The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification
In Data Assimilation, observations are fused with simulations to obtain an accurate estimate of the state and parameters for a given physical system. Combining data with a model, however, while accurately estimating uncertainty, is computationally expensive and infeasible to run in real-time for com...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-06 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Mücke, Nikolaj T Bohté, Sander M Oosterlee, Cornelis W |
description | In Data Assimilation, observations are fused with simulations to obtain an accurate estimate of the state and parameters for a given physical system. Combining data with a model, however, while accurately estimating uncertainty, is computationally expensive and infeasible to run in real-time for complex systems. Here, we present a novel particle filter methodology, the Deep Latent Space Particle filter or D-LSPF, that uses neural network-based surrogate models to overcome this computational challenge. The D-LSPF enables filtering in the low-dimensional latent space obtained using Wasserstein AEs with modified vision transformer layers for dimensionality reduction and transformers for parameterized latent space time stepping. As we demonstrate on three test cases, including leak localization in multi-phase pipe flow and seabed identification for fully nonlinear water waves, the D-LSPF runs orders of magnitude faster than a high-fidelity particle filter and 3-5 times faster than alternative methods while being up to an order of magnitude more accurate. The D-LSPF thus enables real-time data assimilation with uncertainty quantification for physical systems. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3064732671</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3064732671</sourcerecordid><originalsourceid>FETCH-proquest_journals_30647326713</originalsourceid><addsrcrecordid>eNqNjssKwjAQAIMgWNR_WPBcqEl9XEUtHjz4qGdZwhZXYlqTLeLfW8QP8DSHmcP0VKKNmabLXOuBGsd4z7JMzxd6NjOJovJGsCFqYI9CXuDcoCU4YBC2jqBgJxSgqgOcCF1a8qPrURBWMfKDHQrXHl4sN7h4S0GQvbzh2KIXrth-_Uj1K3SRxj8O1aTYlutd2oT62VKU671ug-_U1WTzfGG6v6n5r_oA73tGRA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3064732671</pqid></control><display><type>article</type><title>The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification</title><source>Free E- Journals</source><creator>Mücke, Nikolaj T ; Bohté, Sander M ; Oosterlee, Cornelis W</creator><creatorcontrib>Mücke, Nikolaj T ; Bohté, Sander M ; Oosterlee, Cornelis W</creatorcontrib><description>In Data Assimilation, observations are fused with simulations to obtain an accurate estimate of the state and parameters for a given physical system. Combining data with a model, however, while accurately estimating uncertainty, is computationally expensive and infeasible to run in real-time for complex systems. Here, we present a novel particle filter methodology, the Deep Latent Space Particle filter or D-LSPF, that uses neural network-based surrogate models to overcome this computational challenge. The D-LSPF enables filtering in the low-dimensional latent space obtained using Wasserstein AEs with modified vision transformer layers for dimensionality reduction and transformers for parameterized latent space time stepping. As we demonstrate on three test cases, including leak localization in multi-phase pipe flow and seabed identification for fully nonlinear water waves, the D-LSPF runs orders of magnitude faster than a high-fidelity particle filter and 3-5 times faster than alternative methods while being up to an order of magnitude more accurate. The D-LSPF thus enables real-time data assimilation with uncertainty quantification for physical systems.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Complex systems ; Data assimilation ; Neural networks ; Ocean floor ; Pipe flow ; Real time ; Uncertainty ; Water waves</subject><ispartof>arXiv.org, 2024-06</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Mücke, Nikolaj T</creatorcontrib><creatorcontrib>Bohté, Sander M</creatorcontrib><creatorcontrib>Oosterlee, Cornelis W</creatorcontrib><title>The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification</title><title>arXiv.org</title><description>In Data Assimilation, observations are fused with simulations to obtain an accurate estimate of the state and parameters for a given physical system. Combining data with a model, however, while accurately estimating uncertainty, is computationally expensive and infeasible to run in real-time for complex systems. Here, we present a novel particle filter methodology, the Deep Latent Space Particle filter or D-LSPF, that uses neural network-based surrogate models to overcome this computational challenge. The D-LSPF enables filtering in the low-dimensional latent space obtained using Wasserstein AEs with modified vision transformer layers for dimensionality reduction and transformers for parameterized latent space time stepping. As we demonstrate on three test cases, including leak localization in multi-phase pipe flow and seabed identification for fully nonlinear water waves, the D-LSPF runs orders of magnitude faster than a high-fidelity particle filter and 3-5 times faster than alternative methods while being up to an order of magnitude more accurate. The D-LSPF thus enables real-time data assimilation with uncertainty quantification for physical systems.</description><subject>Complex systems</subject><subject>Data assimilation</subject><subject>Neural networks</subject><subject>Ocean floor</subject><subject>Pipe flow</subject><subject>Real time</subject><subject>Uncertainty</subject><subject>Water waves</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjssKwjAQAIMgWNR_WPBcqEl9XEUtHjz4qGdZwhZXYlqTLeLfW8QP8DSHmcP0VKKNmabLXOuBGsd4z7JMzxd6NjOJovJGsCFqYI9CXuDcoCU4YBC2jqBgJxSgqgOcCF1a8qPrURBWMfKDHQrXHl4sN7h4S0GQvbzh2KIXrth-_Uj1K3SRxj8O1aTYlutd2oT62VKU671ug-_U1WTzfGG6v6n5r_oA73tGRA</recordid><startdate>20240604</startdate><enddate>20240604</enddate><creator>Mücke, Nikolaj T</creator><creator>Bohté, Sander M</creator><creator>Oosterlee, Cornelis W</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240604</creationdate><title>The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification</title><author>Mücke, Nikolaj T ; Bohté, Sander M ; Oosterlee, Cornelis W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30647326713</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Complex systems</topic><topic>Data assimilation</topic><topic>Neural networks</topic><topic>Ocean floor</topic><topic>Pipe flow</topic><topic>Real time</topic><topic>Uncertainty</topic><topic>Water waves</topic><toplevel>online_resources</toplevel><creatorcontrib>Mücke, Nikolaj T</creatorcontrib><creatorcontrib>Bohté, Sander M</creatorcontrib><creatorcontrib>Oosterlee, Cornelis W</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mücke, Nikolaj T</au><au>Bohté, Sander M</au><au>Oosterlee, Cornelis W</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification</atitle><jtitle>arXiv.org</jtitle><date>2024-06-04</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>In Data Assimilation, observations are fused with simulations to obtain an accurate estimate of the state and parameters for a given physical system. Combining data with a model, however, while accurately estimating uncertainty, is computationally expensive and infeasible to run in real-time for complex systems. Here, we present a novel particle filter methodology, the Deep Latent Space Particle filter or D-LSPF, that uses neural network-based surrogate models to overcome this computational challenge. The D-LSPF enables filtering in the low-dimensional latent space obtained using Wasserstein AEs with modified vision transformer layers for dimensionality reduction and transformers for parameterized latent space time stepping. As we demonstrate on three test cases, including leak localization in multi-phase pipe flow and seabed identification for fully nonlinear water waves, the D-LSPF runs orders of magnitude faster than a high-fidelity particle filter and 3-5 times faster than alternative methods while being up to an order of magnitude more accurate. The D-LSPF thus enables real-time data assimilation with uncertainty quantification for physical systems.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3064732671 |
source | Free E- Journals |
subjects | Complex systems Data assimilation Neural networks Ocean floor Pipe flow Real time Uncertainty Water waves |
title | The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T14%3A06%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=The%20Deep%20Latent%20Space%20Particle%20Filter%20for%20Real-Time%20Data%20Assimilation%20with%20Uncertainty%20Quantification&rft.jtitle=arXiv.org&rft.au=M%C3%BCcke,%20Nikolaj%20T&rft.date=2024-06-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3064732671%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3064732671&rft_id=info:pmid/&rfr_iscdi=true |