FarmAssist AI: An Intelligent Web-Based Platform for Plant Disease Detection and Advisory Support Using Deep Learning

This paper presented FarmAssist AI, an end-to-end intelligent web platform integrating MobileNetV2-based plant disease detection with  a structured natural language advisory module for farmer guidance. The system achieves 88.4% top-1 and 96.2% top-3 classification accuracy on the PlantVillage dataset, with an  average end-to-end inference latency of 1.34 seconds, demonstrating both diagnostic efficacy and practical  deployability under real-world network conditions. By unifying visual disease diagnostics and interactive advisory support within a single, accessible web interface requiring no application installation or specialised hardware, FarmAssist AI addresses a critical and previously unmet gap in the agricultural technology landscape. The platform has the potential to democratise expert-grade agronomic knowledge, enabling timely disease intervention, reducing excessive and inappropriate chemical use, and ultimately safeguarding the livelihoods of smallholder farmers across India and other agricultural economies. The authors believe this work contributes a meaningful and practical step toward AI-powered precision agriculture and hope it inspires further interdisciplinary research at the intersection of deep learning, human-computer interaction, and rural development.

[1] 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. [2] D. Hughes and M. Salathé, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” arXiv preprint arXiv:1511.08060, 2015. [3] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. [4] A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017. [5] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proc. IEEE CVPR, 2018, pp. 4510–4520. [6] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, 2019. [7] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [8] A. K. Rangarajan, R. Purushothaman, and A. Ramesh, “Tomato crop disease classification using pre-trained deep learning algorithm,” Procedia Computer Science, vol. 133, pp. 1040–1047, 2018. [9] TensorFlow Development Team, “TensorFlow: Large-scale machine learning on heterogeneous systems,” 2023. [Online]. Available: https://www.tensorflow.org [10] Facebook Open Source, “React—A JavaScript library for building user interfaces,” 2023. [Online]. Available: https://reactjs.org