Show simple item record

dc.contributor.authorPeng, Grace C Y
dc.contributor.authorAlber, Mark
dc.contributor.authorTepole, Adrian Buganza
dc.contributor.authorCannon, William R
dc.contributor.authorDe, Suvranu
dc.contributor.authorDura-Bernal, Salvador
dc.contributor.authorGarikipati, Krishna
dc.contributor.authorKarniadakis, George
dc.contributor.authorLytton, William W
dc.contributor.authorPerdikaris, Paris
dc.contributor.authorPetzold, Linda
dc.contributor.authorKuhl, Ellen
dc.date.accessioned2023-04-10T15:54:40Z
dc.date.available2023-04-10T15:54:40Z
dc.date.issued2020-02-17
dc.identifier.citationPeng GCY, Alber M, Tepole AB, Cannon WR, De S, Dura-Bernal S, Garikipati K, Karniadakis G, Lytton WW, Perdikaris P, Petzold L, Kuhl E. Multiscale modeling meets machine learning: What can we learn? Arch Comput Methods Eng. 2021 May;28(3):1017-1037. doi: 10.1007/s11831-020-09405-5. Epub 2020 Feb 17. PMID: 34093005; PMCID: PMC8172124.en_US
dc.identifier.eissn1886-1784
dc.identifier.doi10.1007/s11831-020-09405-5
dc.identifier.pmid34093005
dc.identifier.urihttp://hdl.handle.net/20.500.12648/8563
dc.description.abstractMachine learning is increasingly recognized as a promising technology in the biological, biomedical, and behavioral sciences. There can be no argument that this technique is incredibly successful in image recognition with immediate applications in diagnostics including electrophysiology, radiology, or pathology, where we have access to massive amounts of annotated data. However, machine learning often performs poorly in prognosis, especially when dealing with sparse data. This is a field where classical physics-based simulation seems to remain irreplaceable. In this review, we identify areas in the biomedical sciences where machine learning and multiscale modeling can mutually benefit from one another: Machine learning can integrate physics-based knowledge in the form of governing equations, boundary conditions, or constraints to manage ill-posted problems and robustly handle sparse and noisy data; multiscale modeling can integrate machine learning to create surrogate models, identify system dynamics and parameters, analyze sensitivities, and quantify uncertainty to bridge the scales and understand the emergence of function. With a view towards applications in the life sciences, we discuss the state of the art of combining machine learning and multiscale modeling, identify applications and opportunities, raise open questions, and address potential challenges and limitations. We anticipate that it will stimulate discussion within the community of computational mechanics and reach out to other disciplines including mathematics, statistics, computer science, artificial intelligence, biomedicine, systems biology, and precision medicine to join forces towards creating robust and efficient models for biological systems.
dc.language.isoenen_US
dc.relation.urlhttps://link.springer.com/article/10.1007/s11831-020-09405-5en_US
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectMachine learningen_US
dc.subjectbiomedicineen_US
dc.subjectmultiscale modelingen_US
dc.subjectphysics-based simulationen_US
dc.titleMultiscale modeling meets machine learning: What can we learn?en_US
dc.typeArticle/Reviewen_US
dc.source.journaltitleArchives of computational methods in engineering : state of the art reviewsen_US
dc.source.volume28
dc.source.issue3
dc.source.beginpage1017
dc.source.endpage1037
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryUnited States
dc.source.countryNetherlands
dc.description.versionAMen_US
refterms.dateFOA2023-04-10T15:54:40Z
html.description.abstractMachine learning is increasingly recognized as a promising technology in the biological, biomedical, and behavioral sciences. There can be no argument that this technique is incredibly successful in image recognition with immediate applications in diagnostics including electrophysiology, radiology, or pathology, where we have access to massive amounts of annotated data. However, machine learning often performs poorly in prognosis, especially when dealing with sparse data. This is a field where classical physics-based simulation seems to remain irreplaceable. In this review, we identify areas in the biomedical sciences where machine learning and multiscale modeling can mutually benefit from one another: Machine learning can integrate physics-based knowledge in the form of governing equations, boundary conditions, or constraints to manage ill-posted problems and robustly handle sparse and noisy data; multiscale modeling can integrate machine learning to create surrogate models, identify system dynamics and parameters, analyze sensitivities, and quantify uncertainty to bridge the scales and understand the emergence of function. With a view towards applications in the life sciences, we discuss the state of the art of combining machine learning and multiscale modeling, identify applications and opportunities, raise open questions, and address potential challenges and limitations. We anticipate that it will stimulate discussion within the community of computational mechanics and reach out to other disciplines including mathematics, statistics, computer science, artificial intelligence, biomedicine, systems biology, and precision medicine to join forces towards creating robust and efficient models for biological systems.
dc.description.institutionN/Aen_US
dc.description.departmentNathan Kline Institute for Psychiatric Researchen_US
dc.description.departmentPhysiology and Pharmacologyen_US
dc.description.degreelevelN/Aen_US
dc.identifier.journalArchives of computational methods in engineering : state of the art reviews


Files in this item

Thumbnail
Name:
nihms-1562951.pdf
Size:
1.779Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 International
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International