AgriMindEdge: An Explainable Edge AI-Based Mobile System

AgriMindEdge set out to answer one question: can a farmer in a village with no internet get AI-powered crop disease diagnosis on their phone? The answer is yes. The system achieves 95.8% accuracy for plant disease detection and 92.4% for soil classification, with results in 87 milliseconds, running entirely offline on a standard Android device. The Score-CAM explainability module ensures the farmer does not have to take the AI's word for it — they can see exactly what the model looked at. Live testing on real field photographs confirmed that these numbers hold outside the lab.   The broader point is this: the gap between what AI can do in a research paper and what actually reaches a farmer in rural India is enormous. AgriMindEdge is one attempt to close that gap — not by building the most sophisticated model possible, but by building one that works under the actual constraints farmers face. No internet. Basic phone. No technical background. It works.

[1] FAO, "The State of Food and Agriculture 2023," FAO, Rome, Italy, 2023. [2] R. N. Strange and P. R. Scott, "Plant disease: A threat to global food security," Annual Review of Phytopathology, vol. 43, pp. 83–116, 2005. [3] S. P. Mohanty, D. P. Hughes, and M. Salathé, "Using deep learning for image-based plant disease detection," Frontiers in Plant Science, vol. 7, p. 1419, 2016. [4] K. P. Ferentinos, "Deep learning models for plant disease detection and diagnosis," Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. [5] S. Sladojevic et al., "Deep neural networks based recognition of plant diseases by leaf image classification," Computational Intelligence and Neuroscience, 2016. [6] W. Shi et al., "Edge computing: Vision and challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, 2016. [7] J. G. A. Barbedo, "Factors influencing the use of deep learning for plant disease recognition," Biosystems Engineering, vol. 172, pp. 84–91, 2018. [8] S. Ramesh and R. Vardhan, "Weather parameter integration for disease prediction," International Journal of Agricultural Information Systems, 2015. [9] R. Gopalan et al., "Lightweight CNN architectures for mobile edge deployment," Journal of Mobile Computing, vol. 12, no. 3, pp. 145–159, 2025. [10] A. Gani et al., "Multi-modal image fusion for plant disease classification," Computers and Electronics in Agriculture, 2025. [11] P. Upadhyay et al., "Weather-aware deep learning for crop disease prediction," Smart Agricultural Technology, 2025.