{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:13:06Z","timestamp":1788221586583,"version":"build-2803163510"},"reference-count":36,"publisher":"American Chemical Society (ACS)","issue":"33","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/na","name":"State Key Laboratory of Chemical Safety","doi-asserted-by":"publisher","award":["SKLCS-2024022"],"award-info":[{"award-number":["SKLCS-2024022"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Hydrogen fuel cell vehicles are being increasingly introduced as low-carbon transport systems. Nevertheless, unintended hydrogen release and ignition may still cause severe explosion hazards, especially in densely built urban settings. Conventional data-driven methods may have difficulty representing obstacle-induced spatial interactions and the transient development of explosion fields. To address this issue, this work develops a physics-informed Transformer framework for real-time prediction of hydrogen explosion scenarios associated with fuel cell vehicles. In this study, \u201cphysics-informed\u201d refers to a flame-informed regularization mechanism rather than a conventional residual-based physics-informed neural network. Specifically, the intrinsic coupling between flame propagation and overpressure evolution is embedded into the Transformer learning objective, enabling the model to learn the relationship between flame-front development and blast-wave evolution instead of merely fitting isolated pressure-field snapshots. A high-fidelity benchmark database was generated through CFD simulations of hydrogen explosions in representative urban blocks. Based on this database, the optimal weighting coefficient was identified as \u03bb = 0.001. Under this configuration, the model achieved an R2 of 0.9385 and an MSE of 1.28 \u00d7 10\u20134 for blast-wave prediction and an R2 of 0.9455 and an MSE of 9.58 \u00d7 10\u20134 for peak-overpressure prediction while requiring only 2.33 s for inference. The proposed approach offers a computationally efficient surrogate for rapid consequence assessment and provides technical support for digital-twin-based urban hydrogen safety management.<\/jats:p>","DOI":"10.1021\/acsomega.6c05805","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:02:04Z","timestamp":1786554124000},"page":"50208-50218","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Prediction\nof Hydrogen Explosions Involving\nFuel Cell Vehicles Using a Physics-Informed Transformer Model"],"prefix":"10.1021","volume":"11","author":[{"given":"Kang","family":"Yu","sequence":"first","affiliation":[{"name":"SINOPEC Research Institute of Safety Engineering Co., Ltd. , , ,","place":["Qingdao, China, 266104"]},{"name":"Ministry of Emergency Management , , ,","place":["Qingdao, China, 266104"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7973-0310","authenticated-orcid":true,"given":"Junjie","family":"Li","sequence":"additional","affiliation":[{"name":"China University of Petroleum , , ,","place":["Qingdao, China, 266580"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4105-9207","authenticated-orcid":true,"given":"Xinqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"SINOPEC Research Institute of Safety Engineering Co., Ltd. , , ,","place":["Qingdao, China, 266104"]},{"name":"Ministry of Emergency Management , , ,","place":["Qingdao, China, 266104"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghao","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University , , , ,","place":["Kowloon, Hong Kong, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"SINOPEC Research Institute of Safety Engineering Co., Ltd. , , ,","place":["Qingdao, China, 266104"]},{"name":"Ministry of Emergency Management , , ,","place":["Qingdao, China, 266104"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anfeng","family":"Yu","sequence":"additional","affiliation":[{"name":"SINOPEC Research Institute of Safety Engineering Co., Ltd. , , ,","place":["Qingdao, China, 266104"]},{"name":"Ministry of Emergency Management , , ,","place":["Qingdao, China, 266104"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"2026083119135098900_cit1","doi-asserted-by":"publisher","first-page":"121300","DOI":"10.1016\/j.renene.2024.121300","article-title":"Effects of relative position of dual vents in the passenger cabin\nof fuel cell bus on leaking hydrogen dispersion","volume":"235","author":"Li","year":"2024","journal-title":"Renewable Energy"},{"issue":"75","key":"2026083119135098900_cit2","doi-asserted-by":"publisher","first-page":"37679","DOI":"10.1016\/j.ijhydene.2021.02.130","article-title":"Development of emergency\nresponse strategies for typical accidents\nof hydrogen fuel cell electric vehicles","volume":"46","author":"Sun","year":"2021","journal-title":"Int.\nJ. Hydrogen Energy"},{"issue":"17","key":"2026083119135098900_cit3","doi-asserted-by":"publisher","first-page":"8954","DOI":"10.1016\/j.ijhydene.2018.07.074","article-title":"Comparisons of hazard\ndistances and accident durations between hydrogen\nvehicles and CNG vehicles","volume":"44","author":"Li","year":"2019","journal-title":"Int. J. Hydrogen\nEnergy"},{"issue":"3","key":"2026083119135098900_cit4","doi-asserted-by":"publisher","first-page":"2436","DOI":"10.1016\/j.ijhydene.2010.04.056","article-title":"Experimental study\nof hydrogen release accidents in a vehicle garage","volume":"36","author":"Merilo","year":"2011","journal-title":"Int. J. Hydrogen Energy"},{"key":"2026083119135098900_cit5","doi-asserted-by":"publisher","first-page":"229450","DOI":"10.1016\/j.jpowsour.2021.229450","article-title":"Sensing advancement\ntowards safety assessment of hydrogen\nfuel cell vehicles","volume":"489","author":"Foorginezhad","year":"2021","journal-title":"J. Power Sources"},{"issue":"17","key":"2026083119135098900_cit6","doi-asserted-by":"publisher","first-page":"8791","DOI":"10.1016\/j.ijhydene.2018.10.065","article-title":"Quantitative risk analysis\nof life safety and financial loss for\nroad accident of fuel cell vehicle","volume":"44","author":"Sun","year":"2019","journal-title":"Int. J.\nHydrogen Energy"},{"key":"2026083119135098900_cit7","volume-title":"Dispersion of unintended\nsubsonic and supersonic hydrogen releases from hydrogen storage systems","author":"Li","year":"2015"},{"key":"2026083119135098900_cit8","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.ijhydene.2024.08.105","article-title":"Research on hydrogen\nleakage diffusion and safety analysis in hydrogen fuel cell vehicles\nwith regard to leakage location and ventilation ports","volume":"83","author":"Song","year":"2024","journal-title":"Int. J. Hydrogen Energy"},{"key":"2026083119135098900_cit9","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1016\/j.ijhydene.2024.05.410","article-title":"Real time hydrogen\nplume spatiotemporal evolution forecasting by\nusing deep probabilistic spatial-temporal neural network","volume":"72","author":"Li","year":"2024","journal-title":"Int. J. Hydrogen Energy"},{"key":"2026083119135098900_cit10","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.jlp.2019.01.001","article-title":"Theoretical\npressure prediction of confined hydrogen\nexplosion considering flame instabilities","volume":"57","author":"Li","year":"2019","journal-title":"J.\nLoss Prev. Process Ind."},{"key":"2026083119135098900_cit11","doi-asserted-by":"publisher","first-page":"134310","DOI":"10.1016\/j.fuel.2025.134310","article-title":"Characterization and overpressure\nprediction modeling of explosions of stratified hydrogen clouds in\nopen space","volume":"387","author":"Wang","year":"2025","journal-title":"Fuel"},{"key":"2026083119135098900_cit12","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1016\/j.psep.2024.07.100","article-title":"Prediction\nof peak overpressure from\nhydrogen-air cloud explosions in vented cylindrical vessels","volume":"190","author":"Hu","year":"2024","journal-title":"Process Saf. Environ. Prot."},{"issue":"23","key":"2026083119135098900_cit13","doi-asserted-by":"publisher","first-page":"12838","DOI":"10.3390\/app132312838","article-title":"A computational\nstudy of hydrogen dispersion and explosion after large-scale leakage\nof liquid hydrogen","volume":"13","author":"Choi","year":"2023","journal-title":"Appl. Sci."},{"issue":"38","key":"2026083119135098900_cit14","doi-asserted-by":"publisher","first-page":"21067","DOI":"10.1016\/j.ijhydene.2019.01.225","article-title":"Failure of reinforced\nconcrete and\ntuff stone masonry buildings as consequence of hydrogen pipeline explosions","volume":"44","author":"Russo","year":"2019","journal-title":"Int. J. Hydrogen Energy"},{"issue":"7","key":"2026083119135098900_cit15","doi-asserted-by":"publisher","first-page":"3075","DOI":"10.1016\/j.ijhydene.2014.12.057","article-title":"Methodology of CFD\nanalysis for evaluating H2 explosion accidents in an open\nspace","volume":"40","author":"Kang","year":"2015","journal-title":"Int. J. Hydrogen Energy"},{"key":"2026083119135098900_cit16","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.psep.2021.09.016","article-title":"Numerical and experimental analysis\nof jet release and jet flame length for qualitative risk analysis\nat hydrogen refueling station","volume":"155","author":"Park","year":"2021","journal-title":"Process Saf.\nEnviron. Prot."},{"key":"2026083119135098900_cit17","doi-asserted-by":"publisher","first-page":"104920","DOI":"10.1016\/j.jlp.2022.104920","article-title":"A state-of-the-art\nreview of experimental and numerical\nstudies on BLEVE overpressure prediction","volume":"80","author":"Wang","year":"2022","journal-title":"J.\nLoss Prev. Process Ind."},{"key":"2026083119135098900_cit18","doi-asserted-by":"publisher","first-page":"121044","DOI":"10.1016\/j.eswa.2023.121044","article-title":"Prediction\nof venting gas explosion overpressure based on a combination of explosive\ntheory and machine learning","volume":"234","author":"Xu","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"2026083119135098900_cit19","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.oceaneng.2018.12.045","article-title":"Stochastic\nanalysis of explosion risk for ultra-deep-water semi-submersible offshore\nplatforms","volume":"172","author":"Shi","year":"2019","journal-title":"Ocean Eng."},{"key":"2026083119135098900_cit20","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jlp.2018.10.009","article-title":"Application of Bayesian Regularization\nArtificial Neural Network in explosion risk analysis of fixed offshore\nplatform","volume":"57","author":"Shi","year":"2019","journal-title":"J. Loss Prev. Process Ind."},{"issue":"12","key":"2026083119135098900_cit21","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.3390\/pr12122946","article-title":"Prediction of a hydrogen\nvapor cloud explosion with a barrier wall\nusing various machine learning methods","volume":"12","author":"Min","year":"2024","journal-title":"Processes"},{"key":"2026083119135098900_cit22","doi-asserted-by":"publisher","first-page":"129361","DOI":"10.1016\/j.energy.2023.129361","article-title":"Hydrogen leakage location prediction at hydrogen refueling\nstations based on deep learning","volume":"284","author":"Bi","year":"2023","journal-title":"Energy"},{"key":"2026083119135098900_cit23","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1016\/j.psep.2021.03.018","article-title":"Prediction of BLEVE\nblast loading\nusing CFD and artificial neural network","volume":"149","author":"Li","year":"2021","journal-title":"Process\nSaf. Environ. Prot."},{"key":"2026083119135098900_cit24","doi-asserted-by":"publisher","first-page":"114244","DOI":"10.1016\/j.oceaneng.2023.114244","article-title":"Real-time natural gas\nexplosion modeling\nof offshore platforms by using deep learning probability approach","volume":"276","author":"Shi","year":"2023","journal-title":"Ocean Eng."},{"key":"2026083119135098900_cit25","doi-asserted-by":"publisher","first-page":"105386","DOI":"10.1016\/j.jlp.2024.105386","article-title":"Flame propagation speed\nprediction model of premixed methane gas\ndeflagration experiments based on Adamax-LSTM for FLNG","volume":"91","author":"Wang","year":"2024","journal-title":"J. Loss Prev. Process Ind."},{"key":"2026083119135098900_cit26","doi-asserted-by":"publisher","first-page":"119572","DOI":"10.1016\/j.energy.2020.119572","article-title":"Probabilistic\nreal-time deep-water natural gas hydrate dispersion modeling by using\na novel hybrid deep learning approach","volume":"219","author":"Shi","year":"2021","journal-title":"Energy"},{"key":"2026083119135098900_cit27","doi-asserted-by":"publisher","first-page":"123461","DOI":"10.1016\/j.renene.2025.123461","article-title":"Domain adaptation based high-fidelity\nprediction for\nhydrogen-blended natural gas leakage and dispersion","volume":"252","author":"Li","year":"2025","journal-title":"Renewable Energy"},{"key":"2026083119135098900_cit28","doi-asserted-by":"publisher","first-page":"110777","DOI":"10.1016\/j.ress.2024.110777","article-title":"Physics_GNN: Towards\nPhysics-informed graph neural network for the real-time simulation\nof obstructed gas explosion","volume":"256","author":"Shi","year":"2025","journal-title":"Reliab. Eng. Syst.\nSaf."},{"issue":"2","key":"2026083119135098900_cit29","doi-asserted-by":"publisher","first-page":"9590012","DOI":"10.26599\/SES.2025.9590012","article-title":"Probabilistic\ngraph neural network-based\nreal-time hydrogen gas explosion prediction from hydrogen production\nplants","volume":"1","author":"Li","year":"2025","journal-title":"Safety Emergency Science"},{"issue":"23","key":"2026083119135098900_cit30","doi-asserted-by":"publisher","first-page":"12464","DOI":"10.1016\/j.ijhydene.2020.09.073","article-title":"Simulating\nvented hydrogen deflagrations: Improved modelling in the CFD tool\nFLACS-hydrogen","volume":"46","author":"Lucas","year":"2021","journal-title":"Int. J. Hydrogen Energy"},{"key":"2026083119135098900_cit31","unstructured":"Middha, P.; Hansen, O. R.; Groethe, M.; Arntzen, B. J.\n          Hydrogen explosion\nstudy in a confined tube: FLACS CFD simulations and experiments. In  Proceedings of 21st International Colloquium of Dynamics\nof Explosions and Reactive Systems; Poitiers: France, 2007."},{"key":"2026083119135098900_cit32","doi-asserted-by":"publisher","first-page":"115416","DOI":"10.1016\/j.engappai.2026.115416","article-title":"Physics-assisted\ndeep\nprobability learning for natural gas leakage detection from infrared\ncameras without anomaly data","volume":"181","author":"Li","year":"2026","journal-title":"Eng. Appl. Artif.\nIntell."},{"key":"2026083119135098900_cit33","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1016\/j.ijhydene.2023.04.126","article-title":"Real-time hydrogen\nrelease and dispersion modelling of hydrogen refuelling station by\nusing deep learning probability approach","volume":"51","author":"Li","year":"2024","journal-title":"Int.\nJ. Hydrogen Energy"},{"issue":"24","key":"2026083119135098900_cit34","doi-asserted-by":"publisher","first-page":"13535","DOI":"10.1016\/j.ijhydene.2020.03.040","article-title":"Stochastic\nexplosion risk analysis\nof hydrogen production facilities","volume":"45","author":"Shi","year":"2020","journal-title":"Int. J. Hydrogen\nEnergy"},{"key":"2026083119135098900_cit35","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.psep.2023.02.008","article-title":"Prediction of BLEVE\nloads on structures using machine learning and\nCFD","volume":"171","author":"Li","year":"2023","journal-title":"Process Saf. Environ. Prot."},{"key":"2026083119135098900_cit36","article-title":"Attention\nis all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process.\nSyst."}],"container-title":["ACS Omega"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsomega.6c05805","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/33\/50208\/66516360\/acsomega.6c05805.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/33\/50208\/66516360\/acsomega.6c05805.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T23:14:00Z","timestamp":1788218040000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/acsodf\/article\/11\/33\/50208\/5253706\/Real-Time-Prediction-of-Hydrogen-Explosions"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":36,"journal-issue":{"issue":"33","published-online":{"date-parts":[[2026,8,12]]},"published-print":{"date-parts":[[2026,8,25]]}},"URL":"https:\/\/doi.org\/10.1021\/acsomega.6c05805","relation":{},"ISSN":["2470-1343"],"issn-type":[{"value":"2470-1343","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]}}}