectively. In the integrated phase, performance improved to 99.74%, 97.76%, and 97.37%. These integrated-phase results are interpreted as evidence that dataset expansion and increased visual diversity can improve model performance, rather than as definitive estimates of field deployment performance. The results show that binary classification is feasible under limited local data, whereas fine-grained disease classification is more constrained by dataset size and class imbalance. Grad-CAM visualizations were used to support qualitative interpretability and should not be interpreted as biological validation of disease localization. The framework is positioned as a decision-support screening approach that requires further expert-validated, multi-farm, and multi-season evaluation before deployment.