Show simple item record

dc.contributor.authorBlakseth, Sindre Stenen
dc.contributor.authorRasheed, Adil
dc.contributor.authorKvamsdal, Trond
dc.contributor.authorSan, Omer
dc.date.accessioned2022-09-19T13:57:09Z
dc.date.available2022-09-19T13:57:09Z
dc.date.created2022-06-08T03:33:10Z
dc.date.issued2022
dc.identifier.citationApplied Soft Computing. 2022, 128, 109533.en_US
dc.identifier.issn1568-4946
dc.identifier.urihttps://hdl.handle.net/11250/3018976
dc.description.abstractUpcoming technologies like digital twins, autonomous, and artificial intelligent systems involving safety–critical applications require accurate, interpretable, computationally efficient, and generalizable models. Unfortunately, the two most commonly used modeling approaches, physics-based modeling (PBM) and data-driven modeling (DDM) struggle to satisfy all these requirements. In the current work, we demonstrate how a hybrid approach combining the best of PBM and DDM can result in models that can outperform both of them. We do so by combining partial differential equations based on first principles describing partially known physics with a black box DDM, in this case, a deep neural network model compensating for the unknown physics. The novelty of the work is in the theoretical contribution of presenting a sound mathematical argument for why the approach should work. The argument is backed by an array of experiments involving a two-dimensional heat diffusion problem with unknown source terms. The hybrid approach demonstrates the method’s superior performance in accuracy and generalizability. Additionally, it is shown how the DDM part can be interpreted within the hybrid framework to make the overall approach reliable. The approach, as we see, will be a door opener for underutilized DDMs in high stake applications.en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.subjectDeep neural networksen_US
dc.subjectReliable hybrid analysis and modelingen_US
dc.subjectPhysics-based modelingen_US
dc.subjectData-driven modelingen_US
dc.titleCombining physics-based and data-driven techniques for reliable hybrid analysis and modeling using the corrective source term approachen_US
dc.title.alternativeCombining physics-based and data-driven techniques for reliable hybrid analysis and modeling using the corrective source term approachen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.rights.holder© 2022 The Author(s)en_US
dc.source.pagenumber20en_US
dc.source.volume128en_US
dc.source.journalApplied Soft Computingen_US
dc.identifier.doi10.1016/j.asoc.2022.109533
dc.identifier.cristin2030101
dc.relation.projectNorges forskningsråd: 313909en_US
dc.relation.projectNorges forskningsråd: 308823en_US
dc.relation.projectNorges forskningsråd: 304843en_US
dc.source.articlenumber109533en_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode2


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal