IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v377y2025ipas0306261924017926.html
   My bibliography  Save this article

Interpretable deep learning framework for hourly solar radiation forecasting based on decomposing multi-scale variations

Author

Listed:
  • Li, You
  • Zhou, Weisheng
  • Wang, Yafei
  • Miao, Sheng
  • Yao, Wanxiang
  • Gao, Weijun

Abstract

High-precision solar radiation forecasting is crucial for the economic and reliable operation of building energy systems and contributes to achieving sustainability goals. However, owing to multi-scale variations and instability of solar radiation, most methods face a zero-sum game of trade-offs between simplicity, reliability, and interpretability. In this study, we propose a reliable and interpretable deep learning framework by deconstructing the multi-scale variations of solar radiation. It integrates feature engineering using transformation matrices, Convolutional Neural Networks classification for local feature recognition, and Long Short-Term Memory prediction for global uncertainty learning. First, the temporal variability of solar radiation is transformed into a simple mathematical description using transformation matrices. Then, Convolutional Neural Network associate local features with embedded skewed labels of solar radiation, resulting in a robust output in the first stage. Finally, Long Short-Term Memory's global feature mining adapts to the instability to obtain the final output. The proposed model was trained and tested using meteorological data collected in Tokyo from January 1, 2000, to December 31, 2021. The results indicate that the proposed model can achieve high-precision predictions by leveraging historical data correlation and inference demonstrated by its high performance on untrained datasets with an R2 of 0.97. Additionally, it is addressing a part of solar radiation time series forecasting problems that previously required black-box models, by using reliable mathematical descriptions and expert knowledge. This enhances the interpretability of the deep learning framework through the ante-hoc design of the model. This study provides valuable insights into the precise geographical expansion of solar radiation datasets and practical adjustment strategies for building energy systems.

Suggested Citation

  • Li, You & Zhou, Weisheng & Wang, Yafei & Miao, Sheng & Yao, Wanxiang & Gao, Weijun, 2025. "Interpretable deep learning framework for hourly solar radiation forecasting based on decomposing multi-scale variations," Applied Energy, Elsevier, vol. 377(PA).
    • Handle: RePEc:eee:appene:v:377:y:2025:i:pa:s0306261924017926
    DOI: 10.1016/j.apenergy.2024.124409
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924017926
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2024.124409?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Song, Zhe & Cao, Sunliang & Yang, Hongxing, 2023. "Assessment of solar radiation resource and photovoltaic power potential across China based on optimized interpretable machine learning model and GIS-based approaches," Applied Energy, Elsevier, vol. 339(C).
    2. Yadav, Amit Kumar & Malik, Hasmat & Chandel, S.S., 2015. "Application of rapid miner in ANN based prediction of solar radiation for assessment of solar energy resource potential of 76 sites in Northwestern India," Renewable and Sustainable Energy Reviews, Elsevier, vol. 52(C), pages 1093-1106.
    3. Gao, Bixuan & Huang, Xiaoqiao & Shi, Junsheng & Tai, Yonghang & Zhang, Jun, 2020. "Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks," Renewable Energy, Elsevier, vol. 162(C), pages 1665-1683.
    4. Ghimire, Sujan & Deo, Ravinesh C. & Raj, Nawin & Mi, Jianchun, 2019. "Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms," Applied Energy, Elsevier, vol. 253(C), pages 1-1.
    5. Carpentieri, A. & Folini, D. & Nerini, D. & Pulkkinen, S. & Wild, M. & Meyer, A., 2023. "Intraday probabilistic forecasts of surface solar radiation with cloud scale-dependent autoregressive advection," Applied Energy, Elsevier, vol. 351(C).
    6. McCandless, T.C. & Haupt, S.E. & Young, G.S., 2016. "A regime-dependent artificial neural network technique for short-range solar irradiance forecasting," Renewable Energy, Elsevier, vol. 89(C), pages 351-359.
    7. Kong, Xiangfei & Du, Xinyu & Xue, Guixiang & Xu, Zhijie, 2023. "Multi-step short-term solar radiation prediction based on empirical mode decomposition and gated recurrent unit optimized via an attention mechanism," Energy, Elsevier, vol. 282(C).
    8. Chang, Kai & Zhang, Qingyuan, 2019. "Improvement of the hourly global solar model and solar radiation for air-conditioning design in China," Renewable Energy, Elsevier, vol. 138(C), pages 1232-1238.
    9. Wang, Baichao & Liu, Yanfeng & Wang, Dengjia & Song, Cong & Fu, Zhiguo & Zhang, Cong, 2024. "A review of the photothermal-photovoltaic energy supply system for building in solar energy enrichment zones," Renewable and Sustainable Energy Reviews, Elsevier, vol. 191(C).
    10. Yao, Wanxiang & Zhang, Chunxiao & Hao, Haodong & Wang, Xiao & Li, Xianli, 2018. "A support vector machine approach to estimate global solar radiation with the influence of fog and haze," Renewable Energy, Elsevier, vol. 128(PA), pages 155-162.
    11. Jiang, Chengcheng & Zhu, Qunzhi, 2023. "Evaluating the most significant input parameters for forecasting global solar radiation of different sequences based on Informer," Applied Energy, Elsevier, vol. 348(C).
    12. Kee Han Kim & John Kie-Whan Oh & WoonSeong Jeong, 2016. "Study on Solar Radiation Models in South Korea for Improving Office Building Energy Performance Analysis," Sustainability, MDPI, vol. 8(6), pages 1-14, June.
    13. Qin, Shujing & Liu, Zhihe & Qiu, Rangjian & Luo, Yufeng & Wu, Jingwei & Zhang, Baozhong & Wu, Lifeng & Agathokleous, Evgenios, 2023. "Short–term global solar radiation forecasting based on an improved method for sunshine duration prediction and public weather forecasts," Applied Energy, Elsevier, vol. 343(C).
    14. Aleh Cherp & Vadim Vinichenko & Jale Tosun & Joel A. Gordon & Jessica Jewell, 2021. "National growth dynamics of wind and solar power compared to the growth required for global climate targets," Nature Energy, Nature, vol. 6(7), pages 742-754, July.
    15. Nian, Victor & Mignacca, Benito & Locatelli, Giorgio, 2022. "Policies toward net-zero: Benchmarking the economic competitiveness of nuclear against wind and solar energy," Applied Energy, Elsevier, vol. 320(C).
    16. Gao, Yuan & Miyata, Shohei & Akashi, Yasunori, 2022. "Interpretable deep learning models for hourly solar radiation prediction based on graph neural network and attention," Applied Energy, Elsevier, vol. 321(C).
    17. Prieto, Jesús-Ignacio & García, David, 2022. "Global solar radiation models: A critical review from the point of view of homogeneity and case study," Renewable and Sustainable Energy Reviews, Elsevier, vol. 155(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Juan A. Tejero-Gómez & Ángel A. Bayod-Rújula, 2024. "Analysis of Grid-Scale Photovoltaic Plants Incorporating Battery Storage with Daily Constant Setpoints," Energies, MDPI, vol. 17(23), pages 1-23, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Xu, Shaozhen & Liu, Jun & Huang, Xiaoqiao & Li, Chengli & Chen, Zaiqing & Tai, Yonghang, 2024. "Minutely multi-step irradiance forecasting based on all-sky images using LSTM-InformerStack hybrid model with dual feature enhancement," Renewable Energy, Elsevier, vol. 224(C).
    2. Gupta, Priya & Singh, Rhythm, 2023. "Combining a deep learning model with multivariate empirical mode decomposition for hourly global horizontal irradiance forecasting," Renewable Energy, Elsevier, vol. 206(C), pages 908-927.
    3. Gao, Yuan & Hu, Zehuan & Chen, Wei-An & Liu, Mingzhe, 2024. "Solutions to the insufficiency of label data in renewable energy forecasting: A comparative and integrative analysis of domain adaptation and fine-tuning," Energy, Elsevier, vol. 302(C).
    4. Hanif, M.F. & Mi, J., 2024. "Harnessing AI for solar energy: Emergence of transformer models," Applied Energy, Elsevier, vol. 369(C).
    5. Xiao, Zenan & Huang, Xiaoqiao & Liu, Jun & Li, Chengli & Tai, Yonghang, 2023. "A novel method based on time series ensemble model for hourly photovoltaic power prediction," Energy, Elsevier, vol. 276(C).
    6. Vu, Ba Hau & Chung, Il-Yop, 2022. "Optimal generation scheduling and operating reserve management for PV generation using RNN-based forecasting models for stand-alone microgrids," Renewable Energy, Elsevier, vol. 195(C), pages 1137-1154.
    7. Khan, Zulfiqar Ahmad & Khan, Shabbir Ahmad & Hussain, Tanveer & Baik, Sung Wook, 2024. "DSPM: Dual sequence prediction model for efficient energy management in micro-grid," Applied Energy, Elsevier, vol. 356(C).
    8. Ngoc-Lan Huynh, Anh & Deo, Ravinesh C. & Ali, Mumtaz & Abdulla, Shahab & Raj, Nawin, 2021. "Novel short-term solar radiation hybrid model: Long short-term memory network integrated with robust local mean decomposition," Applied Energy, Elsevier, vol. 298(C).
    9. Guosheng Duan & Lifeng Wu & Fa Liu & Yicheng Wang & Shaofei Wu, 2022. "Improvement in Solar-Radiation Forecasting Based on Evolutionary KNEA Method and Numerical Weather Prediction," Sustainability, MDPI, vol. 14(11), pages 1-20, June.
    10. Acikgoz, Hakan, 2022. "A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting," Applied Energy, Elsevier, vol. 305(C).
    11. Elizabeth Michael, Neethu & Hasan, Shazia & Al-Durra, Ahmed & Mishra, Manohar, 2022. "Short-term solar irradiance forecasting based on a novel Bayesian optimized deep Long Short-Term Memory neural network," Applied Energy, Elsevier, vol. 324(C).
    12. Zhu, Yinlong & Li, Guoliang & Jiang, Yonglei & Li, Ming & Wang, Yunfeng & Zhang, Ying & Liu, Yali & Yao, Muchi, 2025. "Predicting photovoltaic greenhouse irradiance at low-latitudes of plateau based on ultra-short-term time series," Renewable Energy, Elsevier, vol. 239(C).
    13. Li, Ruohan & Wang, Dongdong & Wang, Zhihao & Liang, Shunlin & Li, Zhanqing & Xie, Yiqun & He, Jiena, 2025. "Transformer approach to nowcasting solar energy using geostationary satellite data," Applied Energy, Elsevier, vol. 377(PA).
    14. Wang, Zheng & Peng, Tian & Zhang, Xuedong & Chen, Jialei & Qian, Shijie & Zhang, Chu, 2025. "Enhancing multi-step short-term solar radiation forecasting based on optimized generalized regularized extreme learning machine and multi-scale Gaussian data augmentation technique," Applied Energy, Elsevier, vol. 377(PD).
    15. Jiang, Chengcheng & Zhu, Qunzhi, 2023. "Evaluating the most significant input parameters for forecasting global solar radiation of different sequences based on Informer," Applied Energy, Elsevier, vol. 348(C).
    16. Sibtain, Muhammad & Li, Xianshan & Saleem, Snoober & Ain, Qurat-ul- & Shi, Qiang & Li, Fei & Saeed, Muhammad & Majeed, Fatima & Shah, Syed Shoaib Ahmed & Saeed, Muhammad Hammad, 2022. "Multifaceted irradiance prediction by exploiting hybrid decomposition-entropy-Spatiotemporal attention based Sequence2Sequence models," Renewable Energy, Elsevier, vol. 196(C), pages 648-682.
    17. Zhao, He & Huang, Xiaoqiao & Xiao, Zenan & Shi, Haoyuan & Li, Chengli & Tai, Yonghang, 2024. "Week-ahead hourly solar irradiation forecasting method based on ICEEMDAN and TimesNet networks," Renewable Energy, Elsevier, vol. 220(C).
    18. Kong, Xiangfei & Du, Xinyu & Xue, Guixiang & Xu, Zhijie, 2023. "Multi-step short-term solar radiation prediction based on empirical mode decomposition and gated recurrent unit optimized via an attention mechanism," Energy, Elsevier, vol. 282(C).
    19. Gupta, Priya & Singh, Rhythm, 2023. "Combining simple and less time complex ML models with multivariate empirical mode decomposition to obtain accurate GHI forecast," Energy, Elsevier, vol. 263(PC).
    20. Feng, Yu & Hao, Weiping & Li, Haoru & Cui, Ningbo & Gong, Daozhi & Gao, Lili, 2020. "Machine learning models to quantify and map daily global solar radiation and photovoltaic power," Renewable and Sustainable Energy Reviews, Elsevier, vol. 118(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:377:y:2025:i:pa:s0306261924017926. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.