Data Assimilation with Machine Learning for Dynamical Systems: Modelling Indoor Ventilation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2023

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

Abstract

Data 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 the physical 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, the approach is used to assimilate observations collected from a classroom in Houndsfield Primary School with predictions from the NIROM.
Fichier principal
Vignette du fichier
26_Heaney_PhysicaA.pdf (12.7 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03938455 , version 1 (13-01-2023)

Identifiers

  • HAL Id : hal-03938455 , version 1

Cite

Claire E Heaney, Jieyi Tang, Jintao Yan, Donghu Guo, Jamesson Ipock, et al.. Data Assimilation with Machine Learning for Dynamical Systems: Modelling Indoor Ventilation. 2023. ⟨hal-03938455⟩
155 View
101 Download

Share

Gmail Facebook X LinkedIn More