EnKF data-driven reduced order assimilation system

This work presents a new predictive data assimilation framework based on a data-driven reduced order model (DDROM). The DDROM is constructed using an Auto-Encoder and a long short-term memory (LSTM) neural networks. The Auto-Encoder is used to project the high-dimensional dynamics into a lower-dimen...

Full description

Saved in:
Bibliographic Details
Published inEngineering analysis with boundary elements Vol. 139; pp. 46 - 55
Main Authors Liu, C., Fu, R., Xiao, D., Stefanescu, R., Sharma, P., Zhu, C., Sun, S., Wang, C.
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.06.2022
Subjects
Auto-Encoder
Deep learning
EnKF
LSTM
Reduced order model
Deep learning
LSTM
Reduced order model
EnKF
Auto-Encoder
Online AccessGet full text
ISSN0955-7997
1873-197X
DOI10.1016/j.enganabound.2022.02.016

Cover

More Information
Summary:This work presents a new predictive data assimilation framework based on a data-driven reduced order model (DDROM). The DDROM is constructed using an Auto-Encoder and a long short-term memory (LSTM) neural networks. The Auto-Encoder is used to project the high-dimensional dynamics into a lower-dimensional space, which can be referred as a latent space. Then, LSTM deep learning method is used to construct a number of response functions to represent the fluid states and dynamics in the latent space. A data assimilation framework based on the Ensemble Kalman Filter (EnKF) and DDROM model is then proposed. A demonstration of the capabilities of this data assimilation system is illustrated by two test cases including the 2D Burgers’ equation and the flow past a cylinder governed by Navier–Stokes equations.
ISSN:0955-7997
1873-197X
DOI:10.1016/j.enganabound.2022.02.016