Copyright © 2025 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{181990,
        author = {Narayanan Subbiah},
        title = {OPTIMIZING CROP YIELD FORECASTING USING HYBRID MACHINE LEARNING MODELS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {287-292},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181990},
        abstract = {Crop yield prediction using machine learning enhances decision-making in agriculture by providing accurate and timely forecasts. This study utilized datasets including climate data, soil properties, satellite imagery, and historical yields. Four models were evaluated: Random Forest, XGBoost, Decision Tree, and Linear Regression. Random Forest Regression achieved the best performance with an R² of 0.97, MAE of 5,412, and RMSE of 12,450.XGBoost followed with an R² of 0.87, showing potential for improvement through hyperparameter tuning. Decision Tree Regression showed overfitting, with perfect training R² but a slightly lower test R² of 0.95.Linear Regression underperformed with an R² of 0.67, failing to capture complex patterns. Remote sensing and advanced analytics enhanced prediction accuracy and real-time monitoring. All models faced issues with infinite MAPE due to zero-yield values, highlighting the need for data cleaning. Random Forest proved to be the most reliable model, promoting efficient and sustainable agricultural practices.},
        keywords = {Machine learning, XGBoost,Mean Absolute Percentage Error, Regression},
        month = {July},
        }