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{182060,
        author = {Ayush Uday Bhole and Prashant Kulkarni and Shubhangi P. Tidake},
        title = {Solar Radiation Prediction Using Machine Learning and Feature Engineering: A Comparative Analysis with AutoML Optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {614-620},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182060},
        abstract = {Accurate prediction of solar radiation is essential for optimizing renewable energy generation. This study utilizes machine learning models such as XGBoost, Random Forest, LightGBM, Neural Networks and stacked ensemble model to predict solar radiation. These models are trained and evaluated using historical weather data, including meteorological characteristics such as temperature, humidity, wind speed, and surface pressure.
To improve prediction accuracy, the dataset is enhanced with manually engineered features, including rolling averages, lag values, and additional time-based variables such as day and month, thereby enabling the models to more effectively capture complex temporal patterns in solar radiation dynamics.
Performance metrics such as R² (coefficient of determination), MAE (mean absolute error), MSE (mean squared error), and RMSE (root mean square error) are used to evaluate the effectiveness of the model. The goal of this research is to improve the accuracy of solar radiation prediction and contribute to the advancement of renewable energy systems and sustainable energy planning.},
        keywords = {Cross-Validation, Solar radiation, Machine Learning, Neural Network,  Automl.},
        month = {July},
        }