No Cover Image

Journal article 73 views 7 downloads

Physics-informed long short-term memory network with data folding for efficient site seismic response prediction

Yongxin Wu, Zhanpeng Yin, Juncheng Wang, Yue Hou Orcid Logo, Haodong Shang, Houle Zhang

Computer-Aided Civil and Infrastructure Engineering, Volume: 44, Start page: 100054

Swansea University Author: Yue Hou Orcid Logo

  • 71969.VoR.pdf

    PDF | Version of Record

    © 2026 The Author(s). This is an open access article under the CC BY-NC-ND license.

    Download (4.66MB)

Check full text

DOI (Published version): 10.1016/j.cacaie.2026.100054

Abstract

Accurate prediction of site seismic response is essential for earthquake engineering and seismic design. Numerical simulation methods, although physically rigorous, become computationally intensive when soils exhibit complex nonlinear behavior and are sensitive to constitutive model selection and pa...

Full description

Published in: Computer-Aided Civil and Infrastructure Engineering
ISSN: 1093-9687
Published: Elsevier BV 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71969
first_indexed 2026-05-21T11:41:57Z
last_indexed 2026-06-09T08:55:03Z
id cronfa71969
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-06-08T15:28:05.0262989</datestamp><bib-version>v2</bib-version><id>71969</id><entry>2026-05-21</entry><title>Physics-informed long short-term memory network with data folding for efficient site seismic response prediction</title><swanseaauthors><author><sid>92bf566c65343cb3ee04ad963eacf31b</sid><ORCID>0000-0002-4334-2620</ORCID><firstname>Yue</firstname><surname>Hou</surname><name>Yue Hou</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-05-21</date><deptcode>ACEM</deptcode><abstract>Accurate prediction of site seismic response is essential for earthquake engineering and seismic design. Numerical simulation methods, although physically rigorous, become computationally intensive when soils exhibit complex nonlinear behavior and are sensitive to constitutive model selection and parameter calibration. Data&#x2011;driven deep learning models can approximate nonlinear mappings efficiently, yet they lack built&#x2011;in physical constraints and risk producing predictions that violate fundamental mechanics when extrapolating beyond the training domain. This study presents a physics&#x2011;informed deep long short-term memory (LSTM) framework for efficient and accurate site seismic response prediction. The framework enforces physical consistency by adding kinematic derivative relationships as soft constraints in the loss function and improves training efficiency by using Data folding modules. A targeted data augmentation strategy addresses measurement noise and signal variability in recorded data. Comprehensive validation on numerically simulated events and on KiK&#x2011;net recordings shows the effectiveness of the methodology. On numerical data, the physics&#x2011;informed model reaches a 97.98% confidence level within &#xB1;2% normalized error and reduces training time by more than 60%. On recorded data, the enhanced model with data augmentation reaches an 88.84% confidence level and a response spectrum correlation of 0.951, which supports reliable prediction of frequency content for engineering use. The framework provides an efficient and physically consistent solution for site response prediction with implications for seismic hazard assessment and structural design.</abstract><type>Journal Article</type><journal>Computer-Aided Civil and Infrastructure Engineering</journal><volume>44</volume><journalNumber/><paginationStart>100054</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1093-9687</issnPrint><issnElectronic/><keywords>Physics-informed neural networks; Long short-term memory; Seismic response prediction; Data folding; Data augmentation; KiK-net</keywords><publishedDay>1</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-04-01</publishedDate><doi>10.1016/j.cacaie.2026.100054</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace Civil Electrical and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders>National Natural Science Foundation of China, Grant/ Number: 42377140</funders><projectreference/><lastEdited>2026-06-08T15:28:05.0262989</lastEdited><Created>2026-05-21T12:41:04.1511122</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>Yongxin</firstname><surname>Wu</surname><order>1</order></author><author><firstname>Zhanpeng</firstname><surname>Yin</surname><order>2</order></author><author><firstname>Juncheng</firstname><surname>Wang</surname><order>3</order></author><author><firstname>Yue</firstname><surname>Hou</surname><orcid>0000-0002-4334-2620</orcid><order>4</order></author><author><firstname>Haodong</firstname><surname>Shang</surname><order>5</order></author><author><firstname>Houle</firstname><surname>Zhang</surname><order>6</order></author></authors><documents><document><filename>71969__36885__1c5d2f2e41a4414ab98d6b38cda98810.pdf</filename><originalFilename>71969.VoR.pdf</originalFilename><uploaded>2026-06-08T15:24:44.9262402</uploaded><type>Output</type><contentLength>4889490</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2026 The Author(s). This is an open access article under the CC BY-NC-ND license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-06-08T15:28:05.0262989 v2 71969 2026-05-21 Physics-informed long short-term memory network with data folding for efficient site seismic response prediction 92bf566c65343cb3ee04ad963eacf31b 0000-0002-4334-2620 Yue Hou Yue Hou true false 2026-05-21 ACEM Accurate prediction of site seismic response is essential for earthquake engineering and seismic design. Numerical simulation methods, although physically rigorous, become computationally intensive when soils exhibit complex nonlinear behavior and are sensitive to constitutive model selection and parameter calibration. Data‑driven deep learning models can approximate nonlinear mappings efficiently, yet they lack built‑in physical constraints and risk producing predictions that violate fundamental mechanics when extrapolating beyond the training domain. This study presents a physics‑informed deep long short-term memory (LSTM) framework for efficient and accurate site seismic response prediction. The framework enforces physical consistency by adding kinematic derivative relationships as soft constraints in the loss function and improves training efficiency by using Data folding modules. A targeted data augmentation strategy addresses measurement noise and signal variability in recorded data. Comprehensive validation on numerically simulated events and on KiK‑net recordings shows the effectiveness of the methodology. On numerical data, the physics‑informed model reaches a 97.98% confidence level within ±2% normalized error and reduces training time by more than 60%. On recorded data, the enhanced model with data augmentation reaches an 88.84% confidence level and a response spectrum correlation of 0.951, which supports reliable prediction of frequency content for engineering use. The framework provides an efficient and physically consistent solution for site response prediction with implications for seismic hazard assessment and structural design. Journal Article Computer-Aided Civil and Infrastructure Engineering 44 100054 Elsevier BV 1093-9687 Physics-informed neural networks; Long short-term memory; Seismic response prediction; Data folding; Data augmentation; KiK-net 1 4 2026 2026-04-01 10.1016/j.cacaie.2026.100054 COLLEGE NANME Aerospace Civil Electrical and Mechanical Engineering COLLEGE CODE ACEM Swansea University Other National Natural Science Foundation of China, Grant/ Number: 42377140 2026-06-08T15:28:05.0262989 2026-05-21T12:41:04.1511122 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Civil Engineering Yongxin Wu 1 Zhanpeng Yin 2 Juncheng Wang 3 Yue Hou 0000-0002-4334-2620 4 Haodong Shang 5 Houle Zhang 6 71969__36885__1c5d2f2e41a4414ab98d6b38cda98810.pdf 71969.VoR.pdf 2026-06-08T15:24:44.9262402 Output 4889490 application/pdf Version of Record true © 2026 The Author(s). This is an open access article under the CC BY-NC-ND license. true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
spellingShingle Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
Yue Hou
title_short Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
title_full Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
title_fullStr Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
title_full_unstemmed Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
title_sort Physics-informed long short-term memory network with data folding for efficient site seismic response prediction
author_id_str_mv 92bf566c65343cb3ee04ad963eacf31b
author_id_fullname_str_mv 92bf566c65343cb3ee04ad963eacf31b_***_Yue Hou
author Yue Hou
author2 Yongxin Wu
Zhanpeng Yin
Juncheng Wang
Yue Hou
Haodong Shang
Houle Zhang
format Journal article
container_title Computer-Aided Civil and Infrastructure Engineering
container_volume 44
container_start_page 100054
publishDate 2026
institution Swansea University
issn 1093-9687
doi_str_mv 10.1016/j.cacaie.2026.100054
publisher Elsevier BV
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 1
active_str 0
description Accurate prediction of site seismic response is essential for earthquake engineering and seismic design. Numerical simulation methods, although physically rigorous, become computationally intensive when soils exhibit complex nonlinear behavior and are sensitive to constitutive model selection and parameter calibration. Data‑driven deep learning models can approximate nonlinear mappings efficiently, yet they lack built‑in physical constraints and risk producing predictions that violate fundamental mechanics when extrapolating beyond the training domain. This study presents a physics‑informed deep long short-term memory (LSTM) framework for efficient and accurate site seismic response prediction. The framework enforces physical consistency by adding kinematic derivative relationships as soft constraints in the loss function and improves training efficiency by using Data folding modules. A targeted data augmentation strategy addresses measurement noise and signal variability in recorded data. Comprehensive validation on numerically simulated events and on KiK‑net recordings shows the effectiveness of the methodology. On numerical data, the physics‑informed model reaches a 97.98% confidence level within ±2% normalized error and reduces training time by more than 60%. On recorded data, the enhanced model with data augmentation reaches an 88.84% confidence level and a response spectrum correlation of 0.951, which supports reliable prediction of frequency content for engineering use. The framework provides an efficient and physically consistent solution for site response prediction with implications for seismic hazard assessment and structural design.
published_date 2026-04-01T06:39:38Z
_version_ 1867859024850976768
score 11.108426

Similar Items