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{202895,
        author = {Athulya KV and ABI VARSHINI K and S SALMA and S SRINILA and SHADHANA G V and V GNANASEKAR and R SUGANESHWARAN},
        title = {KisanKrishi AI: An Intelligent Agricultural Decision-Support Framework Utilizing Deep Learning for Crop Health Management},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {9581-9588},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202895},
        abstract = {Semi-arid agricultural regions face challenges such as crop diseases, inefficient resource use, and lack of real-time guidance. Pearl millet (Kambu), widely grown in Tamil Nadu, is highly susceptible to diseases that reduce yield and farmer income. Traditional methods rely on manual inspection, which is time-consuming and error-prone.
This study presents KisanKrishi AI, an intelligent farming system that provides real-time decision support using artificial intelligence. It employs EfficientNetV2S for crop disease detection, Random Forest and XGBoost for soil analysis, and LSTM and ARIMA models for price forecasting. The system is optimized with TensorFlow Lite for offline use and implemented through a Flutter mobile app integrated with FastAPI and PostgreSQL.
Results show a high accuracy of around 95% with low latency, making it suitable for real-world use. The system improves productivity, reduces costs, and supports data-driven sustainable farming.},
        keywords = {Intelligent Agriculture, Deep Learning, EfficientNetV2S, TensorFlow Lite, Plant Disease Detection, Precision Farming, Machine Learning},
        month = {May},
        }