Integrating Feature Selection with Machine Learning for Accurate Reservoir Landslide Displacement Prediction
Accurate prediction of reservoir landslide displacements is crucial for early warning and hazard prevention. Current machine learning (ML) paradigms for predicting landslide displacement demonstrate superior performance, while often relying on various feature engineering techniques, such as decompos...
Gespeichert in:
Veröffentlicht in: | Water (Basel) 2024-08, Vol.16 (15), p.2152 |
---|---|
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 | 15 |
container_start_page | 2152 |
container_title | Water (Basel) |
container_volume | 16 |
creator | Ge, Qi Wang, Jingyong Liu, Cheng Wang, Xiaohong Deng, Yiyan Li, Jin |
description | Accurate prediction of reservoir landslide displacements is crucial for early warning and hazard prevention. Current machine learning (ML) paradigms for predicting landslide displacement demonstrate superior performance, while often relying on various feature engineering techniques, such as decomposing into different temporal lags and feature selection. This study investigates the impact of various feature selection techniques on the performance of ML algorithms for landslide displacement prediction. The Shuping and Baishuihe landslides in China’s Three Gorges Reservoir Area are used to comprehensively benchmark four prevalent ML algorithms. Both static ML models, including backpropagation neural network (BPNN), support vector machine (SVM), and dynamic models, such as long short-term memory (LSTM), and gated recurrent unit (GRU), are included. Each ML model is evaluated under three feature engineering techniques: raw multivariate time series, and feature selection under maximal information coefficient-partial autocorrelation function (MIC-PACF), or grey relational analysis-PACF (GRA-PACF). The results demonstrate that appropriate feature selection methods could significantly improve the performance of static ML models. In contrast, dynamic models effectively leverage inherent capabilities in capturing temporal dynamics within raw multivariate time series, seeing marginal gains with extensive feature engineering compared to no feature selection strategy. The optimal feature selection approach varies based on the ML model and specific landslide, highlighting the importance of case-specific assessments. The findings in this study offer guidance on integrating feature selection techniques with different machine learning models to maximize the robustness and generalizability of data-driven landslide displacement prediction frameworks. |
doi_str_mv | 10.3390/w16152152 |
format | Article |
fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_miscellaneous_3153704177</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A804515682</galeid><sourcerecordid>A804515682</sourcerecordid><originalsourceid>FETCH-LOGICAL-c219t-adfba4053e118873104946d0e4f484173813b13400e920db2fa57da90aa10f153</originalsourceid><addsrcrecordid>eNpdkU1LBDEMhgdRUNSD_6DgRQ-r6bSz0zkufsOK4sd5yHbStTLbrm3HxX9vdUXEJJAQnvclkKI44HAiRAOnKz7mVZlro9gpoRYjKSXf_DNvF_sxvkIO2ShVwU7R37hE84DJujm7JExDIPZIPelkvWMrm17YLeoX64hNCYP74owPbKL1kGXEHihSePc2sCm6Lva2I3Zu47JHTQtyid0H6uy33V6xZbCPtP_Td4vny4uns-vR9O7q5mwyHemSN2mEnZmhhEoQ50rVgudr5bgDkkYqyWuhuJhxIQGoKaGblQarusMGEDkYXond4mjtuwz-baCY2oWNmvoeHfkhtiIzNWSnOqOH_9BXPwSXr2sFNNCUQiiRqZM1NceeWuuMTwF1zo4WVntHxub9RIGseDVWZRYcrwU6-BgDmXYZ7ALDR8uh_fpV-_sr8QleaITr</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3090923383</pqid></control><display><type>article</type><title>Integrating Feature Selection with Machine Learning for Accurate Reservoir Landslide Displacement Prediction</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Ge, Qi ; Wang, Jingyong ; Liu, Cheng ; Wang, Xiaohong ; Deng, Yiyan ; Li, Jin</creator><creatorcontrib>Ge, Qi ; Wang, Jingyong ; Liu, Cheng ; Wang, Xiaohong ; Deng, Yiyan ; Li, Jin</creatorcontrib><description>Accurate prediction of reservoir landslide displacements is crucial for early warning and hazard prevention. Current machine learning (ML) paradigms for predicting landslide displacement demonstrate superior performance, while often relying on various feature engineering techniques, such as decomposing into different temporal lags and feature selection. This study investigates the impact of various feature selection techniques on the performance of ML algorithms for landslide displacement prediction. The Shuping and Baishuihe landslides in China’s Three Gorges Reservoir Area are used to comprehensively benchmark four prevalent ML algorithms. Both static ML models, including backpropagation neural network (BPNN), support vector machine (SVM), and dynamic models, such as long short-term memory (LSTM), and gated recurrent unit (GRU), are included. Each ML model is evaluated under three feature engineering techniques: raw multivariate time series, and feature selection under maximal information coefficient-partial autocorrelation function (MIC-PACF), or grey relational analysis-PACF (GRA-PACF). The results demonstrate that appropriate feature selection methods could significantly improve the performance of static ML models. In contrast, dynamic models effectively leverage inherent capabilities in capturing temporal dynamics within raw multivariate time series, seeing marginal gains with extensive feature engineering compared to no feature selection strategy. The optimal feature selection approach varies based on the ML model and specific landslide, highlighting the importance of case-specific assessments. The findings in this study offer guidance on integrating feature selection techniques with different machine learning models to maximize the robustness and generalizability of data-driven landslide displacement prediction frameworks.</description><identifier>ISSN: 2073-4441</identifier><identifier>EISSN: 2073-4441</identifier><identifier>DOI: 10.3390/w16152152</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Algorithms ; Analysis ; autocorrelation ; Case studies ; China ; Dams ; Deformation ; Engineering ; Feature selection ; Landslides ; Landslides & mudslides ; Machine learning ; Neural networks ; prediction ; Support vector machines ; temporal variation ; Time series ; time series analysis ; water</subject><ispartof>Water (Basel), 2024-08, Vol.16 (15), p.2152</ispartof><rights>COPYRIGHT 2024 MDPI AG</rights><rights>2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c219t-adfba4053e118873104946d0e4f484173813b13400e920db2fa57da90aa10f153</cites><orcidid>0009-0006-2316-9169 ; 0000-0003-0743-6643 ; 0009-0002-1381-9966</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Ge, Qi</creatorcontrib><creatorcontrib>Wang, Jingyong</creatorcontrib><creatorcontrib>Liu, Cheng</creatorcontrib><creatorcontrib>Wang, Xiaohong</creatorcontrib><creatorcontrib>Deng, Yiyan</creatorcontrib><creatorcontrib>Li, Jin</creatorcontrib><title>Integrating Feature Selection with Machine Learning for Accurate Reservoir Landslide Displacement Prediction</title><title>Water (Basel)</title><description>Accurate prediction of reservoir landslide displacements is crucial for early warning and hazard prevention. Current machine learning (ML) paradigms for predicting landslide displacement demonstrate superior performance, while often relying on various feature engineering techniques, such as decomposing into different temporal lags and feature selection. This study investigates the impact of various feature selection techniques on the performance of ML algorithms for landslide displacement prediction. The Shuping and Baishuihe landslides in China’s Three Gorges Reservoir Area are used to comprehensively benchmark four prevalent ML algorithms. Both static ML models, including backpropagation neural network (BPNN), support vector machine (SVM), and dynamic models, such as long short-term memory (LSTM), and gated recurrent unit (GRU), are included. Each ML model is evaluated under three feature engineering techniques: raw multivariate time series, and feature selection under maximal information coefficient-partial autocorrelation function (MIC-PACF), or grey relational analysis-PACF (GRA-PACF). The results demonstrate that appropriate feature selection methods could significantly improve the performance of static ML models. In contrast, dynamic models effectively leverage inherent capabilities in capturing temporal dynamics within raw multivariate time series, seeing marginal gains with extensive feature engineering compared to no feature selection strategy. The optimal feature selection approach varies based on the ML model and specific landslide, highlighting the importance of case-specific assessments. The findings in this study offer guidance on integrating feature selection techniques with different machine learning models to maximize the robustness and generalizability of data-driven landslide displacement prediction frameworks.</description><subject>Algorithms</subject><subject>Analysis</subject><subject>autocorrelation</subject><subject>Case studies</subject><subject>China</subject><subject>Dams</subject><subject>Deformation</subject><subject>Engineering</subject><subject>Feature selection</subject><subject>Landslides</subject><subject>Landslides & mudslides</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>prediction</subject><subject>Support vector machines</subject><subject>temporal variation</subject><subject>Time series</subject><subject>time series analysis</subject><subject>water</subject><issn>2073-4441</issn><issn>2073-4441</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpdkU1LBDEMhgdRUNSD_6DgRQ-r6bSz0zkufsOK4sd5yHbStTLbrm3HxX9vdUXEJJAQnvclkKI44HAiRAOnKz7mVZlro9gpoRYjKSXf_DNvF_sxvkIO2ShVwU7R37hE84DJujm7JExDIPZIPelkvWMrm17YLeoX64hNCYP74owPbKL1kGXEHihSePc2sCm6Lva2I3Zu47JHTQtyid0H6uy33V6xZbCPtP_Td4vny4uns-vR9O7q5mwyHemSN2mEnZmhhEoQ50rVgudr5bgDkkYqyWuhuJhxIQGoKaGblQarusMGEDkYXond4mjtuwz-baCY2oWNmvoeHfkhtiIzNWSnOqOH_9BXPwSXr2sFNNCUQiiRqZM1NceeWuuMTwF1zo4WVntHxub9RIGseDVWZRYcrwU6-BgDmXYZ7ALDR8uh_fpV-_sr8QleaITr</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>Ge, Qi</creator><creator>Wang, Jingyong</creator><creator>Liu, Cheng</creator><creator>Wang, Xiaohong</creator><creator>Deng, Yiyan</creator><creator>Li, Jin</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7S9</scope><scope>L.6</scope><orcidid>https://orcid.org/0009-0006-2316-9169</orcidid><orcidid>https://orcid.org/0000-0003-0743-6643</orcidid><orcidid>https://orcid.org/0009-0002-1381-9966</orcidid></search><sort><creationdate>20240801</creationdate><title>Integrating Feature Selection with Machine Learning for Accurate Reservoir Landslide Displacement Prediction</title><author>Ge, Qi ; Wang, Jingyong ; Liu, Cheng ; Wang, Xiaohong ; Deng, Yiyan ; Li, Jin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c219t-adfba4053e118873104946d0e4f484173813b13400e920db2fa57da90aa10f153</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Analysis</topic><topic>autocorrelation</topic><topic>Case studies</topic><topic>China</topic><topic>Dams</topic><topic>Deformation</topic><topic>Engineering</topic><topic>Feature selection</topic><topic>Landslides</topic><topic>Landslides & mudslides</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>prediction</topic><topic>Support vector machines</topic><topic>temporal variation</topic><topic>Time series</topic><topic>time series analysis</topic><topic>water</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ge, Qi</creatorcontrib><creatorcontrib>Wang, Jingyong</creatorcontrib><creatorcontrib>Liu, Cheng</creatorcontrib><creatorcontrib>Wang, Xiaohong</creatorcontrib><creatorcontrib>Deng, Yiyan</creatorcontrib><creatorcontrib>Li, Jin</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</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>AGRICOLA</collection><collection>AGRICOLA - Academic</collection><jtitle>Water (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ge, Qi</au><au>Wang, Jingyong</au><au>Liu, Cheng</au><au>Wang, Xiaohong</au><au>Deng, Yiyan</au><au>Li, Jin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Integrating Feature Selection with Machine Learning for Accurate Reservoir Landslide Displacement Prediction</atitle><jtitle>Water (Basel)</jtitle><date>2024-08-01</date><risdate>2024</risdate><volume>16</volume><issue>15</issue><spage>2152</spage><pages>2152-</pages><issn>2073-4441</issn><eissn>2073-4441</eissn><abstract>Accurate prediction of reservoir landslide displacements is crucial for early warning and hazard prevention. Current machine learning (ML) paradigms for predicting landslide displacement demonstrate superior performance, while often relying on various feature engineering techniques, such as decomposing into different temporal lags and feature selection. This study investigates the impact of various feature selection techniques on the performance of ML algorithms for landslide displacement prediction. The Shuping and Baishuihe landslides in China’s Three Gorges Reservoir Area are used to comprehensively benchmark four prevalent ML algorithms. Both static ML models, including backpropagation neural network (BPNN), support vector machine (SVM), and dynamic models, such as long short-term memory (LSTM), and gated recurrent unit (GRU), are included. Each ML model is evaluated under three feature engineering techniques: raw multivariate time series, and feature selection under maximal information coefficient-partial autocorrelation function (MIC-PACF), or grey relational analysis-PACF (GRA-PACF). The results demonstrate that appropriate feature selection methods could significantly improve the performance of static ML models. In contrast, dynamic models effectively leverage inherent capabilities in capturing temporal dynamics within raw multivariate time series, seeing marginal gains with extensive feature engineering compared to no feature selection strategy. The optimal feature selection approach varies based on the ML model and specific landslide, highlighting the importance of case-specific assessments. The findings in this study offer guidance on integrating feature selection techniques with different machine learning models to maximize the robustness and generalizability of data-driven landslide displacement prediction frameworks.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/w16152152</doi><orcidid>https://orcid.org/0009-0006-2316-9169</orcidid><orcidid>https://orcid.org/0000-0003-0743-6643</orcidid><orcidid>https://orcid.org/0009-0002-1381-9966</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2073-4441 |
ispartof | Water (Basel), 2024-08, Vol.16 (15), p.2152 |
issn | 2073-4441 2073-4441 |
language | eng |
recordid | cdi_proquest_miscellaneous_3153704177 |
source | MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
subjects | Algorithms Analysis autocorrelation Case studies China Dams Deformation Engineering Feature selection Landslides Landslides & mudslides Machine learning Neural networks prediction Support vector machines temporal variation Time series time series analysis water |
title | Integrating Feature Selection with Machine Learning for Accurate Reservoir Landslide Displacement Prediction |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T22%3A51%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Integrating%20Feature%20Selection%20with%20Machine%20Learning%20for%20Accurate%20Reservoir%20Landslide%20Displacement%20Prediction&rft.jtitle=Water%20(Basel)&rft.au=Ge,%20Qi&rft.date=2024-08-01&rft.volume=16&rft.issue=15&rft.spage=2152&rft.pages=2152-&rft.issn=2073-4441&rft.eissn=2073-4441&rft_id=info:doi/10.3390/w16152152&rft_dat=%3Cgale_proqu%3EA804515682%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3090923383&rft_id=info:pmid/&rft_galeid=A804515682&rfr_iscdi=true |