A Hierarchical Deep Learning Framework for Coffee Leaf Disease Detection and Visible Severity Classification Under Saudi Arabian Field Conditions
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Coffee research and impacts · Remote Sensing in Agriculture
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science, King Khalid University, Abha 61421, Saudi Arabia
Funding
Deanship of Research and Graduate Studies at King Khalid University
References (32)
Show source-provided references
1. Food and Agriculture Organization of the United Nations (2023). The Impact of Disasters on Agriculture and Food Security 2023, FAO. Available online: https://openknowledge.fao.org/handle/20.500.14283/cd4706en.
2. International Coffee Organization (2023). Coffee Report and Outlook December 2023, ICO. Available online: https://icocoffee.org/documents/cy2023-24/Coffee_Report_and_Outlook_December_2023_ICO.pdf.
3. FAO Plant Production and Protection Division (NSP) (2022). Agroecology Knowledge Hub, FAO. Available online: https://www.fao.org/3/cc2447en/cc2447en.pdf.
4. Sarkozi, A. (2025, December 12). New Standards to Curb the Global Spread of Plant Pests and Diseases, FAO News, Available online: https://www.fao.org/newsroom/detail/New-standards-to-curb-the-global-spread-of-plant-pests-and-diseases/en.
5. Ojiambo, P.S. (2025). Insect pest and plant disease management in horticultural crop production: Recent insights provide opportunities for improved control. Front. Hortic., 4.10.3389/fhort.2025.1605035 ↗
6. UNESCO (2025, September 10). Arabic Coffee, a Symbol of Generosity. Available online: https://ich.unesco.org/en/RL/arabic-coffee-a-symbol-of-generosity-01074.
7. Public Investment Fund (2025, September 10). PIF Launches Saudi Coffee Company, Available online: https://www.pif.gov.sa/en/news-and-insights/press-releases/2022/pif-launches-saudi-coffee/.
8. Saudi Coffee Company (2025, September 10). PIF Launches the Saudi Coffee Company. Available online: https://www.saudicoffee.com/news.
9. Ministry of Environment, Water and Agriculture (2025, September 10). Strategic Partnerships to Support Coffee Cultivation in Jazan, Al-Baha, and Aseer, Available online: https://www.mewa.gov.sa/en/MediaCenter/News/Pages/engnews2226.aspx.
10. Food and Agriculture Organization, and Ministry of Environment, Water and Agriculture (2021). Catalogue of Coffee Diseases, Pests and Weeds in the Kingdom of Saudi Arabia.
11. First Occurrence of Coffee Leaf Rust Caused by Hemileia vastatrix on Coffee in Saudi Arabia10.3390/microbiolres15010011 ↗
12. Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions10.1186/s40537-021-00444-8 ↗
13. Enhanced Pest and Disease Detection in Agriculture Using Deep Learning-Enabled Drones10.56578/ataiml030101 ↗
14. Ali, M.H., Mahmud, T., Aziz, M.T., Aziz, M.F.B.A., Hossain, M.S., and Andersson, K. (2024). Leveraging Transfer Learning for Efficient Classification of Coffee Leaf Diseases. Proceedings of the 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kamand, India, 24–28 June 2024, IEEE.10.1109/ICCCNT61001.2024.10725973 ↗
15. Deep Learning for Coffee Leaf Diseases Detection in Precision Agriculture10.61356/j.oia.2024.1292 ↗
16. Paulos, E.B., and Woldeyohannis, M.M. (2022). Detection and Classification of Coffee Leaf Disease Using Deep Learning. Proceedings of the 2022 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), IEEE.10.1109/ICT4DA56482.2022.9971300 ↗
17. Hitimana, E., Sinayobye, O.J., Ufitinema, J.C., Mukamugema, J., Rwibasira, P., Murangira, T., Masabo, E., Chepkwony, L.C., Kamikazi, M.C.A., and Uwera, J.A.U. (2023). An Intelligent System-Based Coffee Plant Leaf Disease Recognition Using Deep Learning on Rwandan Arabica Dataset. Technologies, 11.10.3390/technologies11050116 ↗
18. Coffee Plant Leaf Disease Detection for Digital Agriculture10.5753/jis.2024.3804 ↗
19. Novtahaning, D., Shah, H.A., and Kang, J.-M. (2022). Deep Learning Ensemble-Based Automated and High-Performing Recognition of Coffee Leaf Disease. Agriculture, 12.10.3390/agriculture12111909 ↗
20. Araújo, S.O., Peres, R.S., Ramalho, J.C., Lidon, F., and Barata, J. (2023). Machine Learning Applications in Agriculture: Current Trends, Challenges, and Future Perspectives. Agronomy, 13.10.3390/agronomy13122976 ↗
21. Girón-Morales, G., Alvarez-Huezo, E., Estrada-Peraza, E., and Rodriguez-Gallo, Y. (2024). Rust Detection on Coffee Crops Using Artificial Intelligence and Vegetation Indices. Proceedings of the 2024 IEEE Central America and Panama Student Conference (CONESCAPAN), IEEE.10.1109/CONESCAPAN62181.2024.10891078 ↗
22. Early Detection of Colletotrichum kahawae Disease in Coffee Cherry Based on Computer Vision Techniques
23. Revolutionizing Coffee Farming: A Mobile App with GPS-Enabled Reporting for Rapid and Accurate On-Site Detection of Coffee Leaf Diseases Using Integrated Deep Learning10.3390/software3020007 ↗
24. Kaushik, P., and Sharma, P. (2025). Automated Coffee Leaf Disease Detection Using Convolutional Neural Networks: An EfficientNet-Based Approach. Proceedings of the 2025 International Conference on Automation and Computation (AUTOCOM), IEEE.10.1109/AUTOCOM64127.2025.10956473 ↗
25. Chaubey, H.K., Arelli, S., Raj, A., and Naik, N.S. (2023). Coffee Leaf Disease and Severity Prediction Using Deep Learning. Proceedings of TENCON 2023—2023 IEEE Region 10 Conference, IEEE.10.1109/TENCON58879.2023.10322425 ↗
26. DeepEMPR: Coffee Leaf Disease Detection with Deep Learning and Enhanced Multivariance Product Representation10.7717/peerj-cs.2406 ↗
27. Carneiro, A.L.C., Silva, L.B., and Faulin, M.S.A.R. (2021). Artificial Intelligence for Detection and Quantification of Rust and Leaf Miner in Coffee Crop. arXiv, Available online: https://arxiv.org/abs/2103.11241.
28. Marcos, A.P., Silva Rodovalho, N.L., and Backes, A.R. (2019). Coffee Leaf Rust Detection Using Convolutional Neural Network. Proceedings of the 2019 XV Workshop de Visão Computacional (WVC), IEEE.10.1109/WVC.2019.8876931 ↗
29. Jepkoech, J., Kenduiywo, B., Mugo, D., and Chebet, E. (2021). JMuBEN Dataset. Mendeley Data, V1.
30. Jepkoech, J., Mugo, D., Kenduiywo, B., and Chebet, E. (2021). JMuBEN2 Dataset. Mendeley Data, V1.
31. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA. Available online: https://arxiv.org/abs/1412.6980.
32. Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017). Focal Loss for Dense Object Detection. Proceedings of ICCV 2017, IEEE.10.1109/ICCV.2017.324 ↗