Afficher la notice abrégée

Data Assimilation with Machine Learning for Dynamical Systems: Modelling Indoor Ventilation

hal.structure.identifierImperial College London
dc.contributor.authorHEANEY, Claire
hal.structure.identifierImperial College London
dc.contributor.authorTANG, Jieyi
hal.structure.identifierImperial College London
dc.contributor.authorYAN, Jintao
hal.structure.identifierImperial College London
dc.contributor.authorGUO, Donghu
hal.structure.identifierImperial College London
dc.contributor.authorIPOCK, Jamesson
hal.structure.identifierImperial College London
dc.contributor.authorKALUVAKOLLU, Sanjana
hal.structure.identifierImperial College London
hal.structure.identifierUniversity of Manchester [Manchester]
dc.contributor.authorLIN, Yushen
hal.structure.identifierImperial College London
dc.contributor.authorSHAO, Danhui
hal.structure.identifierImperial College London
dc.contributor.authorCHEN, Boyang
hal.structure.identifierImperial College London
hal.structure.identifierModélisation et calculs pour l'électrophysiologie cardiaque [CARMEN]
dc.contributor.authorMOTTET, Laetitia
hal.structure.identifierUniversity of Surrey [UNIS]
dc.contributor.authorKUMAR, Prashant
hal.structure.identifierImperial College London
dc.contributor.authorPAIN, Christopher
dc.date.accessioned2024-04-04T02:36:06Z
dc.date.available2024-04-04T02:36:06Z
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190701
dc.description.abstractEnData assimilation is a method of combining physical observations with prior knowledge (for instance, a computational simulation) in order to produce an improved model; that is, improved over what thephysical observations or the computational simulation could offer in isolation. Recently, machine learning techniques have been deployed in order to address the significant computational burden that is associated with the procedures involved in data assimilation.In this paper we propose an approach that uses a non-intrusive reduced-order model (NIROM) as a surrogate for a high-resolution model thereby saving computational effort. The mismatch between observations and the surrogate model is propagated forwards and backwards in time in a manner similar to 4D-variational data assimilation methods. The observations and prior are reconciled in a new way which takes full advantage of the neural network used in the NIROM and also means that there is no need to form the sensitivities explicitly when propagating the mismatch. Instead, the observations are part of the input and output of the network.Modelling the air quality in a school classroom is the test case for our demonstration. Firstly, the data assimilation approach is shown to perform very well in a dual-twin type experiment, and secondly, theapproach is used to assimilate observations collected from a classroom in Houndsfield Primary School with predictions from the NIROM.
dc.language.isoen
dc.subject.enmachine learning
dc.subject.endata assimilation
dc.subject.enAdversarial neural networks
dc.subject.enindoor fluid dynamics modelling
dc.title.enData Assimilation with Machine Learning for Dynamical Systems: Modelling Indoor Ventilation
dc.typeDocument de travail - Pré-publication
dc.subject.halPhysique [physics]
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
hal.identifierhal-03938455
hal.version1
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03938455v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=HEANEY,%20Claire&TANG,%20Jieyi&YAN,%20Jintao&GUO,%20Donghu&IPOCK,%20Jamesson&rft.genre=preprint


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée