Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178065,
        author = {Dr. Sasidhar Babu Suvanam and M. Abhishek and K. Srihari and MD. Sailesh and Tushar Sagore},
        title = {A Machine Learning Approach Towards Plant Disease Prediction and Control Monitoring System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {3826-3838},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178065},
        abstract = {Crop diseases represent a persistent threat to global agricultural productivity, causing significant yield losses and economic challenges, particularly for smallholder farmers in resource-scarce regions. Conventional disease identification, reliant on manual observation by experts, is labor-intensive, prone to errors, and often inaccessible to farmers in remote areas. This research presents an innovative, AI-driven platform that transforms crop disease management by integrating real-time detection, intelligent diagnostic support, and geospatial resource localization into a cohesive, farmer-centric solution. At its core, the system employs the advanced YOLOv8 convolutional neural network, which achieves high-precision identification of diseases in rice, wheat, and maize crops. Trained on a meticulously curated dataset from Roboflow, the model incorporates data augmentation to ensure robustness across varying environmental conditions, such as lighting and occlusion, delivering over 90% detection accuracy with rapid inference speeds suitable for field applications.
Complementing the detection module, a conversational AI chatbot powered by Google Gemini Flash provides farmers with in-depth disease insights, including causes, tailored treatment options, and preventive measures. The chatbot’s lightweight architecture ensures low-latency responses, making it ideal for rural settings with limited connectivity, while its intuitive interface empowers users with minimal technical expertise to access expert-level guidance. A geospatial mapping component, utilizing OpenStreetMap’s Overpass and Nominatim APIs, enables farmers to locate nearby plant nurseries and pesticide suppliers within a 5km radius, bridging the gap between diagnosis and actionable intervention. Visualized through interactive Folium maps, this feature ensures prompt access to critical resources, enhancing disease management efficiency.
Hosted on a Streamlit-based web application, the platform operates seamlessly on standard mobile or desktop devices, eliminating the need for expensive hardware like drones or high-end servers. This accessibility distinguishes the system from existing solutions, which often focus solely on detection without integrating advisory or resource-mapping capabilities. By unifying computer vision, natural language processing, and geospatial analytics, the platform offers a scalable, end-to-end tool that empowers farmers to make informed, timely decisions. Rigorous testing validated the system’s performance, with the YOLOv8 model demonstrating robust generalization across diverse crop conditions and the chatbot achieving a 98% relevance score across varied queries. The mapping feature successfully retrieved accurate shop locations, further enhancing its practical utility.
This work advances precision agriculture by addressing key gaps in scalability, affordability, and integration, aligning with global sustainability and food security objectives. It democratizes access to advanced agricultural technology, enabling small-scale farmers to mitigate crop losses and improve livelihoods. Future enhancements will expand the system’s crop and disease coverage, incorporate offline inference capabilities for remote regions, and integrate real-time environmental data, such as weather and soil conditions, to enable predictive disease modeling. By fostering data-driven, sustainable farming practices, this platform sets a foundation for scalable agricultural innovation, with potential applications in national and global farming ecosystems.},
        keywords = {Crop Disease Detection, YOLOv8, Conversational AI, Geospatial Mapping, Precision Farming, Sustainable Agriculture},
        month = {May},
        }