IDEAS home Printed from https://ideas.repec.org/a/eee/rensus/v207y2025ics1364032124006245.html
   My bibliography  Save this article

Hydrogen jet and diffusion modeling by physics-informed graph neural network

Author

Listed:
  • Zhang, Xinqi
  • Shi, Jihao
  • Li, Junjie
  • Huang, Xinyan
  • Xiao, Fu
  • Wang, Qiliang
  • Usmani, Asif Sohail
  • Chen, Guoming

Abstract

Renewable Power-to-Hydrogen (P2H2) system is an emerging decarbonization strategy for achieving global carbon neutrality. However, the propensity of hydrogen to leak and diffuse from the P2H2 facility poses great challenges to scaling up and safe applications. Accurate and efficient prediction of hydrogen jet and diffusion is critical to ensure the safety and efficacy of P2H2 system. Deep learning methods have shown promise in predicting gas jet and diffusion, but their generalization is limited, because of insufficient simulation data and excluding physical laws during the training process. This study develops a physics-informed graph neural network (Physics_GNN) for hydrogen jet and diffusion prediction using sparse sensor data. Graph network is applied to model the spatial dependency between sensor data and governing equations, so the hydrogen jet and diffusion is immediately solved at each graph node. The computed residuals are then applied to constrain the training process of the graph network. Experimental data of subsonic and under-expanded hydrogen jet and diffusion are applied to validate the model. Results demonstrated Physics_GNN exhibits 1000 times higher prediction accuracy compared to state-of-the-art physics-informed neural network and 100 times faster than CFD simulation. It enables accurate and rapid prediction of hydrogen jet and diffusion concentration and velocity, supporting safety design, operation management and rulemaking of P2H2 system in future.

Suggested Citation

  • Zhang, Xinqi & Shi, Jihao & Li, Junjie & Huang, Xinyan & Xiao, Fu & Wang, Qiliang & Usmani, Asif Sohail & Chen, Guoming, 2025. "Hydrogen jet and diffusion modeling by physics-informed graph neural network," Renewable and Sustainable Energy Reviews, Elsevier, vol. 207(C).
  • Handle: RePEc:eee:rensus:v:207:y:2025:i:c:s1364032124006245
    DOI: 10.1016/j.rser.2024.114898
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1364032124006245
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.rser.2024.114898?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. Yin, Xiong & Wen, Kai & Huang, Weihe & Luo, Yinwei & Ding, Yi & Gong, Jing & Gao, Jianfeng & Hong, Bingyuan, 2023. "A high-accuracy online transient simulation framework of natural gas pipeline network by integrating physics-based and data-driven methods," Applied Energy, Elsevier, vol. 333(C).
    2. Maestre, V.M. & Ortiz, A. & Ortiz, I., 2021. "Challenges and prospects of renewable hydrogen-based strategies for full decarbonization of stationary power applications," Renewable and Sustainable Energy Reviews, Elsevier, vol. 152(C).
    3. Azadnia, Amir Hossein & McDaid, Conor & Andwari, Amin Mahmoudzadeh & Hosseini, Seyed Ehsan, 2023. "Green hydrogen supply chain risk analysis: A european hard-to-abate sectors perspective," Renewable and Sustainable Energy Reviews, Elsevier, vol. 182(C).
    4. Shi, Jihao & Li, Junjie & Usmani, Asif Sohail & Zhu, Yuan & Chen, Guoming & Yang, Dongdong, 2021. "Probabilistic real-time deep-water natural gas hydrate dispersion modeling by using a novel hybrid deep learning approach," Energy, Elsevier, vol. 219(C).
    5. Gordon, Joel A. & Balta-Ozkan, Nazmiye & Nabavi, Seyed Ali, 2023. "Socio-technical barriers to domestic hydrogen futures: Repurposing pipelines, policies, and public perceptions," Applied Energy, Elsevier, vol. 336(C).
    6. Qi, Meng & Vo, Dat Nguyen & Yu, Haoshui & Shu, Chi-Min & Cui, Chengtian & Liu, Yi & Park, Jinwoo & Moon, Il, 2023. "Strategies for flexible operation of power-to-X processes coupled with renewables," Renewable and Sustainable Energy Reviews, Elsevier, vol. 179(C).
    7. Tu, Hao & Moura, Scott & Wang, Yebin & Fang, Huazhen, 2023. "Integrating physics-based modeling with machine learning for lithium-ion batteries," Applied Energy, Elsevier, vol. 329(C).
    8. Schrotenboer, Albert H. & Veenstra, Arjen A.T. & uit het Broek, Michiel A.J. & Ursavas, Evrim, 2022. "A Green Hydrogen Energy System: Optimal control strategies for integrated hydrogen storage and power generation with wind energy," Renewable and Sustainable Energy Reviews, Elsevier, vol. 168(C).
    9. Tsiklios, C. & Hermesmann, M. & Müller, T.E., 2022. "Hydrogen transport in large-scale transmission pipeline networks: Thermodynamic and environmental assessment of repurposed and new pipeline configurations," Applied Energy, Elsevier, vol. 327(C).
    10. Seck, Gondia S. & Hache, Emmanuel & Sabathier, Jerome & Guedes, Fernanda & Reigstad, Gunhild A. & Straus, Julian & Wolfgang, Ove & Ouassou, Jabir A. & Askeland, Magnus & Hjorth, Ida & Skjelbred, Hans , 2022. "Hydrogen and the decarbonization of the energy system in europe in 2050: A detailed model-based analysis," Renewable and Sustainable Energy Reviews, Elsevier, vol. 167(C).
    11. Shu, Zhiyong & Liang, Wenqing & Zheng, Xiaohong & Lei, Gang & Cao, Peng & Dai, Wenxiao & Qian, Hua, 2021. "Dispersion characteristics of hydrogen leakage: Comparing the prediction model with the experiment," Energy, Elsevier, vol. 236(C).
    12. Bünning, Felix & Huber, Benjamin & Schalbetter, Adrian & Aboudonia, Ahmed & Hudoba de Badyn, Mathias & Heer, Philipp & Smith, Roy S. & Lygeros, John, 2022. "Physics-informed linear regression is competitive with two Machine Learning methods in residential building MPC," Applied Energy, Elsevier, vol. 310(C).
    13. Ishitsuka, Kazuya & Lin, Weiren, 2023. "Physics-informed neural network for inverse modeling of natural-state geothermal systems," Applied Energy, Elsevier, vol. 337(C).
    14. Zhang, Jincheng & Zhao, Xiaowei, 2021. "Three-dimensional spatiotemporal wind field reconstruction based on physics-informed deep learning," Applied Energy, Elsevier, vol. 300(C).
    15. Zhang, Jincheng & Zhao, Xiaowei, 2021. "Spatiotemporal wind field prediction based on physics-informed deep learning and LIDAR measurements," Applied Energy, Elsevier, vol. 288(C).
    16. Shen, Yahao & Lv, Hong & Zheng, Tao & Liu, Yi & Zhou, Wei & Zhang, Cunman, 2023. "Temporal and spatial evolution of hydrogen leakage and diffusion from tube fittings on fuel cell vehicles under the effect of ambient wind," Renewable and Sustainable Energy Reviews, Elsevier, vol. 185(C).
    17. Lv, Hong & Shen, Yahao & Zheng, Tao & Zhou, Wei & Ming, Pingwen & Zhang, Cunman, 2023. "Numerical study of hydrogen leakage, diffusion, and combustion in an outdoor parking space under different parking configurations," Renewable and Sustainable Energy Reviews, Elsevier, vol. 173(C).
    18. Di Natale, L. & Svetozarevic, B. & Heer, P. & Jones, C.N., 2023. "Towards scalable physically consistent neural networks: An application to data-driven multi-zone thermal building models," Applied Energy, Elsevier, vol. 340(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. Shi, Jihao & Li, Junjie & Zhang, Haoran & Xie, Bin & Xie, Zonghao & Yu, Qing & Yan, Jinyue, 2025. "Real-time gas explosion prediction at urban scale by GIS and graph neural network," Applied Energy, Elsevier, vol. 377(PC).

    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. Shi, Jihao & Zhang, Xinqi & Zhang, Haoran & Wang, Qiliang & Yan, Jinyue & Xiao, Linda, 2024. "Automated detection and diagnosis of leak fault considering volatility by graph deep probability learning," Applied Energy, Elsevier, vol. 361(C).
    2. Li, Rui & Zhang, Jincheng & Zhao, Xiaowei, 2022. "Dynamic wind farm wake modeling based on a Bilateral Convolutional Neural Network and high-fidelity LES data," Energy, Elsevier, vol. 258(C).
    3. 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).
    4. Jesús Rey & Francisca Segura & José Manuel Andújar, 2023. "Green Hydrogen: Resources Consumption, Technological Maturity, and Regulatory Framework," Energies, MDPI, vol. 16(17), pages 1-29, August.
    5. Li, Jianwei & Liu, Jie & Wang, Tianci & Zou, Weitao & Yang, Qingqing & Shen, Jun, 2024. "Analysis of the evolution characteristics of hydrogen leakage and diffusion in a temperature stratified environment," Energy, Elsevier, vol. 293(C).
    6. Chen, Dong & Chui, Chee-Kong & Lee, Poh Seng, 2025. "Adaptive physically consistent neural networks for data center thermal dynamics modeling," Applied Energy, Elsevier, vol. 377(PD).
    7. Yan, Chang & Xu, Shengfeng & Sun, Zhenxu & Lutz, Thorsten & Guo, Dilong & Yang, Guowei, 2024. "A framework of data assimilation for wind flow fields by physics-informed neural networks," Applied Energy, Elsevier, vol. 371(C).
    8. Tian, Runze & Kou, Peng & Zhang, Yuanhang & Mei, Mingyang & Zhang, Zhihao & Liang, Deliang, 2024. "Residual-connected physics-informed neural network for anti-noise wind field reconstruction," Applied Energy, Elsevier, vol. 357(C).
    9. Kourougianni, Fanourios & Arsalis, Alexandros & Olympios, Andreas V. & Yiasoumas, Georgios & Konstantinou, Charalampos & Papanastasiou, Panos & Georghiou, George E., 2024. "A comprehensive review of green hydrogen energy systems," Renewable Energy, Elsevier, vol. 231(C).
    10. Guo, Yanhua & Wang, Ningbo & Shao, Shuangquan & Huang, Congqi & Zhang, Zhentao & Li, Xiaoqiong & Wang, Youdong, 2024. "A review on hybrid physics and data-driven modeling methods applied in air source heat pump systems for energy efficiency improvement," Renewable and Sustainable Energy Reviews, Elsevier, vol. 204(C).
    11. Chen, Yuanqing & Wang, Ding & Feng, Dachuan & Tian, Geng & Gupta, Vikrant & Cao, Renjing & Wan, Minping & Chen, Shiyi, 2025. "Three-dimensional spatiotemporal wind field reconstruction based on LiDAR and multi-scale PINN," Applied Energy, Elsevier, vol. 377(PC).
    12. Konstantin Gomonov & Marina Reshetnikova & Svetlana Ratner, 2023. "Economic Analysis of Recently Announced Green Hydrogen Projects in Russia: A Multiple Case Study," Energies, MDPI, vol. 16(10), pages 1-15, May.
    13. Seck, Gondia Sokhna & Hache, Emmanuel & D'Herbemont, Vincent & Guyot, Mathis & Malbec, Louis-Marie, 2023. "Hydrogen development in Europe: Estimating material consumption in net zero emissions scenarios," International Economics, Elsevier, vol. 176(C).
    14. Martins, Flavio Pinheiro & De-León Almaraz, Sofía & Botelho Junior, Amilton Barbosa & Azzaro-Pantel, Catherine & Parikh, Priti, 2024. "Hydrogen and the sustainable development goals: Synergies and trade-offs," Renewable and Sustainable Energy Reviews, Elsevier, vol. 204(C).
    15. Gokhale, Gargya & Claessens, Bert & Develder, Chris, 2022. "Physics informed neural networks for control oriented thermal modeling of buildings," Applied Energy, Elsevier, vol. 314(C).
    16. Zhang, Rui & Cao, Xuewen & Zhang, Xingwang & Yang, Jian & Bian, Jiang, 2024. "Co-benefits of the liquid hydrogen economy and LNG economy: Advances in LNG integrating LH2 production processes," Energy, Elsevier, vol. 301(C).
    17. Sonja Knežević & Darko Šošić, 2024. "Isolated Work of a Multi-Energy Carrier Microgrid," Energies, MDPI, vol. 17(12), pages 1-15, June.
    18. Mohammed I. Alghamdi, 2022. "Optimization of Load Balancing and Task Scheduling in Cloud Computing Environments Using Artificial Neural Networks-Based Binary Particle Swarm Optimization (BPSO)," Sustainability, MDPI, vol. 14(19), pages 1-20, September.
    19. Jiang, Weixin & Wang, Junfang & Varbanov, Petar Sabev & Yuan, Qing & Chen, Yujie & Wang, Bohong & Yu, Bo, 2024. "Hybrid data-mechanism-driven model of the unsteady soil temperature field for long-buried crude oil pipelines with non-isothermal batch transportation," Energy, Elsevier, vol. 292(C).
    20. Gustavo Ezequiel Martinez & Roel Degens & Gabriela Espadas-Aldana & Daniele Costa & Giuseppe Cardellini, 2024. "Prospective Life Cycle Assessment of Hydrogen: A Systematic Review of Methodological Choices," Energies, MDPI, vol. 17(17), pages 1-15, August.

    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:rensus:v:207:y:2025:i:c:s1364032124006245. 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/600126/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.