No Cover Image

Journal article 320 views

MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS

Yadu Sukumarapillai, Michelle Baxter, Perumal Nithiarasu Orcid Logo

Annual Review of Heat Transfer, Volume: 28, Issue: 1, Pages: 91 - 132

Swansea University Authors: Yadu Sukumarapillai, Perumal Nithiarasu Orcid Logo

  • Accepted Manuscript under embargo until: 31st December 2026

Check full text

DOI (Published version): 10.1615/annualrevheattransfer.2025060593

Abstract

This study aims to systematically examine various methods leveraging machine learning (ML) to assimilate data for investigating thermal systems. These measured or observed data may include temperature or thermal material properties and could be synthetically (computationally) generated or experiment...

Full description

Published in: Annual Review of Heat Transfer
ISSN: 1049-0787 2375-0294
Published: Begell House 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa70159
first_indexed 2025-08-11T08:11:05Z
last_indexed 2026-01-31T05:31:51Z
id cronfa70159
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-01-30T14:52:30.3882093</datestamp><bib-version>v2</bib-version><id>70159</id><entry>2025-08-11</entry><title>MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS</title><swanseaauthors><author><sid>c590c6acde1b6ef2f880b92985494903</sid><firstname>Yadu</firstname><surname>Sukumarapillai</surname><name>Yadu Sukumarapillai</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>3b28bf59358fc2b9bd9a46897dbfc92d</sid><ORCID>0000-0002-4901-2980</ORCID><firstname>Perumal</firstname><surname>Nithiarasu</surname><name>Perumal Nithiarasu</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-08-11</date><abstract>This study aims to systematically examine various methods leveraging machine learning (ML) to assimilate data for investigating thermal systems. These measured or observed data may include temperature or thermal material properties and could be synthetically (computationally) generated or experimentally obtained. The goal of these ML-augmented methods is to derive the unknown material properties and/or reconstruct the full temperature field by integrating such measured data into physics-based computational models, such as FE models. The present work continues the previously conducted review of ML in heat transfer with a strong focus on inverse modeling techniques. It also attempts to closely incorporate ML into the FE workflow. Data assimilation and inverse modeling are closely linked tasks. While inverse modeling typically focuses on recovering unknown parameters or inputs from given observational data, data assimilation incorporates observations into dynamic models in a sequential manner, often with the goal of improving forecasting performance. In this review, we use the terms interchangeably for simplicity, though they arise from distinct methodological traditions.</abstract><type>Journal Article</type><journal>Annual Review of Heat Transfer</journal><volume>28</volume><journalNumber>1</journalNumber><paginationStart>91</paginationStart><paginationEnd>132</paginationEnd><publisher>Begell House</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1049-0787</issnPrint><issnElectronic>2375-0294</issnElectronic><keywords>Inverse heat transfer problems, Machine learning, data assimilation, deep learning, digital twin, heat transfer, finite element method</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-12-31</publishedDate><doi>10.1615/annualrevheattransfer.2025060593</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>This work is funded by the United Kingdom Atomic Energy Authority (UKAEA) and the Engineering and Physical Sciences Research Council (EPSRC) under the Grant Agreement Number EP/W524694/1.</funders><projectreference/><lastEdited>2026-01-30T14:52:30.3882093</lastEdited><Created>2025-08-11T09:06:40.8271372</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering</level></path><authors><author><firstname>Yadu</firstname><surname>Sukumarapillai</surname><order>1</order></author><author><firstname>Michelle</firstname><surname>Baxter</surname><order>2</order></author><author><firstname>Perumal</firstname><surname>Nithiarasu</surname><orcid>0000-0002-4901-2980</orcid><order>3</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2025-08-11T09:10:49.2721715</uploaded><type>Output</type><contentLength>9694304</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2026-12-31T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2026-01-30T14:52:30.3882093 v2 70159 2025-08-11 MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS c590c6acde1b6ef2f880b92985494903 Yadu Sukumarapillai Yadu Sukumarapillai true false 3b28bf59358fc2b9bd9a46897dbfc92d 0000-0002-4901-2980 Perumal Nithiarasu Perumal Nithiarasu true false 2025-08-11 This study aims to systematically examine various methods leveraging machine learning (ML) to assimilate data for investigating thermal systems. These measured or observed data may include temperature or thermal material properties and could be synthetically (computationally) generated or experimentally obtained. The goal of these ML-augmented methods is to derive the unknown material properties and/or reconstruct the full temperature field by integrating such measured data into physics-based computational models, such as FE models. The present work continues the previously conducted review of ML in heat transfer with a strong focus on inverse modeling techniques. It also attempts to closely incorporate ML into the FE workflow. Data assimilation and inverse modeling are closely linked tasks. While inverse modeling typically focuses on recovering unknown parameters or inputs from given observational data, data assimilation incorporates observations into dynamic models in a sequential manner, often with the goal of improving forecasting performance. In this review, we use the terms interchangeably for simplicity, though they arise from distinct methodological traditions. Journal Article Annual Review of Heat Transfer 28 1 91 132 Begell House 1049-0787 2375-0294 Inverse heat transfer problems, Machine learning, data assimilation, deep learning, digital twin, heat transfer, finite element method 31 12 2025 2025-12-31 10.1615/annualrevheattransfer.2025060593 COLLEGE NANME COLLEGE CODE Swansea University Not Required This work is funded by the United Kingdom Atomic Energy Authority (UKAEA) and the Engineering and Physical Sciences Research Council (EPSRC) under the Grant Agreement Number EP/W524694/1. 2026-01-30T14:52:30.3882093 2025-08-11T09:06:40.8271372 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Yadu Sukumarapillai 1 Michelle Baxter 2 Perumal Nithiarasu 0000-0002-4901-2980 3 Under embargo Under embargo 2025-08-11T09:10:49.2721715 Output 9694304 application/pdf Accepted Manuscript true 2026-12-31T00:00:00.0000000 true eng
title MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
spellingShingle MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
Yadu Sukumarapillai
Perumal Nithiarasu
title_short MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
title_full MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
title_fullStr MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
title_full_unstemmed MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
title_sort MACHINE LEARNING FOR DATA ASSIMILATION/INVERSE MODELING IN THERMAL PROBLEMS
author_id_str_mv c590c6acde1b6ef2f880b92985494903
3b28bf59358fc2b9bd9a46897dbfc92d
author_id_fullname_str_mv c590c6acde1b6ef2f880b92985494903_***_Yadu Sukumarapillai
3b28bf59358fc2b9bd9a46897dbfc92d_***_Perumal Nithiarasu
author Yadu Sukumarapillai
Perumal Nithiarasu
author2 Yadu Sukumarapillai
Michelle Baxter
Perumal Nithiarasu
format Journal article
container_title Annual Review of Heat Transfer
container_volume 28
container_issue 1
container_start_page 91
publishDate 2025
institution Swansea University
issn 1049-0787
2375-0294
doi_str_mv 10.1615/annualrevheattransfer.2025060593
publisher Begell House
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering
document_store_str 0
active_str 0
description This study aims to systematically examine various methods leveraging machine learning (ML) to assimilate data for investigating thermal systems. These measured or observed data may include temperature or thermal material properties and could be synthetically (computationally) generated or experimentally obtained. The goal of these ML-augmented methods is to derive the unknown material properties and/or reconstruct the full temperature field by integrating such measured data into physics-based computational models, such as FE models. The present work continues the previously conducted review of ML in heat transfer with a strong focus on inverse modeling techniques. It also attempts to closely incorporate ML into the FE workflow. Data assimilation and inverse modeling are closely linked tasks. While inverse modeling typically focuses on recovering unknown parameters or inputs from given observational data, data assimilation incorporates observations into dynamic models in a sequential manner, often with the goal of improving forecasting performance. In this review, we use the terms interchangeably for simplicity, though they arise from distinct methodological traditions.
published_date 2025-12-31T05:31:51Z
_version_ 1856986898798477312
score 11.096068

Similar Items