SavedAdd your journal

Journals / Turkish Journal of Forecasting / 2026 / Volume: 10 Issue: 1

Wavelet-Enhanced Machine Learning Models for Hourly Solar Irradiance Forecasting

Gbadebo İsmaila Olatona(Osun State University)0000-0001-9415-6265
Shuaib Adisa(Osun State University)0000-0001-9389-1874
Muyideen Olalekan Lawal(Osun State University)0000-0001-8705-0569
Saheed Adewinbi(Osun State University)0000-0002-1057-2462
Sherifdeen Mosebolatan Oyedokun(Osun State University)0000-0001-9013-5512
Pages
—
Publication Date
2026-03-12
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Results showed that MLP consistently achieved the best predictive accuracy with 12.9494 MAE, 339.81 MSE, 18.43 RMSE, -1.86 MBE and 0.9945 R2, while RF and GBR also performed competitively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Forecasting solar irradiance accurately is critical for optimizing renewable energy systems.
📊
Key Findings & Data:The models were trained with 70% and assessed with 30% of the dataset with five statistical metrics.
💡
Conclusion & Impact:Results showed that MLP consistently achieved the best predictive accuracy with 12.9494 MAE, 339.81 MSE, 18.43 RMSE, -1.86 MBE and 0.9945 R2, while RF and GBR also performed competitively.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Forecasting · Machine Learning · Solar Irradiance

Abstract

Forecasting solar irradiance accurately is critical for optimizing renewable energy systems. In this study CWT was applied to solar irradiance for time frequency features. The CWT features, meteorological data and lag solar irradiance data were used to train seven ML models. The models were trained with 70% and assessed with 30% of the dataset with five statistical metrics. Results showed that MLP consistently achieved the best predictive accuracy with 12.9494 MAE, 339.81 MSE, 18.43 RMSE, -1.86 MBE and 0.9945 R2, while RF and GBR also performed competitively. Also, kNN with 32.71 MAE, 2115 MSE, 45.99 RMSE, -5.03 MBE and 0.97 R2 exhibited the weakest performance. These results show that CWT coefficient statistical features allow model like MLP, RF and GBR to capture irradiance variability more effectively.

🔖

Cite This Article

Olatona, G. İ., Adisa, S., Lawal, M. O., Adewinbi, S., Oyedokun, S. M. (2026). Wavelet-Enhanced Machine Learning Models for Hourly Solar Irradiance Forecasting. Turkish Journal of Forecasting, Volume: 10 Issue: 1. https://doi.org/10.34110/forecasting.1855955

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (26)

  1. Ağbulut, Ü., Gürel, A. E., & Biçen, Y. (2020). Prediction of daily global solar radiation using different machine learning algorithms: Evaluation and comparison. Renewable and Sustainable Energy Reviews, 135, 110114. https://doi.org/10.1016/j.rser.2020.110114
  2. Almaghrabi, S., Rana, M., Hamilton, M., & Rahaman, M. S. (2022). Solar power time series forecasting utilising wavelet coefficients. Neurocomputing, 508, 182–207. https://doi.org/10.1016/j.neucom.2022.08.016
  3. Alonso-Montesinos, J., & Batlles, F. (2015). Solar radiation forecasting in the short- and medium-term under all sky conditions. Energy, 83, 387–393. https://doi.org/10.1016/j.energy.2015.02.036
  4. Amer, A. A., Ravana, S. D., & Habeeb, R. a. A. (2025). Effective k-nearest neighbor models for data classification enhancement. Journal of Big Data, 12(1). https://doi.org/10.1186/s40537-025-01137-2
  5. Badaoui, H. E., Abdallaoui, A., & Chabaa, S. (2013). Using MLP neural networks for predicting global solar radiation. The International Journal of Engineering and Science, Volume 2(Issue12), 48–56. Benali, L., Notton, G., Fouilloy, A., Voyant, C., & Dizene, R. (2018). Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components. Renewable Energy, 132, 871–884. Caruana, R., & Niculescu-Mizil, A. (2006). An empirical comparison of supervised learning algorithms. 23rd International Conference on Machine Learning, 161–168. https://doi.org/10.1145/1143844.1143865 Chodakowska, E., Nazarko, J., Nazarko, Ł., & Rabayah, H. S. (2024). Solar Radiation Forecasting: A Systematic Meta-Review of Current Methods and Emerging Trends. Energies, 17(13), 3156. https://doi.org/10.3390/en17133156
  6. El-Shahat, D., Tolba, A., Abouhawwash, M., & Abdel-Basset, M. (2024). Machine learning and deep learning models-based grid search cross validation for short-term solar irradiance forecasting. Journal of Big Data, 11(1). https://doi.org/10.1186/s40537-024-00991-w
  7. Erbs, D., Klein, S., & Duffie, J. (1982). Estimation of the diffuse radiation fraction for hourly, daily and monthly-average global radiation. Solar Energy, 28(4), 293–302. https://doi.org/10.1016/0038-092x(82)90302-4
  8. Esposito, E., Leanza, G., & Di Francia, G. (2024). Comparative analysis of Ground-Based solar irradiance measurements and Copernicus satellite observations. Energies, 17(7), 1579. https://doi.org/10.3390/en17071579
  9. Falayi E. O, Adewole A. T., Adelaja A. D., Roy-Layinde T. O. (2020), “Wavelet spectrum analysis of Air temperature and Relative humidity in some selected stations in Nigeria”, Dutse Journal of Pure and Applied Sciences, vol. 6, no. 1, pp. 47-59.
  10. Khanlari, A., Sözen, A., Afshari, F., Şirin, C., Tuncer, A. D., & Gungor, A. (2019a). Drying municipal sewage sludge with v-groove triple-pass and quadruple-pass solar air heaters along with testing of a solar absorber drying chamber. The Science of the Total Environment, 709, 136198. https://doi.org/10.1016/j.scitotenv.2019.136198
  11. Khanlari, A., Sözen, A., Şirin, C., Tuncer, A. D., & Gungor, A. (2019b). Performance enhancement of a greenhouse dryer: Analysis of a cost-effective alternative solar air heater. Journal of Cleaner Production, 251, 119672. https://doi.org/10.1016/j.jclepro.2019.119672
  12. Menze, B. H., Kelm, B. M., Masuch, R., Himmelreich, U., Bachert, P., Petrich, W., & Hamprecht, F. A. (2009). A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics, 10(1). https://doi.org/10.1186/1471-2105-10-213
  13. Mohammadi, K., Shamshirband, S., Anisi, M. H., Alam, K. A., & Petković, D. (2014). Support vector regression based prediction of global solar radiation on a horizontal surface. Energy Conversion and Management, 91, 433–441. https://doi.org/10.1016/j.enconman.2014.12.015
  14. Orgill, J., & Hollands, K. (1977). Correlation equation for hourly diffuse radiation on a horizontal surface. Solar Energy, 19(4), 357–359. https://doi.org/10.1016/0038-092x(77)90006-8
  15. Priya, K. S. (2021). Linear Regression Algorithm in Machine Learning through MATLAB. International Journal for Research in Applied Science and Engineering Technology, 9(12), 989–995. https://doi.org/10.22214/ijraset.2021.39410
  16. Reindl, D., Beckman, W., & Duffie, J. (1990). Diffuse fraction correlations. Solar Energy, 45(1), 1–7. https://doi.org/10.1016/0038-092x(90)90060-p
  17. Sananmuang, T., Mankong, K., & Chokeshaiusaha, K. (2024). Multilayer perceptron and support vector regression models for feline parturition date prediction. Heliyon, 10(6), e27992. https://doi.org/10.1016/j.heliyon.2024.e27992
  18. Sarica, A., Cerasa, A., & Quattrone, A. (2017). Random Forest Algorithm for the Classification of neuroimaging data in Alzheimer’s Disease: a Systematic review. Frontiers in Aging Neuroscience, 9. https://doi.org/10.3389/fnagi.2017.00329
  19. Singla, P., Duhan, M., & Saroha, S. (2021). An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network. Earth Science Informatics, 15(1), 291–306. https://doi.org/10.1007/s12145-021-00723-1
  20. Tandon, A., Awasthi, A., Pattnayak, K. C., Tandon, A., Choudhury, T., & Kotecha, K. (2025). Machine learning-driven solar irradiance prediction: advancing renewable energy in Rajasthan. Deleted Journal, 7(2). https://doi.org/10.1007/s42452-025-06490-8
  21. Tasci, E., & Onan, A. (2017). K-En Yakın Komşu Algoritması Parametrelerinin Sınıflandırma Performansı Üzerine Etkisinin İncelenmesi.
  22. Torrence, C., and Compo, G.P. (1998). A Practical Guide to Wavelet Analysis. Bulletin of the American Meteorological Society, 79: 61–78.
  23. Uday kiran, (2018). Usage of neural networks in communication links with structural inverted vee antenna, International journal of engineering Research and applications (IJERA), vol.8, no.9, 2018, pp. 65-69.
  24. Yin, S., & Liu, H. (2022). Wind power prediction based on outlier correction, ensemble reinforcement learning, and residual correction. Energy, 250, 123857. https://doi.org/10.1016/j.energy.2022.123857
  25. Zafar, R., Vu, B. H., Husein, M., & Chung, I. (2021). Day-Ahead Solar Irradiance Forecasting Using Hybrid Recurrent Neural Network with Weather Classification for Power System Scheduling. Applied Sciences, 11(15), 6738. https://doi.org/10.3390/app11156738
  26. Zhang, B., Ren, H., Huang, G., Cheng, Y., & Hu, C. (2019). Predicting blood pressure from physiological index data using the SVR algorithm. BMC Bioinformatics, 20(1). https://doi.org/10.1186/s12859-019-2667-y