Vol. 337 No. 7 (2026)
DOI https://doi.org/10.18799/24131830/2026/7/5132
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
Keywords:
hybrid, machine learning models, advanced statistical modelling, mean squared error, climate data analysis, energy transition, sustainable development goal 7 (SDG 7)
References:
1. Sher F., Curnick O., Azizan M.T. Sustainable conversion of renewable energy sources. Sustainability, 2021, vol. 13, no. 5, Art. 2940. DOI: 10.3390/su13052940.
2. Kumar D.S., Yagli G.M., Kashyap M., Srinivasan D. Solar irradiance resource and forecasting: a comprehensive review. IET Renewable Power Generation, 2020, vol. 14, no. 10, pp. 1641–1656. DOI: 10.1049/iet-rpg.2019.1227.
3. Akhter M.N., Mekhilef S., Mokhlis H., Shah N.M. Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques. IET Renewable Power Generation, 2019, vol. 13, no. 7, pp. 1009–1023. DOI: 10.1049/iet-rpg.2018.5649.
4. Sobri S., Koohi-Kamali S., Rahim N.A. Solar photovoltaic generation forecasting methods: a review. Energy Conversion and Management, 2018, vol. 156, pp. 459–497. DOI: 10.1016/j.enconman.2017.11.019.
5. Hengl T., Nussbaum M., Wright M.N., Heuvelink G.B.M., Gräler B. Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ, 2018, vol. 6, Art. e5518. DOI: 10.7717/peerj.5518.
6. Khalyasmaa A., Eroshenko S.A., Chakravarthy T.P., Gasi V.G., Bollu S.K.Y., Caire R., Atluri S.K.R., Karrolla S. Prediction of solar power generation based on random forest regressor model. 2019 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON). Novosibirsk, Russia, IEEE, 2019. pp. 780–785. DOI: 10.1109/SIBIRCON48586.2019.8958063.
7. Fonti V., Belitser E. Feature selection using LASSO. VU Amsterdam Research Paper in Business Analytics, 2017, vol. 30, pp. 1–25.
8. Fox E.W., Ver Hoef J.M., Olsen A.R. Comparing spatial regression to random forests for large environmental data sets. PLOS ONE, 2020, vol. 15, no. 3, Art. e0229509. DOI: 10.1371/journal.pone.0229509.
9. Etukudor C., Couraud B., Robu V., Früh W.-G., Flynn D., Okereke C. Automated negotiation for peer-to-peer electricity trading in local energy markets. Energies, 2020, vol. 13, no. 4, Art. 920. DOI: 10.3390/en13040920.
10. Akpuluma D.A., Yurchenko A.V. Advancing solar irradiation prediction in extreme climates: a LASSO regression analysis in Tomsk. Proceedings of International Conference on Applied Innovation in IT, 2024, vol. 12, no. 1, pp. 257–263. DOI: 10.25673/115712.
11. Akpuluma D.A., Abam J.I., Williams C.A. Enhancing predictive accuracy in environmental data analysis: a hybrid LASSO–RFR approach for climatic analysis in Siberia. Prospects of Fundamental Sciences Development. Proc. of the XXI International Conference of Students and Young Scientists. Tomsk, April 23–26, 2024. Vol. 3: Mathematics. Tomsk, Tomsk Polytechnic University Publ., 2024. pp. 23–25.
12. Ludwig N., Feuerriegel S., Neumann D. Putting Big Data analytics to work: feature selection for forecasting electricity prices using the LASSO and random forests. Journal of Decision Systems, 2015, vol. 24, no. 1, pp. 19–36. DOI: 10.1080/12460125.2015.994290.
13. Akpuluma D., Yurchenko A.V., Firoz N., Abam J.I., Iheji V.N., Belan B.D. Enhanced forecasting of PV power output using LSTM integrated with LASSO-RFR hybrid models in extreme weather conditions. 2024 IEEE 3rd International Conference on Problems of Informatics, Electronics and Radio Engineering (PIERE). Novosibirsk, Russian Federation, IEEE, 2024. pp. 780–785. DOI: 10.1109/PIERE62470.2024.10805041.
14. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay É. Scikit-learn: machine learning in Python. Journal of Machine Learning Research, 2011, vol. 12, pp. 2825–2830.
15. Gaunov S.R., Baimuradov U.G., Sitnikov S.Yu. Machine learning in Python: using TensorFlow and Scikit-learn libraries. Economics and Management: Problems, Solutions, 2024, vol. 12, no. 8, pp. 72–81. (In Russ.) DOI: 10.36871/ek.up.p.r.2024.12.08.009.
16. Brown M.G.L., Peterson M.G., Tezaur I.K., Peterson K.J., Bull D.L. Random forest regression feature importance for climate impact pathway detection. Journal of Computational and Applied Mathematics, 2025, vol. 464, Art. 116479. DOI: 10.1016/j.cam.2024.116479.
17. Atiea M.A., Shaheen A.M., Alassaf A., Alsaleh I. Enhanced solar power prediction models with integrating meteorological data toward sustainable energy forecasting. International Journal of Energy Research, 2024, vol. 2024, no. 1, Art. 8022398. DOI: 10.1155/er/8022398.
18. Asiedu S.T., Nyarko F.K.A., Boahen S., Effah F.B., Asaaga B.A. Machine learning forecasting of solar PV production using single and hybrid models over different time horizons. Heliyon, 2024, vol. 10, no. 7, Art. e28898. DOI: 10.1016/j.heliyon.2024.e28898.
19. El-Shahat D., Tolba A., Abouhawwash M., Abdel-Basset M. Machine learning and deep learning models based grid search cross validation for short-term solar irradiance forecasting. Journal of Big Data, 2024, vol. 11, no. 1, Art. 134. DOI: 10.1186/s40537-024-00991-w.
20. Khan S., Mazhar T., Khan M.A., Shahzad T., Ahmad W., Bibi A., Saeed M.M., Hamam H. Comparative analysis of deep neural network architectures for renewable energy forecasting: enhancing accuracy with meteorological and time-based features. Discover Sustainability, 2024, vol. 5, no. 1, Art. 533. DOI: 10.1007/s43621-024-00783-5.
21. Gunning D., Aha D.W. DARPA’s Explainable Artificial Intelligence (XAI) Program. AI Magazine, 2019, vol. 40, no. 2, pp. 44–58. DOI: 10.1609/aimag.v40i2.2850.
22. Teixeira B., Carvalhais L., Pinto T., Vale Z. Application of XAI-based framework for PV energy generation forecasting. 2023 IEEE Conference on Artificial Intelligence (CAI). Santa Clara, CA, USA, IEEE, 2023. pp. 67–68. DOI: 10.1109/CAI54212.2023.00036.
