AI-Augmented Clear-Sky Algorithms for High-Granularity Solar Irradiance Modelling

Authors

DOI:

https://doi.org/10.70917/jcc-2026-009

Keywords:

Hybrid solar forecasting, Physics-informed machine learning, Clear-sky modelling;, Solar irradiance prediction, Atmospheric features, Performance forecasting

Abstract

Accurate short-term solar irradiance forecasting is important for reliable photovoltaic operation in regions affected by rapid cloud movement and atmospheric variability. However, clear-sky models cannot adequately respond to cloud-driven irradiance fluctuations, while purely data-driven models may suffer from weak physical consistency and reduced generalisability. The present study developed a physics-informed hybrid framework in which clear-sky irradiance was used as the physical baseline, while machine learning was employed to learn the residual atmospheric deviations caused by clouds, aerosols, moisture and near-surface meteorology. The proposed model was evaluated against persistence, clear-sky, AI-only and standalone Gated Recurrent Unit benchmark models using 10-min-ahead global horizontal irradiance prediction. During the Roodepoort summer test period, the hybrid model achieved an RMSE of 79 W/m2, MAE of 59 W/m2, MBE of −8 W/m2 and R2 of 0.91, corresponding to RMSE reductions of 32%, 44%, 27% and 18% when compared with the persistence, clear-sky, AI-only and Gated Recurrent Unit models, respectively. Furthermore, the model maintained seasonal RMSE values between 79 and 96 W/m2 without retraining, retained useful transferability at external Southern African Universities Radiometric Network stations with a mean external RMSE of 95.5 W/m2 and R2 of 0.86, and produced calibrated 95% prediction intervals with 93% empirical coverage. These findings showed that clear-sky constrained residual learning can improve deterministic accuracy, uncertainty reliability and seasonal robustness, thus supporting more reliable photovoltaic forecasting, grid integration and operational energy management under variable sky conditions.

Author Biographies

  • Dr. Kudzanayi Chiteka, University of South Africa, Science Campus, Florida, South Africa

    Postdoctoral research Fellow

    Department of Mechanical, Bioresources and Biomedical Engineering,

  • Prof Christopher Enweremadu, University of South Africa, Science Campus, Florida, South Africa

    Professor

    Department of Mechanical, Bioresources and Biomedical Engineering

References

Al-Ansary H., Al-Shehri A., Alaqel S., Djajadiwinata E., Saeed R. S., Saleh N. S., El-Leathy A., Danish S., Al-Suhaibani Z. “Economic and environmental assessment of a concentrated solar power system using sand as a heat transfer medium”, Green Technology & Innovation, 1, pp. 1–10, 2025. https://dx.doi.org/10.36922/GTI025290009

Assaf A. M., Haron H., Abdull Hamed H. N., Ghaleb F. A., Qasem S. N., Albarrak A. M. “A Review on Neural Network Based Models for Short Term Solar Irradiance Forecasting”, Applied Sciences, 13, pp. 8332, 2023. https://doi.org/10.3390/app13148332 .

Bai M., Fang Z., Tao S., Xiang S., Bian J., Xiang Y., Zhao P., Jin W., Weyn J. A., Dong H., Zhang B., Sun H., Thambiratnam K., Zhang Q., Sun H., Zhang X., Wu Q. “SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA”, arXiv, 2025. https://doi.org/10.48550/arXiv.2508.03590.

Bakhsh B. J., Cantino G. “European Hydrogen Valleys as catalysts for systemic decarbonization: A sustainability-oriented innovation and multi-level perspective analysis”, Green Technology & Innovation, 1, pp. 1–15, 2025. https://doi.org/10.36922/GTI025330012.

Brahma B., Wadhvani R. “Solar Irradiance Forecasting Based on Deep Learning Methodologies and Multi-Site Data”, Symmetry, 12, pp. 1830, 2020. https://doi.org/10.3390/sym12111830.

Chandel P., Roy L. “Solar Radiation Prediction Based on Hybrid Machine Learning Technique”. In Proceedings of the 2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS), pp. 418–24, 2023. https://doi.org/10.1109/ICTACS59847. 2023.10390492.

Chauvin R., Nou J., Eynard J., Thil S., Grieu S. “A new approach to the real-time assessment and intraday forecasting of clear-sky direct normal irradiance”, Solar Energy, 167, pp. 35–51, 2018. https://doi.org/10.1016/j.solener.2018.02.027.

Fernández-Peruchena C. M., Gastón M., Schroedter-Homscheidt M., Marco I. M., Casado-Rubio J. L., García-Moya J. A. “Increasing the temporal resolution of direct normal solar irradiance forecasted series”, AIP Conference Proceedings, 1850, pp. 140007, 2017. https://doi.org/10. 1063/1.4984515.

Gueymard C. A., Ruiz-Arias J. A. “Validation of direct normal irradiance predictions under arid conditions: A review of radiative models and their turbidity-dependent performance”, Renewable and Sustainable Energy Reviews, 45, pp. 379–96, 2015. https://doi.org/10.1016/j.rser.2015. 01.065.

Ineichen P., Perez R. “A new airmass independent formulation for the Linke turbidity coefficient”, Solar Energy, 73, pp. 151–57, 2002. https://doi.org/10.1016/S0038-092X(02)00045-2.

Kasten F., Young A. T. “Revised optical air mass tables and approximation formula”, Applied Optics, 28, pp. 4735–38, 1989. https://doi.org/10.1364/AO.28.004735.

Kreuwel F. P. M., Knap W., Schmeits M., Vilà-Guerau de Arellano J., van Heerwaarden C. C. “Forecasting day-ahead 1-minute irradiance variability from numerical weather predictions”, Solar Energy, 258, pp. 57–71, 2023. https://doi.org/10.1016/j.solener.2023.04.050.

Langella R., Proto D., Testa A. “Solar Radiation Forecasting, Accounting for Daily Variability”, Energies, 9, pp. 200, 2016. https://doi.org/10.3390/en9030200.

Mandal P., Reddy K. S. “Techno-economic assessment of solar power tower and solar parabolic dish system in India”, GD, 1, pp. 1–17, 2025. https://doi.org/10.17184/eac.9496.

Mathiesen P., Collier C., Kleissl J. “A high-resolution, cloud-assimilating numerical weather prediction model for solar irradiance forecasting”, Solar Energy, 92, pp. 47–61, 2013. https://doi.org/ 10.1016/j.solener.2013.02.018.

Mercier T. M., Rahman T., Sabet A. “Solar Irradiance Anticipative Transformer”. In Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2065–74, 2023. https://doi.org/10.1109/CVPRW59228.2023.00200.

Nallakaruppan M. K., Johnson J., Mapari S., Dasgupta A., Udgir S., Narmatha C. “Reliable and efficient solar radiation estimation with the insights of XAI”, Scientific Reports, 16, pp. 3549, 2026. https://doi.org/10.1038/s41598-025-33604-4.

Odejobi O. A., Alawode K. O., Lawal M. O. “Efficient Method For Forecasting Solar Irradiance - A Review”, Fudma Journal of Sciences, 8, pp. 285–98, 2024. https://doi.org/10.33003/fjs-2024-0806-2786.

Paletta Q., Terrén-Serrano G., Nie Y., Li B., Bieker J., Zhang W., Dubus L., Dev S., Feng C. “Advances in solar forecasting: Computer vision with deep learning”, Advances in Applied Energy, 11, pp. 100150, 2023. https://doi.org/10.1016/j.adapen.2023.100150.

Papachristopoulou K., Fountoulakis I., Bais A. F., Psiloglou B. E., Papadimitriou N., Raptis I.-P., Kazantzidis A., Kontoes C., Hatzaki M., Kazadzis S. “Effects of clouds and aerosols on downwelling surface solar irradiance nowcasting and short-term forecasting”, Atmospheric Measurement Techniques, 17, pp. 1851–77, 2024. https://doi.org/10.5194/amt-17-1851-2024.

Peiró-Signes A., García-Díaz J. C., Peiró-Signes A. “A Comparative Study of Statistical and Machine Learning Methods for Solar Irradiance Forecasting Using the Folsom PLC Dataset”, Preprints, 2025. https://doi.org/10.20944/preprints202506.0827.v1.

Pereira S., Canhoto P., Salgado R. “Development and assessment of artificial neural network models for direct normal solar irradiance forecasting using operational numerical weather prediction data”, Energy and AI, 15, pp. 100314, 2024. https://doi.org/10.1016/j.egyai.2023.100314.

Polo J., Zarzalejo L. F., Martín L., Navarro A. A., Marchante R. “Estimation of daily Linke turbidity factor by using global irradiance measurements at solar noon”, Solar Energy, 83, pp. 1177–85, 2009. https://doi.org/10.1016/j.solener.2009.01.018.

Razak T. R., Alaoui A. E., Jarimi H., Ul-Saufie A. Z., Ismail M. H., Fuzi M. F. M. “An AI-Based Hybrid Prophet–LSTM Model for Forecasting and Financial Optimisation in Sustainable Energy Grids”, AIFSC, 1, pp. 42–60, 2026. https://doi.org/10.65582/aifsc.2026.004.

Razak T. R., Ismail M. H., Darus M. Y., Jarimi H., Su Y. “Artificial Intelligence in Renewable Energy: A Systematic Review of Trends in Solar, Wind, and Smart Grid Applications”, Research and Reviews in Sustainability, 1, pp. 1–22, 2025. https://doi.org/10.5334/rss.6.

Richardson W., Cañadillas D., Moncada A., Guerrero-Lemus R., Shephard L., Vega-Avila R., Krishnaswami H. “Validation of All-Sky Imager Technology and Solar Irradiance Forecasting at Three Locations: NREL, San Antonio, Texas, and the Canary Islands, Spain”, Applied Sciences, 9, pp. 684, 2019. https://doi.org/10.3390/app9040684.

Riffat J., Reza Samaei S. “Recent Advances in Perovskite–Silicon Tandem Solar Cells: Progress, Challenges, and Pathways to Commercialisation”, EC, 1, pp. 113–26, 2025. https://doi.org/ 10.61552/EC.2025.009.

Salman D., Direkoglu C., Kusaf M., Fahrioglu M. “Hybrid deep learning models for time series forecasting of solar power”, Neural Computing and Applications, 36, pp. 9095–112, 2024. https://doi.org/10.1007/s00521-024-09558-5.

Sasaki J., Okada M., Utsunomiya K., Yamaguchi K. “A Physics-Informed Machine Learning Approach utilizing Multiband Satellite Data for Solar Irradiance Estimation”, arXiv, 2024. https://doi.org/10.48550/arXiv.2407.04283.

Siddiqa A., Rana N., Khan W. Z., Jeribi F., Tahir A. “Explaining solar forecasts with generative AI: A two-stage framework combining transformers and LLMs”, PLoS One, 20, pp. e0331516, 2025. https://doi.org/10.1371/journal.pone.0331516.

Sultana N., Tsutsumida N. “Combining Machine Learning with Physics-Based Mathematical Models for Near-Real-Time Clear-Sky Irradiance Prediction from Geostationary Satellite Imagery”. In Proceedings of the IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, pp. 7472–77, 2024. https://doi.org/10.1109/IGARSS53475.2024.10642113.

Thaker J., Höller R. “A Comparative Study of Time Series Forecasting of Solar Energy Based on Irradiance Classification”, Energies, 15, pp. 2837, 2022. https://doi.org/10.3390/en15082837.

Yan K., Shen H., Wang L., Zhou H., Xu M., Mo Y. “Short-Term Solar Irradiance Forecasting Based on a Hybrid Deep Learning Methodology”, Information, 11, pp. 32, 2020. https://doi.org/10.3390/ info11010032.

Yang D. “Choice of clear-sky model in solar forecasting”, Journal of Renewable and Sustainable Energy, 12, pp. 026101, 2020. https://doi.org/10.1063/5.0003495.

Zhuang Z., Wang H., Yu C. “Short-Term Irradiance Prediction Based on Transformer with Inverted Functional Area Structure”, Mathematics, 12, pp. 3213, 2024. https://doi.org/10.3390/ math12203213.

Downloads

Published

2026-06-29

Issue

Vol. 12 No. 1 (2026)

Section

Articles

License

Copyright (c) 2026 Dr. Kudzanayi Chiteka, Prof Christopher Enweremadu (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

AI-Augmented Clear-Sky Algorithms for High-Granularity Solar Irradiance Modelling. (2026). Journal of Climate Change, 12(1), 20. https://doi.org/10.70917/jcc-2026-009