IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v335y2025ics0360544225037417.html

Data-driven approach of atrium skylights-integrated photovoltaic systems design based on multimodal deep learning: Considering different regions in China

Author

Listed:
  • Chen, Zhengshu
  • Cui, Yanqiu
  • Ren, Zhen
  • Ning, Qiao
  • Ding, Xin

Abstract

Atriums in public buildings significantly enhance daylighting but can increase heating and cooling loads in extreme climates. Skylight-integrated photovoltaic (SIPV) systems efficiently reduce carbon emissions but may compromise daylight quality and visual comfort due to excessive PV coverage. Therefore, this study develops a data-driven approach that integrates simulation, prediction, and optimization on the Grasshopper-Python platform. Image features are extracted using ResNet-50, ViT-32, and Inception-V4; numerical features are processed via MLP and TabTransformer. Feature fusion to form a multimodal neural network model, which serves as a surrogate model within an optimization framework. Using 7 cities in China as case studies, the approach optimizes atrium form, skylight, PV system, and fenestration factors to minimize carbon emissions and energy return on investment (EROI), while improving daylighting. The results show that: (1) Carbon emission reduction rate (CER) exceeds 89 %, Daylight factor (DF) increases by 1.2 %–3.4 %, Daylight glare probability (DGP) remains below 0.28, and Energy return on investment (EROI) reaches 9.37; (2) atrium width, skylight-to-roof ratio (SRR), PV coverage, and horizontal panel are key factors; (3) the ViT-32+MLP model significantly improves prediction accuracy and efficiency. This research offers a practical method for SIPV design, supporting regional adaptation and scalable application in public building atriums.

Suggested Citation

  • Chen, Zhengshu & Cui, Yanqiu & Ren, Zhen & Ning, Qiao & Ding, Xin, 2025. "Data-driven approach of atrium skylights-integrated photovoltaic systems design based on multimodal deep learning: Considering different regions in China," Energy, Elsevier, vol. 335(C).
    • Handle: RePEc:eee:energy:v:335:y:2025:i:c:s0360544225037417
    DOI: 10.1016/j.energy.2025.138099
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544225037417
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2025.138099?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

    for a different version of it.

    References listed on IDEAS

    as
    1. Karthick, A. & Kalidasa Murugavel, K. & Kalaivani, L., 2018. "Performance analysis of semitransparent photovoltaic module for skylights," Energy, Elsevier, vol. 162(C), pages 798-812.
    2. Ge, Biqiu & Fan, Zhengyu & Liu, Jiaping, 2025. "Thermal and carbon emission multi-objective optimization of photovoltaic skylights integrated large railway station in the cold zone of China," Energy, Elsevier, vol. 327(C).
    3. Acosta, Ignacio & Varela, Carmen & Molina, Juan Francisco & Navarro, Jaime & Sendra, Juan José, 2018. "Energy efficiency and lighting design in courtyards and atriums: A predictive method for daylight factors," Applied Energy, Elsevier, vol. 211(C), pages 1216-1228.
    4. Vishwanatha M. Rao & Michael Hla & Michael Moor & Subathra Adithan & Stephen Kwak & Eric J. Topol & Pranav Rajpurkar, 2025. "Multimodal generative AI for medical image interpretation," Nature, Nature, vol. 639(8056), pages 888-896, March.
    5. Shi, Shaohang & Zhu, Ning & Wu, Shuangdui & Song, Yehao, 2024. "Evaluation and analysis of transmitted daylight color quality for different colored semi-transparent PV glazing," Renewable Energy, Elsevier, vol. 222(C).
    6. Barone, G. & Vassiliades, C. & Elia, C. & Savvides, A. & Kalogirou, S., 2023. "Design optimization of a solar system integrated double-skin façade for a clustered housing unit," Renewable Energy, Elsevier, vol. 215(C).
    7. Zhan, Jin & He, Wenjing & Huang, Jianxiang, 2024. "Comfort, carbon emissions, and cost of building envelope and photovoltaic arrangement optimization through a two-stage model," Applied Energy, Elsevier, vol. 356(C).
    8. Barbón, A. & Fortuny Ayuso, P. & Bayón, L. & Fernández-Rubiera, J.A., 2020. "Predicting beam and diffuse horizontal irradiance using Fourier expansions," Renewable Energy, Elsevier, vol. 154(C), pages 46-57.
    9. Wijeratne, W.M. Pabasara Upalakshi & Samarasinghalage, Tharushi Imalka & Yang, Rebecca Jing & Wakefield, Ron, 2022. "Multi-objective optimisation for building integrated photovoltaics (BIPV) roof projects in early design phase," Applied Energy, Elsevier, vol. 309(C).
    10. Chao Ding & Jing Ke & Mark Levine & Jessica Granderson & Nan Zhou, 2024. "Potential of artificial intelligence in reducing energy and carbon emissions of commercial buildings at scale," Nature Communications, Nature, vol. 15(1), pages 1-9, December.
    11. Raugei, Marco & Fullana-i-Palmer, Pere & Fthenakis, Vasilis, 2012. "The energy return on energy investment (EROI) of photovoltaics: Methodology and comparisons with fossil fuel life cycles," Energy Policy, Elsevier, vol. 45(C), pages 576-582.
    12. Chen, Liutao & Sun, Yong & Zhang, Ning & Yang, Jiachuan & Wang, Dan, 2024. "Quantifying the benefits of BIPV windows in urban environment under climate change: A comparison of three Chinese cities," Renewable Energy, Elsevier, vol. 221(C).
    13. Xu, Chengliang & Chen, Shiao & Ren, Haoshan & Xu, Chen & Li, Guannan & Li, Tao & Sun, Yongjun, 2025. "A novel deep learning and GIS integrated method for accurate city-scale assessment of building facade solar energy potential," Applied Energy, Elsevier, vol. 387(C).
    14. Gao, Yuan & Hu, Zehuan & Yamate, Shun & Otomo, Junichiro & Chen, Wei-An & Liu, Mingzhe & Xu, Tingting & Ruan, Yingjun & Shang, Juan, 2025. "Unlocking predictive insights and interpretability in deep reinforcement learning for Building-Integrated Photovoltaic and Battery (BIPVB) systems," Applied Energy, Elsevier, vol. 384(C).
    15. Tang, Haida & Chai, Xingkang & Chen, Jiayu & Wan, Yang & Wang, Yuqin & Wan, Wei & Li, Chunying, 2025. "Assessment of BIPV power generation potential at the city scale based on local climate zones: Combining physical simulation, machine learning and 3D building models," Renewable Energy, Elsevier, vol. 244(C).
    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. Ge, Biqiu & Fan, Zhengyu & Liu, Jiaping, 2025. "Thermal and carbon emission multi-objective optimization of photovoltaic skylights integrated large railway station in the cold zone of China," Energy, Elsevier, vol. 327(C).
    2. Mahdiyeh Tabatabaei & Ernesto Antonini, 2025. "Machine Learning for Optimizing Urban Photovoltaics: A Review of Static and Dynamic Factors," Sustainability, MDPI, vol. 17(18), pages 1-34, September.
    3. Skandalos, Nikolaos & Wang, Meng & Kapsalis, Vasileios & D'Agostino, Delia & Parker, Danny & Bhuvad, Sushant Suresh & Udayraj, & Peng, Jinqing & Karamanis, Dimitris, 2022. "Building PV integration according to regional climate conditions: BIPV regional adaptability extending Köppen-Geiger climate classification against urban and climate-related temperature increases," Renewable and Sustainable Energy Reviews, Elsevier, vol. 169(C).
    4. Ruan, Dawei & Fan, Cheng & Hu, Mingwei & Li, Yumin & Guan, Jun, 2025. "Building-integrated photovoltaics through multi-physics synergies: A critical review of optical, thermal, and electrical models in facade applications," Renewable Energy, Elsevier, vol. 251(C).
    5. Chen, Zhengshu & Cui, Yanqiu & Cai, Hongbin & Zheng, Haichao & Ning, Qiao & Ding, Xin, 2025. "Multi-objective optimization of photovoltaic facades in prefabricated academic buildings using transfer learning and genetic algorithms," Energy, Elsevier, vol. 328(C).
    6. Gao, Meng & Feng, Yidan & Ni, Pingan & Zheng, Hanjie & Sun, Hongli & Zhang, Yongwang & Qin, Guojin & He, Bao-Jie, 2026. "Solar energy potential evaluation of multi-scale urban building surfaces under complex shading: A multi-dimensional analysis," Renewable Energy, Elsevier, vol. 259(C).
    7. Barbón, A. & Fortuny Ayuso, P. & Bayón, L. & Silva, C.A., 2023. "Experimental and numerical investigation of the influence of terrain slope on the performance of single-axis trackers," Applied Energy, Elsevier, vol. 348(C).
    8. Hong, Sanghyun & Kim, Eunsung & Jeong, Saerok, 2023. "Evaluating the sustainability of the hydrogen economy using multi-criteria decision-making analysis in Korea," Renewable Energy, Elsevier, vol. 204(C), pages 485-492.
    9. Enrica Leccisi & Marco Raugei & Vasilis Fthenakis, 2016. "The Energy and Environmental Performance of Ground-Mounted Photovoltaic Systems—A Timely Update," Energies, MDPI, vol. 9(8), pages 1-13, August.
    10. Moh’d Al-Nimr & Abdallah Milhem & Basel Al-Bishawi & Khaleel Al Khasawneh, 2020. "Integrating Transparent and Conventional Solar Cells TSC/SC," Sustainability, MDPI, vol. 12(18), pages 1-22, September.
    11. Chenhang Bian & Panpan Hu & Chun Yin Li & Chi Chung Lee & Xi Chen, 2025. "Balancing Solar Energy, Thermal Comfort, and Emissions: A Data-Driven Urban Morphology Optimization Approach," Energies, MDPI, vol. 18(13), pages 1-28, June.
    12. Zhaoyang Kong & Xiucheng Dong & Bo Xu & Rui Li & Qiang Yin & Cuifang Song, 2015. "EROI Analysis for Direct Coal Liquefaction without and with CCS: The Case of the Shenhua DCL Project in China," Energies, MDPI, vol. 8(2), pages 1-22, January.
    13. Thopil, George Alex & Sachse, Christiaan Eddie & Lalk, Jörg & Thopil, Miriam Sara, 2020. "Techno-economic performance comparison of crystalline and thin film PV panels under varying meteorological conditions: A high solar resource southern hemisphere case," Applied Energy, Elsevier, vol. 275(C).
    14. Ron Swenson, 2016. "The Solarevolution: Much More with Way Less, Right Now—The Disruptive Shift to Renewables," Energies, MDPI, vol. 9(9), pages 1-22, August.
    15. Constantinos Vassiliades & Christos Minterides & Olga-Eleni Astara & Giovanni Barone & Ioannis Vardopoulos, 2023. "Socio-Economic Barriers to Adopting Energy-Saving Bioclimatic Strategies in a Mediterranean Sustainable Real Estate Setting: A Quantitative Analysis of Resident Perspectives," Energies, MDPI, vol. 16(24), pages 1-18, December.
    16. Barbón, A. & Aparicio-Bermejo, J. & Bayón, L. & Fortuny Ayuso, P., 2025. "The optimal design for photovoltaic power plants on sites with a general slope," Applied Energy, Elsevier, vol. 387(C).
    17. Good, Clara, 2016. "Environmental impact assessments of hybrid photovoltaic–thermal (PV/T) systems – A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 55(C), pages 234-239.
    18. Irene Del Hierro López & Nuria Martín-Chivelet & Jesús Polo & Lorenzo Olivieri, 2025. "Renovation of Typological Clusters with Building-Integrated Photovoltaic Systems," Energies, MDPI, vol. 18(6), pages 1-20, March.
    19. Suopajärvi, Hannu & Pongrácz, Eva & Fabritius, Timo, 2013. "The potential of using biomass-based reducing agents in the blast furnace: A review of thermochemical conversion technologies and assessments related to sustainability," Renewable and Sustainable Energy Reviews, Elsevier, vol. 25(C), pages 511-528.
    20. Yang, Haotian & Liu, Xingjiang & Gu, Yaping & Shen, Chao, 2025. "A novel photovoltaic-photothermal coupling skylight based on spectral complementation conception: System design and performance investigation," Renewable Energy, Elsevier, vol. 243(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:eee:energy:v:335:y:2025:i:c:s0360544225037417. 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.journals.elsevier.com/energy .

    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.