IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v18y2025i9p2300-d1646619.html
   My bibliography  Save this article

Nowcasting Solar Irradiance Components Using a Vision Transformer and Multimodal Data from All-Sky Images and Meteorological Observations

Author

Listed:
  • Onon Bayasgalan

    (Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture and Technology, Nakacho 2-24-16, Koganei 184-8588, Tokyo, Japan
    School of Engineering Technology, National University of Mongolia, Ikh Surguuliin Gudamj-1, Sukhbaatar District, Ulaanbaatar 14201, Mongolia)

  • Atsushi Akisawa

    (Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture and Technology, Nakacho 2-24-16, Koganei 184-8588, Tokyo, Japan)

Abstract

As the solar share in energy generation is expanding globally, solar nowcasting is becoming increasingly important for the efficient and economical management of the power grid. This study leveraged the spatial context provided by all-sky images (ASI) in addition to the meteorological records for improved nowcasting of global, direct, and diffuse irradiance components. The proposed methodology consists of two branches for processing the multimodal data of ASIs and meteorological data. Due to its capability of understanding the overall characteristics of the image through self-attention, a vision transformer is utilized for the image branch while normal dense layers process the tabular meteorological data. The proposed architecture is compared against the baselines of the Ineichen clear sky model, a feedforward neural network (FFNN) where cloud coverage is computed from the ASIs by a simple color-channel threshold algorithm, and a hybrid of FFNN and U-Net model, which replaces the color threshold algorithm with fully convolutional layers for cloud segmentation. The models are trained, validated, and tested using the quality-assured ground-truth data collected in Ulaanbaatar, Mongolia, from May to August 2024, under one-minute intervals with a random split of 70%, 15%, and 15%. Our approach exhibits superior performance to baselines with a significantly lower mean absolute error (MAE) of 15–33 W/m 2 and root mean square error (RMSE) of 26–72 W/m 2 , thus potentially aiding grid operators’ decision-making in real-time.

Suggested Citation

  • Onon Bayasgalan & Atsushi Akisawa, 2025. "Nowcasting Solar Irradiance Components Using a Vision Transformer and Multimodal Data from All-Sky Images and Meteorological Observations," Energies, MDPI, vol. 18(9), pages 1-22, April.
    • Handle: RePEc:gam:jeners:v:18:y:2025:i:9:p:2300-:d:1646619
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/18/9/2300/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/18/9/2300/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Niu, Yinsen & Song, Jifeng & Zou, Lianglin & Yan, Zixuan & Lin, Xilong, 2024. "Cloud detection method using ground-based sky images based on clear sky library and superpixel local threshold," Renewable Energy, Elsevier, vol. 226(C).
    2. Liu, Jingxuan & Zang, Haixiang & Cheng, Lilin & Ding, Tao & Wei, Zhinong & Sun, Guoqiang, 2023. "A Transformer-based multimodal-learning framework using sky images for ultra-short-term solar irradiance forecasting," Applied Energy, Elsevier, vol. 342(C).
    3. Su-Chang Lim & Jun-Ho Huh & Seok-Hoon Hong & Chul-Young Park & Jong-Chan Kim, 2022. "Solar Power Forecasting Using CNN-LSTM Hybrid Model," Energies, MDPI, vol. 15(21), pages 1-17, November.
    Full references (including those not matched with items on IDEAS)

    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. Nie, Yuhao & Paletta, Quentin & Scott, Andea & Pomares, Luis Martin & Arbod, Guillaume & Sgouridis, Sgouris & Lasenby, Joan & Brandt, Adam, 2024. "Sky image-based solar forecasting using deep learning with heterogeneous multi-location data: Dataset fusion versus transfer learning," Applied Energy, Elsevier, vol. 369(C).
    2. Tao, Kejun & Zhao, Jinghao & Tao, Ye & Qi, Qingqing & Tian, Yajun, 2024. "Operational day-ahead photovoltaic power forecasting based on transformer variant," Applied Energy, Elsevier, vol. 373(C).
    3. Pei, Jingyin & Dong, Yunxuan & Guo, Pinghui & Wu, Thomas & Hu, Jianming, 2024. "A Hybrid Dual Stream ProbSparse Self-Attention Network for spatial–temporal photovoltaic power forecasting," Energy, Elsevier, vol. 305(C).
    4. Li, Hao & Ma, Gang & Wang, Bo & Wang, Shu & Li, Wenhao & Meng, Yuxiang, 2025. "Multi-modal feature fusion model based on TimesNet and T2T-ViT for ultra-short-term solar irradiance forecasting," Renewable Energy, Elsevier, vol. 240(C).
    5. Abad-Alcaraz, V. & Castilla, M. & Carballo, J.A. & Bonilla, J. & Álvarez, J.D., 2025. "Multimodal deep learning for solar radiation forecasting," Applied Energy, Elsevier, vol. 393(C).
    6. Al-Dahidi, Sameer & Alrbai, Mohammad & Rinchi, Bilal & Alahmer, Hussein & Al-Ghussain, Loiy & Hayajneh, Hassan S. & Alahmer, Ali, 2025. "Techno-economic implications and cost of forecasting errors in solar PV power production using optimized deep learning models," Energy, Elsevier, vol. 323(C).
    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. Zhiwei Liao & Wenlong Min & Chengjin Li & Bowen Wang, 2024. "Photovoltaic Power Prediction Based on Irradiation Interval Distribution and Transformer-LSTM," Energies, MDPI, vol. 17(12), pages 1-17, June.
    9. Habib, Md. Ahasan & Hossain, M.J., 2024. "Advanced feature engineering in microgrid PV forecasting: A fast computing and data-driven hybrid modeling framework," Renewable Energy, Elsevier, vol. 235(C).
    10. Zang, Haixiang & Chen, Dianhao & Liu, Jingxuan & Cheng, Lilin & Sun, Guoqiang & Wei, Zhinong, 2024. "Improving ultra-short-term photovoltaic power forecasting using a novel sky-image-based framework considering spatial-temporal feature interaction," Energy, Elsevier, vol. 293(C).
    11. Liu, Jingxuan & Zang, Haixiang & Cheng, Lilin & Ding, Tao & Wei, Zhinong & Sun, Guoqiang, 2025. "Generative probabilistic forecasting of wind power: A Denoising-Diffusion-based nonstationary signal modeling approach," Energy, Elsevier, vol. 317(C).
    12. Xie, Yang & Zheng, Jianyong & Mei, Fei & Taylor, Gareth & Gao, Ang, 2025. "An efficient approach for regional photovoltaic power forecasting optimization based on texture features from satellite images and transfer learning," Applied Energy, Elsevier, vol. 385(C).
    13. Liu, Jingxuan & Zang, Haixiang & Zhang, Fengchun & Cheng, Lilin & Ding, Tao & Wei, Zhinong & Sun, Guoqiang, 2023. "A hybrid meteorological data simulation framework based on time-series generative adversarial network for global daily solar radiation estimation," Renewable Energy, Elsevier, vol. 219(P1).
    14. Ukwuoma, Chiagoziem C. & Cai, Dongsheng & Bamisile, Olusola & Yin, Hongbo & Nneji, Grace Ugochi & Monday, Happy N. & Oluwasanmi, Ariyo & Huang, Qi, 2024. "An attention fused sequence -to-sequence convolutional neural network for accurate solar irradiance forecasting and prediction using sky images," Renewable Energy, Elsevier, vol. 237(PB).
    15. Zhu, Jianhua & He, Yaoyao, 2025. "A novel hybrid model based on evolving multi-quantile long and short-term memory neural network for ultra-short-term probabilistic forecasting of photovoltaic power," Applied Energy, Elsevier, vol. 377(PC).
    16. Yin, Linfei & Zhou, Hang, 2024. "Modal decomposition integrated model for ultra-supercritical coal-fired power plant reheater tube temperature multi-step prediction," Energy, Elsevier, vol. 292(C).
    17. Elias Roumpakias & Tassos Stamatelos, 2023. "Comparative Performance Analysis of a Grid-Connected Photovoltaic Plant in Central Greece after Several Years of Operation Using Neural Networks," Sustainability, MDPI, vol. 15(10), pages 1-26, May.
    18. Verdone, Alessio & Panella, Massimo & De Santis, Enrico & Rizzi, Antonello, 2025. "A review of solar and wind energy forecasting: From single-site to multi-site paradigm," Applied Energy, Elsevier, vol. 392(C).
    19. Hanif, M.F. & Mi, J., 2024. "Harnessing AI for solar energy: Emergence of transformer models," Applied Energy, Elsevier, vol. 369(C).
    20. Wang, Yuqing & Fu, Wenjie & Wang, Junlong & Zhen, Zhao & Wang, Fei, 2024. "Ultra-short-term distributed PV power forecasting for virtual power plant considering data-scarce scenarios," Applied Energy, Elsevier, vol. 373(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    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:gam:jeners:v:18:y:2025:i:9:p:2300-:d:1646619. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.