Loading…

Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential

This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that w...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers of Structural and Civil Engineering 2021-04, Vol.15 (2), p.490-505
Main Authors: AHMAD, Mahmood, TANG, Xiao-Wei, QIU, Jiang-Nan, AHMAD, Feezan, GU, Wen-Jing
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743
cites cdi_FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743
container_end_page 505
container_issue 2
container_start_page 490
container_title Frontiers of Structural and Civil Engineering
container_volume 15
creator AHMAD, Mahmood
TANG, Xiao-Wei
QIU, Jiang-Nan
AHMAD, Feezan
GU, Wen-Jing
description This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy ( OA), precision, recall, F-measure, and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models' performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.
doi_str_mv 10.1007/s11709-020-0669-5
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2535299924</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2535299924</sourcerecordid><originalsourceid>FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743</originalsourceid><addsrcrecordid>eNp9kF1LwzAUhosoOOZ-gHcBr6snST-SyzH8goE3eh3S9KTN6JqadIL_3s7KvFtuEsj7vOfwJMkthXsKUD5ESkuQKTBIoShkml8kCwYyT1mWycvTm8N1sopxBwAUSg6CL5J6PQydM3p0vifekr02reuRdKhD7_qG6K7xwY3tPhLrAxlbJPilu8OJiOji3hkSvetI5z4PaLX5_Rz8iP3odHeTXFndRVz93cvk4-nxffOSbt-eXzfrbWp4kY-pzIvMClEUDCtGCymyikNVYFlnopKmEtaIrDac81LTejqiFBywtlWNhpUZXyZ3c-8Q_LRHHNXOH0I_jVQs5zmTUrJjis4pE3yMAa0agtvr8K0oqKNPNftUk0919KnyiWEzE6ds32D4bz4HiRlqXdNiwHoIGKOywU9WMJxDfwAZpYvs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2535299924</pqid></control><display><type>article</type><title>Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential</title><source>Springer Nature</source><creator>AHMAD, Mahmood ; TANG, Xiao-Wei ; QIU, Jiang-Nan ; AHMAD, Feezan ; GU, Wen-Jing</creator><creatorcontrib>AHMAD, Mahmood ; TANG, Xiao-Wei ; QIU, Jiang-Nan ; AHMAD, Feezan ; GU, Wen-Jing</creatorcontrib><description>This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy ( OA), precision, recall, F-measure, and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models' performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.</description><identifier>ISSN: 2095-2430</identifier><identifier>EISSN: 2095-2449</identifier><identifier>DOI: 10.1007/s11709-020-0669-5</identifier><language>eng</language><publisher>Beijing: Higher Education Press</publisher><subject>Algorithms ; Bayesian analysis ; Bayesian belief network ; Belief networks ; Cities ; Civil Engineering ; cone penetration test ; Cone penetration tests ; Countries ; Earthquakes ; Engineering ; Grain size ; Learning algorithms ; Liquefaction ; Machine learning ; Mathematical models ; parameter learning ; Performance indices ; Performance prediction ; Regions ; Research Article ; Seismic activity ; Seismic response ; seismic soil liquefaction ; Sensitivity analysis ; Soil investigations ; Soils ; structural learning ; Tabu search ; Training evaluation</subject><ispartof>Frontiers of Structural and Civil Engineering, 2021-04, Vol.15 (2), p.490-505</ispartof><rights>Copyright reserved, 2021, Higher Education Press</rights><rights>Higher Education Press 2021</rights><rights>Higher Education Press 2021.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743</citedby><cites>FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>AHMAD, Mahmood</creatorcontrib><creatorcontrib>TANG, Xiao-Wei</creatorcontrib><creatorcontrib>QIU, Jiang-Nan</creatorcontrib><creatorcontrib>AHMAD, Feezan</creatorcontrib><creatorcontrib>GU, Wen-Jing</creatorcontrib><title>Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential</title><title>Frontiers of Structural and Civil Engineering</title><addtitle>Front. Struct. Civ. Eng</addtitle><description>This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy ( OA), precision, recall, F-measure, and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models' performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.</description><subject>Algorithms</subject><subject>Bayesian analysis</subject><subject>Bayesian belief network</subject><subject>Belief networks</subject><subject>Cities</subject><subject>Civil Engineering</subject><subject>cone penetration test</subject><subject>Cone penetration tests</subject><subject>Countries</subject><subject>Earthquakes</subject><subject>Engineering</subject><subject>Grain size</subject><subject>Learning algorithms</subject><subject>Liquefaction</subject><subject>Machine learning</subject><subject>Mathematical models</subject><subject>parameter learning</subject><subject>Performance indices</subject><subject>Performance prediction</subject><subject>Regions</subject><subject>Research Article</subject><subject>Seismic activity</subject><subject>Seismic response</subject><subject>seismic soil liquefaction</subject><subject>Sensitivity analysis</subject><subject>Soil investigations</subject><subject>Soils</subject><subject>structural learning</subject><subject>Tabu search</subject><subject>Training evaluation</subject><issn>2095-2430</issn><issn>2095-2449</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kF1LwzAUhosoOOZ-gHcBr6snST-SyzH8goE3eh3S9KTN6JqadIL_3s7KvFtuEsj7vOfwJMkthXsKUD5ESkuQKTBIoShkml8kCwYyT1mWycvTm8N1sopxBwAUSg6CL5J6PQydM3p0vifekr02reuRdKhD7_qG6K7xwY3tPhLrAxlbJPilu8OJiOji3hkSvetI5z4PaLX5_Rz8iP3odHeTXFndRVz93cvk4-nxffOSbt-eXzfrbWp4kY-pzIvMClEUDCtGCymyikNVYFlnopKmEtaIrDac81LTejqiFBywtlWNhpUZXyZ3c-8Q_LRHHNXOH0I_jVQs5zmTUrJjis4pE3yMAa0agtvr8K0oqKNPNftUk0919KnyiWEzE6ds32D4bz4HiRlqXdNiwHoIGKOywU9WMJxDfwAZpYvs</recordid><startdate>20210401</startdate><enddate>20210401</enddate><creator>AHMAD, Mahmood</creator><creator>TANG, Xiao-Wei</creator><creator>QIU, Jiang-Nan</creator><creator>AHMAD, Feezan</creator><creator>GU, Wen-Jing</creator><general>Higher Education Press</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20210401</creationdate><title>Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential</title><author>AHMAD, Mahmood ; TANG, Xiao-Wei ; QIU, Jiang-Nan ; AHMAD, Feezan ; GU, Wen-Jing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Bayesian analysis</topic><topic>Bayesian belief network</topic><topic>Belief networks</topic><topic>Cities</topic><topic>Civil Engineering</topic><topic>cone penetration test</topic><topic>Cone penetration tests</topic><topic>Countries</topic><topic>Earthquakes</topic><topic>Engineering</topic><topic>Grain size</topic><topic>Learning algorithms</topic><topic>Liquefaction</topic><topic>Machine learning</topic><topic>Mathematical models</topic><topic>parameter learning</topic><topic>Performance indices</topic><topic>Performance prediction</topic><topic>Regions</topic><topic>Research Article</topic><topic>Seismic activity</topic><topic>Seismic response</topic><topic>seismic soil liquefaction</topic><topic>Sensitivity analysis</topic><topic>Soil investigations</topic><topic>Soils</topic><topic>structural learning</topic><topic>Tabu search</topic><topic>Training evaluation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>AHMAD, Mahmood</creatorcontrib><creatorcontrib>TANG, Xiao-Wei</creatorcontrib><creatorcontrib>QIU, Jiang-Nan</creatorcontrib><creatorcontrib>AHMAD, Feezan</creatorcontrib><creatorcontrib>GU, Wen-Jing</creatorcontrib><collection>CrossRef</collection><jtitle>Frontiers of Structural and Civil Engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>AHMAD, Mahmood</au><au>TANG, Xiao-Wei</au><au>QIU, Jiang-Nan</au><au>AHMAD, Feezan</au><au>GU, Wen-Jing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential</atitle><jtitle>Frontiers of Structural and Civil Engineering</jtitle><stitle>Front. Struct. Civ. Eng</stitle><date>2021-04-01</date><risdate>2021</risdate><volume>15</volume><issue>2</issue><spage>490</spage><epage>505</epage><pages>490-505</pages><issn>2095-2430</issn><eissn>2095-2449</eissn><abstract>This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy ( OA), precision, recall, F-measure, and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models' performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.</abstract><cop>Beijing</cop><pub>Higher Education Press</pub><doi>10.1007/s11709-020-0669-5</doi><tpages>16</tpages></addata></record>
fulltext fulltext
identifier ISSN: 2095-2430
ispartof Frontiers of Structural and Civil Engineering, 2021-04, Vol.15 (2), p.490-505
issn 2095-2430
2095-2449
language eng
recordid cdi_proquest_journals_2535299924
source Springer Nature
subjects Algorithms
Bayesian analysis
Bayesian belief network
Belief networks
Cities
Civil Engineering
cone penetration test
Cone penetration tests
Countries
Earthquakes
Engineering
Grain size
Learning algorithms
Liquefaction
Machine learning
Mathematical models
parameter learning
Performance indices
Performance prediction
Regions
Research Article
Seismic activity
Seismic response
seismic soil liquefaction
Sensitivity analysis
Soil investigations
Soils
structural learning
Tabu search
Training evaluation
title Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A27%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Application%20of%20machine%20learning%20algorithms%20for%20the%20evaluation%20of%20seismic%20soil%20liquefaction%20potential&rft.jtitle=Frontiers%20of%20Structural%20and%20Civil%20Engineering&rft.au=AHMAD,%20Mahmood&rft.date=2021-04-01&rft.volume=15&rft.issue=2&rft.spage=490&rft.epage=505&rft.pages=490-505&rft.issn=2095-2430&rft.eissn=2095-2449&rft_id=info:doi/10.1007/s11709-020-0669-5&rft_dat=%3Cproquest_cross%3E2535299924%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c365t-9564f88662eb216984b30b6e7d48b9cb8fc84dc3337a1dddd87830edfbdec2743%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2535299924&rft_id=info:pmid/&rfr_iscdi=true