A Review of Farmer-Centric Accessibility And Usability in Plant Disease Detection Technologies

Plant disease detection has changed a lot because of technologies. Machine learning, better imaging, spectroscopy, molecular tools, biosensors, the Internet of Things, drones, and mobile and edge computing have all played a part. These tools have helped improve how we find plant diseases. They allow for classification, faster detection, automation, and the ability to monitor crops over large areas [1]–[7], [9]–[15], [17]–[30]. Even with all these advances, the real question is whether these tools are actually useful for farmers. Some systems can detect diseases early and with high accuracy. They often need expensive equipment, lab setups, stable internet, strong computing power, or technical knowledge. That makes them hard to use in farm settings [8]–[14], [16], [19]–[25], [30]. So just because a method works well in a lab doesn’t mean it works well in the field. Future research in plant disease detection should not aim to build better tools but also make sure the tools work in real farming environments. We need testing in actual field systems that use fewer resources and involve farmers when testing usability. It's also important to connect disease detection with measuring how bad the disease is and giving advice on what to do. A detection system is only truly successful if it helps a farmer understand the disease, make a decision, and take the right steps. In the end, success is not about accuracy. It’s about how the system supports the farmer in solving the problem.

[1] V. S. Dhaka, N. Kundu, G. Rani, E. Zumpano, and E. Vocaturo, “Role of Internet of Things and Deep Learning Techniques in Plant Disease Detection and Classification: A Focused Review,” Sensors, vol. 23, no. 18, Art. no. 7877, 2023, doi: 10.3390/s23187877. [2]   L. Li, S. Zhang, and B. Wang, “Plant Disease Detection and Classification by Deep Learning—A Review,” IEEE Access, 2021, doi: 10.1109/ACCESS.2021.3069646. [3]  B. Ramana Reddy, G. Kalnoor, D. Mudigonda, and S. K. Reddy Palagiri, “Deep Learning Based Mobile Application for Automated Plant Disease Detection,” IEEE Access , 2 0 2 5 , d o i : 1 0 . 11 0 9 / ACCESS.2025.3581099. [4]   S. Nigam and R. Jain, “Plant disease identification using Deep Learning: A review,” Indian Journal of Agricultural Sciences, vol. 90, no. 2, pp. 249–257, 2020. [5]  M. Xu, J. E. Park, J. Lee, J. Yang, and S. Yoon, “Plant Disease Recognition Datasets in the Age of Deep Learning: Challenges and Opportunities,” arXiv preprint arXiv:2312.07905, 2023. [6]  T. D. Singh and R. Bharti, “Detection and Classification of Plant Diseases in Crops (Solanum lycopersicum) due to Pests Using Deep Learning Techniques: A Review,” Asian Journal of Computer Science and Technology, vol. 12, no. 2, pp. 39–47, 2023. [7]   A. Saletnik, B. Saletnik, G. Zaguła, and C. Puchalski, “Raman Spectroscopy for Plant Disease Detection in Next-Generation Agriculture” Sustainability, vol. 16, Art. no. 5474, 2024, doi: 10.3390/su16135474. [8]  M. S. Rahman, M. S. Ali, M. H. Kabir, and M. M. Alam, “Problem Faced by the Farmers in Using Information Communication Technology Tools for Receiving Rice Production Information,” Asian Journal of Agricultural Extension, Economics & Sociology, vol. 41, no. 10, pp. 443–451, 2023, doi: 10.9734/AJAEES/2023/v41i102188. [9] A. F. Cheshkova, “A review of hyperspectral image analysis techniques for plant disease detection and identification,” Vavilov Journal of Genetics and Breeding, vol. 26, no. 2, pp. 202–213, 2022, doi: 10.18699/ VJGB-22-25. [10] A. Chaturvedi, D. Tripathi, and R. Ranjan, “Nano-enabled biosensors in early detection of plant diseases,” Frontiers in Nanotechnology, vol. 7, Art. no. 1545792, 2025, doi: 10.3389/fnano.2025.1545792.