InVAErt networks: A data-driven framework for model synthesis and identifiability analysis

Simple item page
dc.article.number116846
dc.catalogadorjwg
dc.contributor.authorTong G.G.
dc.contributor.authorSing Long Collao, Carlos Alberto
dc.contributor.authorSchiavazzi D.E.
dc.date.accessioned2024-05-30T14:11:45Z
dc.date.available2024-05-30T14:11:45Z
dc.date.issued2024
dc.description.abstractUse of generative models and deep learning for physics-based systems is currently dominated by the task of emulation. However, the remarkable flexibility offered by data-driven architectures would suggest to extend this representation to other aspects of system analysis including model inversion and identifiability. We introduce InVAErt (pronounced invert) networks, a comprehensive framework for data-driven analysis and synthesis of parametric physical systems which uses a deterministic encoder and decoder to represent the forward and inverse solution maps, a normalizing flow to capture the probabilistic distribution of system outputs, and a variational encoder designed to learn a compact latent representation for the lack of bijectivity between inputs and outputs. We formally analyze how changes in the penalty coefficients affect the stationarity condition of the loss function, the phenomenon of posterior collapse, and propose strategies for latent space sampling, since we find that all these aspects significantly affect both training and testing performance. We verify our framework through extensive numerical examples, including simple linear, nonlinear, and periodic maps, dynamical systems, and spatio-temporal PDEs.
dc.description.funderCentro Nacional de Inteligencia Artificial CENIA
dc.description.funderMarco Radeschi
dc.description.funderNSF
dc.description.funderUniversity of Notre Dame
dc.description.funderFondecyt
dc.description.funderPontificia Universidad Católica de Chile
dc.description.funderANID
dc.fechaingreso.objetodigital2024-09-05
dc.fuente.origenSCOPUS
dc.identifier.doi10.1016/j.cma.2024.116846
dc.identifier.issn00457825
dc.identifier.scopusidSCOPUS_ID:85186264509
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/85983
dc.identifier.wosidWOS:001199956100001
dc.information.autorucInstituto de Ingeniería Matemática y Computacional; Sing Long Collao Carlos Alberto; 0000-0002-2533-2509; 126170
dc.language.isoen
dc.nota.accesocontenido parcial
dc.publisherElsevier B.V.
dc.revistaComputer Methods in Applied Mechanics and Engineering
dc.rightsacceso restringido
dc.subjectData-driven identifiability analysis
dc.subjectDeep neural network
dc.subjectDirect and inverse problems
dc.subjectModel synthesis
dc.subjectVariational autoencoders
dc.subject.ddc000
dc.subject.deweyCiencias de la computaciónes_ES
dc.titleInVAErt networks: A data-driven framework for model synthesis and identifiability analysis
dc.typeartículo
dc.volumen423
sipa.codpersvinculados126170
sipa.trazabilidadORCID;2024-05-27
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
InVAErt networks - A data-driven framework for model synthesis and identifiability analysis.pdf
Size:
2.92 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas