Advancing Prediction of Solar Irradiation using Hybrid XGBoost-LSTM Residual Learning
DOI:
https://doi.org/10.51601/ijse.v6i2.601Abstract
Accurate solar irradiation prediction is crucial for optimizing solar energy generation and supporting energy management systems. This study addresses the challenges of advancing the accuracy of solar irradiance forecasting by developing a Hybrid XGBoost-LSTM residual learning model, using historical solar radiation data from Lampung Selatan. The results highlight the capability of the Hybrid XGBoost-LSTM model as a powerful tool for forecasting solar irradiation, providing a more precise and reliable solution compared to standalone methods. This is demonstrated by the improvement in R² values from the standalone XGBoost predictions, increasing from 0.62 to 0.87 for the training data and from 0.50 to 0.77 on the testing datasets. In addition, the hybrid model demonstrates a decrease in RMSE and MAPE values when compared to standalone XGBoost model, with RMSE and MAPE dropping from 0.26 and 4.19% to 0.14 and 2.39% for the training dataset, and 0.32 and 5.28% to 0.23 and 3.70% for the testing dataset. These findings indicate that the inclusion of LSTM improves the model's ability to refine the residuals from XGBoost, capturing intricate temporal dynamics and fluctuations in solar irradiance data, making it a more reliable and effective tool for predicting solar energy potential in complex environments.
Downloads
References
[1] A. Q. Al-Shetwi, I. Z. Abidin, K. A. Mahafzah, and M. A. Hannan, “Feasibility of future transition to 100% renewable energy: Recent progress, policies, challenges, and perspectives,” J. Clean. Prod., vol. 478, p. 143942, Nov. 2024, doi: 10.1016/j.jclepro.2024.143942.
[2] N. T.R., P. V, S. A. Sridharan, and N. Ramrao, “Harnessing Renewable Energy at Kalasalingam Academy of Research and Education – A Role Model Case,” Journal of Sustainability Perspectives, vol. 1, no. 1, pp. 7–13, Jun. 2021, doi: 10.14710/jsp.2021.11201.
[3] E. H. Sepúlveda-Oviedo, “Impact of environmental factors on photovoltaic system performance degradation,” Energy Strategy Reviews, vol. 59, p. 101682, May 2025, doi: 10.1016/j.esr.2025.101682.
[4] G. Zhang et al., “Solar radiation estimation in different climates with meteorological variables using Bayesian model averaging and new soft computing models,” Energy Reports, vol. 7, pp. 8973–8996, Nov. 2021, doi: 10.1016/j.egyr.2021.10.117.
[5] N. Krishnan, K. R. Kumar, and C. S. Inda, “How solar radiation forecasting impacts the utilization of solar energy: A critical review,” J. Clean. Prod., vol. 388, p. 135860, Feb. 2023, doi: 10.1016/j.jclepro.2023.135860.
[6] J. Tian and R. Ooka, “Prediction of building-scale solar energy potential in urban environment based on parametric modelling and machine learning algorithms,” Sustain. Cities Soc., vol. 119, p. 106057, Feb. 2025, doi: 10.1016/j.scs.2024.106057.
[7] V. Demir, “Evaluation of Solar Radiation Prediction Models Using AI: A Performance Comparison in the High-Potential Region of Konya, Türkiye,” Atmosphere (Basel)., vol. 16, no. 4, Apr. 2025, doi: 10.3390/atmos16040398.
[8] L. Achour, M. Bouharkat, O. Assas, and O. Behar, “Hybrid model for estimating monthly global solar radiation for the Southern of Algeria: (Case study: Tamanrasset, Algeria),” Energy, vol. 135, pp. 526–539, Sep. 2017, doi: 10.1016/j.energy.2017.06.155.
[9] J. Almorox and C. Hontoria, “Global solar radiation estimation using sunshine duration in Spain,” Energy Convers. Manag., vol. 45, no. 9–10, pp. 1529–1535, Jun. 2004, doi: 10.1016/j.enconman.2003.08.022.
[10] D. B. Ampratwum and A. S. S. Dorvlo, “Estimation of solar radiation from the number of sunshine hours,” Appl. Energy, vol. 63, no. 3, pp. 161–167, Jul. 1999, doi: 10.1016/S0306-2619(99)00025-2.
[11] V. Bahel, H. Bakhsh, and R. Srinivasan, “A correlation for estimation of global solar radiation,” Energy, vol. 12, no. 2, pp. 131–135, Feb. 1987, doi: 10.1016/0360-5442(87)90117-4.
[12] K. Bakirci, “Correlations for estimation of daily global solar radiation with hours of bright sunshine in Turkey,” Energy, vol. 34, no. 4, pp. 485–501, Apr. 2009, doi: 10.1016/j.energy.2009.02.005.
[13] A. A. El-Sebaii, A. A. Al-Ghamdi, F. S. Al-Hazmi, and A. S. Faidah, “Estimation of global solar radiation on horizontal surfaces in Jeddah, Saudi Arabia,” Energy Policy, vol. 37, no. 9, pp. 3645–3649, Sep. 2009, doi: 10.1016/j.enpol.2009.04.038.
[14] M. E. Fernández, J. O. Gentili, and A. M. Campo, “Sunshine Duration Analysis as a First Step to Estimate Solar Resource for Photovoltaic Electricity Production in Middle Latitudes,” Environmental Processes, vol. 5, no. 2, pp. 313–328, Jun. 2018, doi: 10.1007/s40710-018-0298-3.
[15] K. Lan, L. Wang, Y. Zhou, Z. Zhang, S. Fang, and P. Cao, “The applicability of sunshine-based global solar radiation models modified with meteorological factors for different climate zones of China,” Front. Energy Res., vol. 10, Jan. 2023, doi: 10.3389/fenrg.2022.1010745.
[16] F. J. Newland, “A study of solar radiation models for the coastal region of South China,” Solar Energy, vol. 43, no. 4, pp. 227–235, 1989, doi: 10.1016/0038-092X(89)90022-4.
[17] M. A. Ali, A. Elsayed, I. Elkabani, M. E. Youssef, and G. E. Hassan, “Modeling global solar radiation using ambient temperature,” Cleaner Energy Systems, vol. 7, p. 100101, Apr. 2024, doi: 10.1016/j.cles.2023.100101.
[18] J. Almorox, M. Bocco, and E. Willington, “Estimation of daily global solar radiation from measured temperatures at Cañada de Luque, Córdoba, Argentina,” Renew. Energy, vol. 60, pp. 382–387, Dec. 2013, doi: 10.1016/j.renene.2013.05.033.
[19] J. Fan, B. Chen, L. Wu, F. Zhang, X. Lu, and Y. Xiang, “Evaluation and development of temperature-based empirical models for estimating daily global solar radiation in humid regions,” Energy, vol. 144, pp. 903–914, Feb. 2018, doi: 10.1016/j.energy.2017.12.091.
[20] N. Ghazouani et al., “Performance Evaluation of Temperature-Based Global Solar Radiation Models—Case Study: Arar City, KSA,” Sustainability, vol. 14, no. 1, p. 35, Dec. 2021, doi: 10.3390/su14010035.
[21] L. Gu et al., “Cloud modulation of surface solar irradiance at a pasture site in southern Brazil,” Agric. For. Meteorol., vol. 106, no. 2, pp. 117–129, Jan. 2001, doi: 10.1016/S0168-1923(00)00209-4.
[22] A. Radovan, V. Šunde, D. Kučak, and Ž. Ban, “Solar Irradiance Forecast Based on Cloud Movement Prediction,” Energies (Basel)., vol. 14, no. 13, p. 3775, Jun. 2021, doi: 10.3390/en14133775.
[23] S. Mujabar and R. Chintaginjala Venkateswara, “Empirical models for estimating the global solar radiation of Jubail Industrial City, the Kingdom of Saudi Arabia,” SN Appl. Sci., vol. 3, no. 1, Jan. 2021, doi: 10.1007/s42452-020-04043-9.
[24] A. Vernet and A. Fabregat, “Evaluation of Empirical Daily Solar Radiation Models for the Northeast Coast of the Iberian Peninsula,” Energies (Basel)., vol. 16, no. 6, p. 2560, Mar. 2023, doi: 10.3390/en16062560.
[25] X. Qing and Y. Niu, “Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM,” Energy, vol. 148, pp. 461–468, Apr. 2018, doi: 10.1016/j.energy.2018.01.177.
[26] A. Aldrees, H. H. Awan, M. F. Javed, and A. M. Mohamed, “Prediction of water quality indexes with ensemble learners: Bagging and boosting,” Process Safety and Environmental Protection, vol. 168, pp. 344–361, Dec. 2022, doi: 10.1016/j.psep.2022.10.005.
[27] S. Hakkal and A. A. Lahcen, “XGBoost To Enhance Learner Performance Prediction,” Computers and Education: Artificial Intelligence, vol. 7, p. 100254, Dec. 2024, doi: 10.1016/j.caeai.2024.100254.
[28] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
[29] Y. Kim and Y. Byun, “Predicting Solar Power Generation from Direction and Tilt Using Machine Learning XGBoost Regression,” J. Phys. Conf. Ser., vol. 2261, no. 1, p. 012003, Jun. 2022, doi: 10.1088/1742-6596/2261/1/012003.
[30] X. Li et al., “Probabilistic solar irradiance forecasting based on XGBoost,” Energy Reports, vol. 8, pp. 1087–1095, Aug. 2022, doi: 10.1016/j.egyr.2022.02.251.
[31] Q.-T. Phan, Y.-K. Wu, and Q.-D. Phan, “Short-term Solar Power Forecasting Using XGBoost with Numerical Weather Prediction,” in 2021 IEEE International Future Energy Electronics Conference (IFEEC), IEEE, Nov. 2021, pp. 1–6. doi: 10.1109/IFEEC53238.2021.9661874.
[32] C. Zhang, Y. Zhang, J. Pu, Z. Liu, Z. Wang, and L. Wang, “An hourly solar radiation prediction model using eXtreme gradient boosting algorithm with the effect of fog-haze,” Energy and Built Environment, vol. 6, no. 1, pp. 18–26, Feb. 2025, doi: 10.1016/j.enbenv.2023.08.001.
[33] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
[34] J. Xu, Z. Wang, X. Li, Z. Li, and Z. Li, “Prediction of Daily Climate Using Long Short-Term Memory (LSTM) Model,” International Journal of Innovative Science and Research Technology (IJISRT), pp. 83–90, Jul. 2024, doi: 10.38124/ijisrt/ijisrt24jul073.
[35] S. Tajjour, S. S. Chandel, M. A. Alotaibi, H. Malik, F. P. Garcia Marquez, and A. Afthanorhan, “Short-Term Solar Irradiance Forecasting Using Deep Learning Techniques: A Comprehensive Case Study,” IEEE Access, vol. 11, pp. 119851–119861, 2023, doi: 10.1109/ACCESS.2023.3325292.
[36] W. K. Wardani and R. Andriyani, “Evaluating the Performance of LSTM in Photovoltaic Energy Optimization using Sunshine Duration Prediction,” Jurnal Fokus Elektroda, vol. 10, no. 3, 2025.
[37] Y. Mariappan, K. Ramasamy, and D. Velusamy, “An optimized deep learning based hybrid model for prediction of daily average global solar irradiance using CNN SLSTM architecture,” Sci. Rep., vol. 15, no. 1, p. 10761, Mar. 2025, doi: 10.1038/s41598-025-95118-3.
[38] A. Vatresia, E. Lestari, F. Utama, and N. Daratha, “Spatial Interpolation Long-Term Patterns Capacity of Renewable Energy in Sumatera,” Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, Jun. 2024, doi: 10.22219/kinetik.v9i3.1929.
[39] J.-S. Kang, D.-H. Shin, J.-W. Baek, and K. Chung, “Activity Recommendation Model Using Rank Correlation for Chronic Stress Management,” Applied Sciences, vol. 9, no. 20, p. 4284, Oct. 2019, doi: 10.3390/app9204284.
[40] A. K. Shrestha, A. Thapa, and H. Gautam, “Solar Radiation, Air Temperature, Relative Humidity, and Dew Point Study: Damak, Jhapa, Nepal,” International Journal of Photoenergy, vol. 2019, pp. 1–7, Dec. 2019, doi: 10.1155/2019/8369231.
[41] Q. Cao, Y. Liu, K. Lyu, Y. Yu, D. H. W. Li, and L. Yang, “Solar radiation zoning and daily global radiation models for regions with only surface meteorological measurements in China,” Energy Convers. Manag., vol. 225, p. 113447, Dec. 2020, doi: 10.1016/j.enconman.2020.113447.
[42] F. Besharat, A. A. Dehghan, and A. R. Faghih, “Empirical models for estimating global solar radiation: A review and case study,” Renewable and Sustainable Energy Reviews, vol. 21, pp. 798–821, May 2013, doi: 10.1016/j.rser.2012.12.043.
[43] P. E. Bett and H. E. Thornton, “The climatological relationships between wind and solar energy supply in Britain,” Renew. Energy, vol. 87, pp. 96–110, Mar. 2016, doi: 10.1016/j.renene.2015.10.006.
[44] K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre-processing and data augmentation techniques,” Global Transitions Proceedings, vol. 3, no. 1, pp. 91–99, Jun. 2022, doi: 10.1016/j.gltp.2022.04.020.
[45] I. B. Mohamad and D. Usman, “Standardization and Its Effects on K-Means Clustering Algorithm,” Research Journal of Applied Sciences, Engineering and Technology, vol. 6, no. 17, pp. 3299–3303, 2013.
[46] D. N. Gono, H. Napitupulu, and Firdaniza, “Silver Price Forecasting Using Extreme Gradient Boosting (XGBoost) Method,” Mathematics, vol. 11, no. 18, p. 3813, Sep. 2023, doi: 10.3390/math11183813.
[47] M. Pacella and G. Papadia, “Evaluation of deep learning with long short-term memory networks for time series forecasting in supply chain management,” Procedia CIRP, vol. 99, pp. 604–609, 2021, doi: 10.1016/j.procir.2021.03.081.
[48] Ottavio Calzone, “An Intuitive Explanation of LSTM,” Medium.
[49] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput Sci, vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623.
[50] T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature,” Geosci Model Dev, vol. 7, no. 3, pp. 1247–1250, Jun. 2014, doi: 10.5194/gmd-7-1247-2014.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ririn Andriyani, Wulan Kusuma Wardani, Putty Yunesti
This work is licensed under a Creative Commons Attribution 4.0 International License.
