{"corpus_id":131969969,"paper_sha":"7a52bc1ce3e9ce9224491cf79b0a2b644c6433bf","doi":"10.1103/PHYSREVFLUIDS.4.034602","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2920959147,"dblp_id":null,"acl_id":null,"title":"Predictive large-eddy-simulation wall modeling via physics-informed neural networks","year":2019,"publication_date":"2019-03-15","venue":"Physical Review Fluids","journal":{"name":"Physical Review Fluids","pages":null,"volume":null},"journal_issn":null,"journal_title":null,"publication_types":[],"pubmed_pub_types":null,"s2_fields_of_study":["Physics","Computer Science","Engineering"],"reference_count":84,"citation_count":227,"influential_citation_count":3,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"A study shows that when trained using channel flow data at just one Reynolds number and informed with known flow physics, the neural network works robustly as a wall model in large-eddy simulation (LES) of channel flow at any Reynolds number. It also outperforms the equilibrium wall model in LES of a 3D boundary layer flow.","claims":[{"public_id":"cl_cd2b303a86fd807399e8330111d14c5a","status":"active","text":"A neural network trained on channel flow data at a single Reynolds number, informed with known flow physics, functions robustly as a wall model in large-eddy simulation of channel flow across different Reynolds numbers.","confidence":0.9,"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_cd2b303a86fd807399e8330111d14c5a"},{"public_id":"cl_7eec92cd84d4468693eb91cc35fa45e6","status":"active","text":"The physics-informed neural network wall model outperforms the equilibrium wall model in large-eddy simulation of a 3D boundary layer flow.","confidence":0.85,"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_7eec92cd84d4468693eb91cc35fa45e6"}],"concepts":[{"public_id":"co_00842b1921c9e0a3bbac7570798174db","status":"active","name":"equilibrium wall model","description":"A baseline wall modeling approach assuming local equilibrium near-wall behavior, used for comparison.","types":["baseline","method"],"aliases":[],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_00842b1921c9e0a3bbac7570798174db"},{"public_id":"co_41ee68694b567ba7f3284ccc45448546","status":"active","name":"large-eddy simulation","description":"A turbulence simulation technique that resolves large flow scales while modeling smaller ones.","types":["method"],"aliases":["LES"],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_41ee68694b567ba7f3284ccc45448546"},{"public_id":"co_46a92d4f6b0853be9827d5cba7a4eda0","status":"active","name":"channel flow","description":"A canonical wall-bounded turbulent flow configuration used as the training and test case in this study.","types":["flow configuration"],"aliases":[],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_46a92d4f6b0853be9827d5cba7a4eda0"},{"public_id":"co_68c0f73ae35d4eb0be7195feb7981846","status":"active","name":"physics-informed neural network","description":"A neural network trained with known flow physics incorporated, used here to predict wall model behavior for LES.","types":["method"],"aliases":["neural network wall model"],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_68c0f73ae35d4eb0be7195feb7981846"},{"public_id":"co_a54611a15a59b295798a2d427e4f6be6","status":"active","name":"wall model","description":"A modeling approach that approximates near-wall flow behavior in turbulence simulations without resolving it directly.","types":["method"],"aliases":[],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_a54611a15a59b295798a2d427e4f6be6"},{"public_id":"co_c9103de7932a85811086fef4d5a9124e","status":"active","name":"Reynolds number","description":"A dimensionless parameter characterizing the flow regime, varied here to test model generalization.","types":["parameter"],"aliases":[],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_c9103de7932a85811086fef4d5a9124e"},{"public_id":"co_ed3efc2ceafb4470aed6352348beed53","status":"active","name":"3D boundary layer flow","description":"A three-dimensional turbulent boundary layer flow case used to evaluate wall model performance.","types":["flow configuration"],"aliases":["3D boundary layer"],"contributors":[{"id":170,"public_id":"gsgmdx9r6e","public_label":"pupuri (gsgmdx9r6e)","roles":["extraction"],"url":"https://sah.borca.ai/u/gsgmdx9r6e"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_ed3efc2ceafb4470aed6352348beed53"}],"external_ids":{"DOI":"10.1103/PHYSREVFLUIDS.4.034602","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2920959147,"DBLP":null,"ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/131969969","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":631177,"paper_uid":"d815c8f7-aa9b-4b2f-87b2-e84367ea8e12","canonical_identity":{"paper_id":631177,"paper_uid":"d815c8f7-aa9b-4b2f-87b2-e84367ea8e12","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/131969969"}