Data Assimilation in the Latent Space of a Convolutional Autoencoder

Maddalena Amendola, Rossella Arcucci*, Laetitia Mottet, César Quilodrán Casas, Shiwei Fan, Christopher Pain, Paul Linden, Yi Ke Guo

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

9 Citations (Scopus)

Abstract

Data Assimilation (DA) is a Bayesian inference that combines the state of a dynamical system with real data collected by instruments at a given time. The goal of DA is to improve the accuracy of the dynamic system making its result as real as possible. One of the most popular technique for DA is the Kalman Filter (KF). When the dynamic system refers to a real world application, the representation of the state of a physical system usually leads to a big data problem. For these problems, KF results computationally too expensive and mandates to use of reduced order modeling techniques. In this paper we proposed a new methodology we called Latent Assimilation (LA). It consists in performing the KF in the latent space obtained by an Autoencoder with non-linear encoder functions and non-linear decoder functions. In the latent space, the dynamic system is represented by a surrogate model built by a Recurrent Neural Network. In particular, an Long Short Term Memory (LSTM) network is used to train a function which emulates the dynamic system in the latent space. The data from the dynamic model and the real data coming from the instruments are both processed through the Autoencoder. We apply the methodology to a real test case and we show that the LA has a good performance both in accuracy and in efficiency.

Original languageEnglish
Title of host publicationComputational Science – ICCS 2021
Subtitle of host publication21st International Conference, Krakow, Poland, June 16–18, 2021, Proceedings, Part V
EditorsMaciej Paszynski, Dieter Kranzlmüller, Valeria V. Krzhizhanovskaya, Jack J. Dongarra, Peter M. Sloot
PublisherSpringer Cham
Pages373-386
Number of pages14
Edition1st
ISBN (Electronic)9783030779771
ISBN (Print)9783030779764
DOIs
Publication statusPublished - 9 Jun 2021
Event21st International Conference on Computational Science, ICCS 2021 - Virtual, Krakow, Poland
Duration: 16 Jun 202118 Jun 2021
https://www.iccs-meeting.org/iccs2021/
https://link.springer.com/conference/iccs-computsci

Publication series

NameLecture Notes in Computer Science
Volume12746
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameTheoretical Computer Science and General Issues
NameICCS: International Conference on Computational Science

Conference

Conference21st International Conference on Computational Science, ICCS 2021
Country/TerritoryPoland
CityVirtual, Krakow
Period16/06/2118/06/21
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • Computer Science(all)

User-Defined Keywords

  • Convolutional autoencoder
  • Data assimilation
  • Long short term memory
  • Machine learning
  • Neural network

Fingerprint

Dive into the research topics of 'Data Assimilation in the Latent Space of a Convolutional Autoencoder'. Together they form a unique fingerprint.

Cite this