{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:04:27Z","timestamp":1780725867794,"version":"3.54.1"},"reference-count":25,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004595","name":"Universiti Sains Malaysia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Communications in Nonlinear Science and Numerical Simulation"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.cnsns.2026.110150","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T15:39:30Z","timestamp":1779464370000},"page":"110150","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P3","title":["Boundary-layer accuracy does not guarantee correct Nusselt scaling: Failure modes of physics-informed neural networks in high-Rayleigh-number Rayleigh\u2013B\u00e9nard convection"],"prefix":"10.1016","volume":"161","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7823-2459","authenticated-orcid":false,"given":"Shatha","family":"Alarman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2843-7082","authenticated-orcid":false,"given":"Saratha","family":"Sathasivam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.cnsns.2026.110150_bib0001","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1103\/RevModPhys.81.503","article-title":"Heat transfer and large-scale dynamics in turbulent Rayleigh\u2013B\u00e9nard convection","volume":"81","author":"Ahlers","year":"2009","journal-title":"Rev Mod Phys"},{"key":"10.1016\/j.cnsns.2026.110150_bib0002","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1017\/jfm.2013.298","article-title":"Boundary layers in rotating Rayleigh\u2013B\u00e9nard convection","volume":"730","author":"Stevens","year":"2013","journal-title":"J Fluid Mech"},{"key":"10.1016\/j.cnsns.2026.110150_bib0003","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","article-title":"Physics-informed neural networks: a deep learning framework for solving partial differential equations","volume":"378","author":"Raissi","year":"2019","journal-title":"J Comput Phys"},{"issue":"34","key":"10.1016\/j.cnsns.2026.110150_bib0004","article-title":"Characterizing possible failure modes in physics-informed neural networks","volume":"118","author":"Krishnapriyan","year":"2021","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"10.1016\/j.cnsns.2026.110150_bib0005","first-page":"A2156","article-title":"When and why PINNs fail to train: a neural tangent kernel perspective","volume":"44","author":"Wang","year":"2022","journal-title":"SIAM J Sci Comput"},{"key":"10.1016\/j.cnsns.2026.110150_bib0006","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1017\/S0022112099007545","article-title":"Scaling in thermal convection: a unifying theory","volume":"407","author":"Grossmann","year":"2000","journal-title":"J Fluid Mech"},{"issue":"12","key":"10.1016\/j.cnsns.2026.110150_bib0007","doi-asserted-by":"crossref","first-page":"4462","DOI":"10.1063\/1.1807751","article-title":"Fluctuations in turbulent Rayleigh\u2013B\u00e9nard convection: the role of plumes","volume":"16","author":"Grossmann","year":"2004","journal-title":"Phys Fluids"},{"key":"10.1016\/j.cnsns.2026.110150_bib0008","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1017\/jfm.2012.207","article-title":"Boundary layer structure in turbulent Rayleigh\u2013B\u00e9nard convection","volume":"706","author":"Shi","year":"2012","journal-title":"J Fluid Mech"},{"key":"10.1016\/j.cnsns.2026.110150_bib0009","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1017\/jfm.2013.488","article-title":"Comparison between two- and three-dimensional Rayleigh\u2013B\u00e9nard convection","volume":"736","author":"van der Poel","year":"2013","journal-title":"J Fluid Mech"},{"key":"10.1016\/j.cnsns.2026.110150_bib0010","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1017\/jfm.2011.354","article-title":"Prandtl and Rayleigh number dependence of heat transport in high Rayleigh number thermal convection","volume":"688","author":"Stevens","year":"2011","journal-title":"J Fluid Mech"},{"key":"10.1016\/j.cnsns.2026.110150_bib0011","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","article-title":"Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators","volume":"3","author":"Lu","year":"2021","journal-title":"Nat Mach Intell"},{"key":"10.1016\/j.cnsns.2026.110150_bib0012","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed machine learning","volume":"3","author":"Karniadakis","year":"2021","journal-title":"Nat Rev Phys"},{"issue":"6","key":"10.1016\/j.cnsns.2026.110150_bib0013","doi-asserted-by":"crossref","DOI":"10.1115\/1.4050542","article-title":"Physics-informed neural networks for heat transfer problems","volume":"143","author":"Cai","year":"2021","journal-title":"J Heat Transf"},{"key":"10.1016\/j.cnsns.2026.110150_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2022.111022","article-title":"Simple computational strategies for more effective physics-informed neural networks modeling of turbulent natural convection","volume":"456","author":"Lucor","year":"2022","journal-title":"J Comput Phys"},{"key":"10.1016\/j.cnsns.2026.110150_bib0015","article-title":"Challenges of PINNs in stiff PDEs","author":"Mishra","year":"2023","journal-title":"Phys Fluids"},{"key":"10.1016\/j.cnsns.2026.110150_bib0016","article-title":"Conservative physics-informed neural networks on discrete domains for conservation laws: applications to forward and inverse problems","volume":"407","author":"Jagtap","year":"2020","journal-title":"J Comput Phys"},{"key":"10.1016\/j.cnsns.2026.110150_bib0017","article-title":"Surrogate modeling for Navier\u2013Stokes equations with physics-informed neural networks","volume":"361","author":"Sun","year":"2020","journal-title":"Comput Methods Appl Mech Eng"},{"issue":"Part A","key":"10.1016\/j.cnsns.2026.110150_bib0018","article-title":"A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks","volume":"403","author":"Wu","year":"2023","journal-title":"Comput Methods Appl Mech Eng"},{"key":"10.1016\/j.cnsns.2026.110150_bib0019","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neucom.2022.05.015","article-title":"Self-adaptive loss balanced physics-informed neural networks","volume":"496","author":"Xiang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cnsns.2026.110150_bib0020","article-title":"Flow organization and thermal plume dynamics in Rayleigh\u2013B\u00e9nard convection","volume":"907","author":"Blass","year":"2020","journal-title":"J Fluid Mech"},{"key":"10.1016\/j.cnsns.2026.110150_bib0021","article-title":"Thermal plume dynamics and large-scale circulation in convection","volume":"122","author":"Ching","year":"2019","journal-title":"Phys Rev Lett"},{"key":"10.1016\/j.cnsns.2026.110150_bib0022","article-title":"Physics-informed neural networks for laminar convection: limitations and boundary errors","volume":"179","author":"Wang","year":"2021","journal-title":"Int J Heat Mass Transf"},{"key":"10.1016\/j.cnsns.2026.110150_bib0023","article-title":"Understanding the failure modes of PINNs in convection-dominated flows","volume":"457","author":"Cai","year":"2022","journal-title":"J Comput Phys"},{"key":"10.1016\/j.cnsns.2026.110150_bib0024","first-page":"568","article-title":"Comparison of turbulent thermal convection between conditions of constant temperature and constant flux","volume":"691","author":"Johnston","year":"2012","journal-title":"J Fluid Mech"},{"key":"10.1016\/j.cnsns.2026.110150_bib0025","first-page":"411","article-title":"Direct numerical simulation of Rayleigh\u2013B\u00e9nard convection at high Rayleigh numbers","volume":"837","author":"Zhu","year":"2018","journal-title":"J Fluid Mech"}],"container-title":["Communications in Nonlinear Science and Numerical Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1007570426005095?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1007570426005095?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T05:33:56Z","timestamp":1780724036000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1007570426005095"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":25,"alternative-id":["S1007570426005095"],"URL":"https:\/\/doi.org\/10.1016\/j.cnsns.2026.110150","relation":{},"ISSN":["1007-5704"],"issn-type":[{"value":"1007-5704","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Boundary-layer accuracy does not guarantee correct Nusselt scaling: Failure modes of physics-informed neural networks in high-Rayleigh-number Rayleigh\u2013B\u00e9nard convection","name":"articletitle","label":"Article Title"},{"value":"Communications in Nonlinear Science and Numerical Simulation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cnsns.2026.110150","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"110150"}}