Advancing SDG 7: a hybrid LASSO-RFR approach for enhanced solar energy forecasting in extreme weather conditions

Relevance. This study is focused on the use of hybrid models in environmental analytics, especially in areas like Siberia, which have highly dynamic short-term climate variables. Findings from the research further advance strategies for efficient and reliable renewable energy system operation by assisting decision-making, such that it improves their management and planning. The study introduces a novel application of a hybrid LASSO-RFR model to solar power prediction in extreme climatic conditions, offering a methodologically innovative and practical tool for improving the accuracy of renewable energy forecasts. This contributes to the broader goal of sustainable energy transition as outlined in SDG7. Aim. Enhance the predictive accuracy of solar power availability in Siberia. Develop a robust hybrid machine learning model with outstanding capabilities. Contribute to SDG7 through improved renewable energy forecasts. Methods. This system combines statistical modelling and machine learning techniques, utilising LASSO for feature selection and Random Forest Regression to handle complicated data relationships, thus tackling the challenges of non-linear, high-dimensional datasets in predicting solar power generation. A hybrid LASSO-RFR approach is employed to forecast solar power output. The method combines LASSO capability for feature reduction and RFR robustness in predictive accuracy. Data collected includes the ones on solar radiation, temperature, humidity, and wind speed in Tomsk and Siberia, spanning January 2021 to January 2024. Results and conclusions. The proposed hybrid model outperformed all individual models in terms of forecasting accuracy (in its optimal configuration, the MSE value was 0.006 with R-squared, 85.7%) and showed great potential to accurately predict solar power output which is essential for effectively coping with renewable energy source variability. For citation: Akpuluma D., Yurchenko A.V., Alkahderi L.A., Abam J.I., Firoz N., Tamunomiebi G., Belan B.D. Advancing SDG 7: a hybrid LASSO-RFR approach for enhanced solar energy forecasting in extreme weather conditions. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2026, vol. 337, no. 7, pp. 187-197. https://doi.org/10.18799/24131830/2026/7/5132