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{190175,
        author = {P Bharath Krishna and K Gajalakshmi},
        title = {Smart Agriculture through Machine Learning - a Deployable Model for Multi-Aspect Farm Advisory},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {3236-3242},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190175},
        abstract = {Smart agriculture is increasingly essential in contemporary farming due to challenges such as climate fluctuations, volatile market conditions, and suboptimal use of agricultural resources, all of which negatively impact productivity. This work introduces a practical and implementable machine learning–driven framework titled “Smart Agriculture through Machine Learning: A Multi-Aspect Farm Advisory System.” The proposed system consolidates four key functionalities—crop recommendation, yield estimation, market price prediction, and fertilizer advisory—within a single decision-support platform. Each component employs data-centric machine learning techniques trained on soil properties, weather patterns, historical pricing data, and crop-related attributes to generate accurate and actionable recommendations for farmers and other stakeholders.
The solution is deployed using a lightweight and scalable Flask-based web application, ensuring broad accessibility across devices without requiring local software installation. Through the integration of predictive modelling, real-time analysis, and user-friendly visual outputs, the system seeks to enhance farm management, minimize uncertainty, and promote data-informed agricultural decision-making. Experimental results indicate that integrating multiple advisory modules improves the reliability of recommendations and offers a useful resource for farmers, researchers, and policymakers. The developed prototype also provides a strong basis for future advancements, including precision farming applications and real-time monitoring using IoT technologies.},
        keywords = {Crop Recommendation, Fertilizer Recommendation, Crop yield prediction, Crop Price Prediction, logistic regression, soil, recommendation.},
        month = {January},
        }