Evaluating the Generalization of an Ensemble Learning Model for Global Horizontal Irradiance Estimation in Guangxi Province Using FY-4A Satellite Data

Authors

  • Jiaqiu Hu

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Yiming Qin

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Qian Ye

    National Satellite Meteorological Center, China Meteorological Administration, Beijing 100081, China
  • Kui Huang

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Houjian Zhan

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Jian Tang

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Jie Lin

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Yixin Zhuo

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China
  • Huanxing Qi

    Power Dispatching Control Center of Guangxi Power Grid, Nanning 530012, China

DOI:

https://doi.org/10.30564/jees.v8i4.13005
Received: 10 January 2026 | Revised: 8 March 2026 | Accepted: 11 March 2026 | Published Online: 15 April 2026

Abstract

This study investigates the application of the Extreme Gradient Boosting (XGBoost) ensemble learning algorithm for estimating global horizontal irradiance (GHI) based on satellite data in Guangxi Province, China. By synergistically integrating top-of-atmosphere (TOA) reflectance and brightness temperature data from 14 spectral bands of the Fengyun-4A (FY-4A) Advanced Geosynchronous Radiation Imager (AGRI) and European Centre for Medium-Range Weather Forecasts Reanalysis v5 (ERA5) reanalysis meteorological variables—including relative humidity, planetary boundary layer height, and surface pressure—we developed an all-sky model to predict hourly surface solar radiation. The model was trained on data from 159 ground stations across China in 2018 and incorporates 31 features covering satellite observations, geographical parameters, and meteorological variables. Validation was conducted using independent observational data from three additional ground stations in Guangxi (Guilin, Nanning, and Beihai) that were withheld from training, yielding Root Mean Square Error (RMSE) of approximately 126–150 W/m2 and Correlation Coefficient (CC) of 0.80–0.84, confirming strong spatial generalization. Seasonal analysis revealed that the model performed best in winter and least accurately in summer, attributable to the complexity of convective cloud dynamics in the subtropical monsoon climate of Guangxi. Feature importance analysis identified brightness temperature at 7.42 μm, solar zenith angle, relative humidity, and TOA reflectance at 0.47 μm as the most influential predictors, consistent with the physical mechanisms governing atmospheric transmissivity. These findings demonstrate that the direct data-driven satellite–machine learning framework offers a computationally efficient and scalable alternative to semi-empirical approaches for regional solar resource assessment.

Keywords:

Global Horizontal Irradiance; FY-4A; XGBoost; Data Validation

References

[1] Jia, D., Hua, J., Wang, L., et al., 2021. Estimations of Global Horizontal Irradiance and Direct Normal Irradiance by Using Fengyun-4A Satellite Data in Northern China. Remote Sensing. 13(4), 790. DOI: https://doi.org/10.3390/rs13040790

[2] Ruiz-Arias, J.A., Gueymard, C.A., 2018. Worldwide Inter-Comparison of Clear-Sky Solar Radiation Models: Consensus-Based Review of Direct and Global Irradiance Components Simulated at the Earth Surface. Solar Energy. 168, 10–29. DOI: https://doi.org/10.1016/j.solener.2018.02.008

[3] Olmo, F.J., Vida, J., Foyo, I., et al., 1999. Prediction of Global Irradiance on Inclined Surfaces from Horizontal Global Irradiance. Energy. 24(8), 689–704. DOI: https://doi.org/10.1016/S0360-5442(99)00025-0

[4] Li, D.H., Lou, S., 2018. Review of Solar Irradiance and Daylight Illuminance Modeling and Sky Classification. Renewable Energy. 126, 445–453. DOI: https://doi.org/10.1016/j.renene.2018.03.063

[5] Zhou, Y., Liu, Y., Wang, D., et al., 2021. A Review on Global Solar Radiation Prediction with Machine Learning Models in a Comprehensive Perspective. Energy Conversion and Management. 235, 113960. DOI: https://doi.org/10.1016/j.enconman.2021.113960

[6] Ramadhan, R.A.A., Heatubun, Y.R.J., Tan, S.F., et al., 2021. Comparison of Physical and Machine Learning Models for Estimating Solar Irradiance and Photovoltaic Power. Renewable Energy. 178, 1006–1019. DOI: https://doi.org/10.1016/j.renene.2021.06.079

[7] Benamrou, B., Ouardouz, M., Allaouzi, I., et al., 2020. A Proposed Model to Forecast Hourly Global Solar Irradiation Based on Satellite Derived Data, Deep Learning and Machine Learning Approaches. Journal of Ecological Engineering. 21(4), 26–38. DOI: https://doi.org/10.12911/22998993/119795

[8] Shi, H., Yang, D., Wang, W., et al., 2023. First Estimation of High-Resolution Solar Photovoltaic Resource Maps over China with Fengyun-4A Satellite and Machine Learning. Renewable and Sustainable Energy Reviews. 184, 113549. DOI: https://doi.org/10.1016/j.rser.2023.113549

[9] Journée, M., Bertrand, C., 2010. Improving the Spatio-Temporal Distribution of Surface Solar Radiation Data by Merging Ground and Satellite Measurements. Remote Sensing of Environment. 114(11), 2692–2704. DOI: https://doi.org/10.1016/j.rse.2010.06.010

[10] Letu, H., Yang, K., Nakajima, T.Y., et al., 2020. High-Resolution Retrieval of Cloud Microphysical Properties and Surface Solar Radiation Using Himawari-8/AHI Next-Generation Geostationary Satellite. Remote Sensing of Environment. 239, 111583. DOI: https://doi.org/10.1016/j.rse.2019.111583

[11] Huang, L., Kang, J., Wan, M., et al., 2021. Solar Radiation Prediction Using Different Machine Learning Algorithms and Implications for Extreme Climate Events. Frontiers in Earth Science. 9, 596860. DOI: https://doi.org/10.3389/feart.2021.596860

[12] Zang, H., Liu, L., Sun, L., et al., 2020. Short-Term Global Horizontal Irradiance Forecasting Based on a Hybrid CNN-LSTM Model with Spatiotemporal Correlations. Renewable Energy. 160, 26–41. DOI: https://doi.org/10.1016/j.renene.2020.05.150

[13] Rajaprasad, S., Mukkamala, R., 2023. A Hybrid Deep Learning Framework for Modeling the Short Term Global Horizontal Irradiance Prediction of a Solar Power Plant in India. Polityka Energetyczna – Energy Policy Journal. 26(3), 101–116. DOI: https://doi.org/10.33223/epj/168115

[14] El-Shahat, D., Tolba, A., Abouhawwash, M., et al., 2024. Machine Learning and Deep Learning Models Based Grid Search Cross Validation for Short-Term Solar Irradiance Forecasting. Journal of Big Data. 11, 134. DOI: https://doi.org/10.1186/s40537-024-00991-w

[15] Tan, Y., Wang, Q., Zhang, Z., 2023. Near-Real-Time Estimation of Global Horizontal Irradiance from Himawari-8 Satellite Data. Renewable Energy. 215, 118994. DOI: https://doi.org/10.1016/j.renene.2023.118994

[16] Suwanwimolkul, S., Tongamrak, N., Thungka, N., et al., 2025. Deep-Learning-Based and Near Real-Time Solar Irradiance Map Using Himawari-8 Satellite Imageries. Solar Energy. 288, 113262. Available from: https://www.sciencedirect.com/science/article/abs/pii/S0038092X25000258

[17] Nadeem, A., Hanif, M.F., Naveed, M.S., et al., 2024. AI-Driven Precision in Solar Forecasting: Breakthroughs in Machine Learning and Deep Learning. AIMS Geosciences. 10(4), 684–734. DOI: https://doi.org/10.3934/geosci.2024035

[18] Zhu, S., Ma, Z., 2021. Does AGRI of FY4A Have the Ability to Capture the Motions of Precipitation? IEEE Geoscience and Remote Sensing Letters. 19, 1–5. DOI: https://doi.org/10.1109/LGRS.2021.3130646

[19] Gao, Y., Mao, D., Wang, X., et al., 2022. Evaluation of FY-4A Temperature Profile Products and Application to Winter Precipitation Type Diagnosis in Southern China. Remote Sensing. 14(10), 2363. DOI: https://doi.org/10.3390/rs14102363

[20] Xu, F., Song, B., Chen, J., et al., 2024. Deep-Learning-Based Daytime COT Retrieval and Prediction Method Using FY4A AGRI Data. Remote Sensing. 16(12), 2136. DOI: https://doi.org/10.3390/rs16122136

[21] Yang, J., Zhang, Z., Wei, C., et al., 2017. Introducing the New Generation of Chinese Geostationary Weather Satellites, Fengyun-4. Bulletin of the American Meteorological Society. 98, 1637–1658. DOI: https://doi.org/10.1175/BAMS-D-16-0065.1

[22] Du, S., Zhang, Y., Wei, W., et al., 2021. Analysis of Influence of Solar Zenith Angle on Reconstruction of Hyperspectral Surface Reflectance. Acta Optica Sinica. 41(2), 0229001. DOI: https://doi.org/10.3788/AOS202141.0229001 (in Chinese)

[23] Liu, H., Hu, B., Zhang, L., et al., 2017. Ultraviolet Radiation over China: Spatial Distribution and Trends. Renewable and Sustainable Energy Reviews. 76, 1371–1383. DOI: https://doi.org/10.1016/j.rser.2017.03.102

[24] Gao, X.-Y., Liu, J.-M., Yuan, Y., et al., 2023. Global Horizontal Irradiance Prediction Model Considering the Effect of Aerosol Optical Depth Based on the Informer Model. SSRN. DOI: http://dx.doi.org/10.2139/ssrn.4522731

[25] Shrestha, A.K., Thapa, A., Gautam, H., 2019. Solar Radiation, Air Temperature, Relative Humidity, and Dew Point Study: Damak, Jhapa, Nepal. International Journal of Photoenergy. 2019(1), 8369231. DOI: https://doi.org/10.1155/2019/8369231

[26] Bilgili, M., Ozgoren, M., 2011. Daily Total Global Solar Radiation Modeling from Several Meteorological Data. Meteorology and Atmospheric Physics. 112, 125–138. DOI: https://doi.org/10.1007/s00703-011-0137-9

[27] Chen, T., Guestrin, C., 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. DOI: https://doi.org/10.1145/2939672.2939785

[28] Taylor, K.E., 2001. Summarizing Multiple Aspects of Model Performance in a Single Diagram. Journal of Geophysical Research: Atmospheres. 106(D7), 7183–7192. DOI: https://doi.org/10.1029/2000JD900719

[29] Willmott, C.J., Matsuura, K., 2005. Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE) in Assessing Average Model Performance. Climate Research. 30(1), 79–82. DOI: https://doi.org/10.3354/cr030079

[30] Chai, T., Draxler, R.R., 2014. Root Mean Square Error (RMSE) or Mean Absolute Error (MAE)?—Arguments against Avoiding RMSE in the Literature. Geoscientific Model Development. 7(3), 1247–1250. DOI: https://doi.org/10.5194/gmd-7-1247-2014

[31] Cronin, T.W., 2014. On the Choice of Average Solar Zenith Angle. Journal of the Atmospheric Sciences. 71(8), 2994–3003. DOI: https://doi.org/10.1175/JAS-D-13-0392.1

[32] Qiao, C., Liu, S., Huo, J., et al., 2023. Retrievals of Precipitable Water Vapor and Aerosol Optical Depth from Direct Sun Measurements with EKO MS711 and MS712 Spectroradiometers. Atmospheric Measurement Techniques. 16(6), 1539–1549. DOI: https://doi.org/10.5194/amt-16-1539-2023

[33] Teillet, P.M., Fedosejevs, G., Ahern, F.J., et al., 1994. Sensitivity of Surface Reflectance Retrieval to Uncertainties in Aerosol Optical Properties. Applied Optics. 33(18), 3933–3940. DOI: https://doi.org/10.1364/AO.33.003933

Downloads

How to Cite

Hu, J., Qin, Y., Ye, Q., Huang, K., Zhan, H., Tang, J., Lin, J., Zhuo, Y., & Qi, H. (2026). Evaluating the Generalization of an Ensemble Learning Model for Global Horizontal Irradiance Estimation in Guangxi Province Using FY-4A Satellite Data. Journal of Environmental & Earth Sciences, 8(4), 143–156. https://doi.org/10.30564/jees.v8i4.13005

Issue

Vol. 8 , Iss. 4 (April 2026)

Article Type

Article

License

Copyright © 2026 Jiaqiu Hu, Yiming Qin, Qian Ye, Kui Huang, Houjian Zhan, Jian Tang, Jie Lin, Yixin Zhuo, Huanxing Qi

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC