Advancing flood susceptibility modeling using stacking ensemble machine learning: A multi-model approach

Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning (ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of geographical sciences 2024-08, Vol.34 (8), p.1513-1536
Hauptverfasser: Yang, Huilin, Yao, Rui, Dong, Linyao, Sun, Peng, Zhang, Qiang, Wei, Yongqiang, Sun, Shao, Aghakouchak, Amir
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1536
container_issue 8
container_start_page 1513
container_title Journal of geographical sciences
container_volume 34
creator Yang, Huilin
Yao, Rui
Dong, Linyao
Sun, Peng
Zhang, Qiang
Wei, Yongqiang
Sun, Shao
Aghakouchak, Amir
description Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning (ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following: (1) The stacking ensemble learning, using RF-XGB-CB-LR model, significantly enhances flood susceptibility simulation. (2) In addition to rainfall, key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland. (3) In the northeast of the study area, heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.
doi_str_mv 10.1007/s11442-024-2259-2
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3091218077</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3091218077</sourcerecordid><originalsourceid>FETCH-LOGICAL-c198t-d775cbb8631405bb3eaacd5530da3a096d24f3da82730187461e0cb356129bf93</originalsourceid><addsrcrecordid>eNp1UMtKxDAUDaLgOPoB7gquozdJmzTuhsEXCG4U3IW8OtOxL5NWmL83dQRXbu49cF5wELokcE0AxE0kJM8pBppjSguJ6RFakJITLAteHicMIDFn4v0UncW4A2Ay53SBtiv3pTtbd5usavreZXGK1g9jbeqmHvdZ2zvfzOwU5xtHbT9m4LvoW9P4rNV2W3c-a7wOXWJus1XWTs1Y4x9rpoch9Elzjk4q3UR_8fuX6O3-7nX9iJ9fHp7Wq2dsiSxH7IQorDElZySHwhjmtbauKBg4zTRI7mheMadLKhiQUuSceLCGFZxQaSrJlujqkJtqPycfR7Xrp9ClSsVAEkpKECKpyEFlQx9j8JUaQt3qsFcE1DyoOgyq0qBqHlTR5KEHT0zabuPDX_L_pm_KKXm1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3091218077</pqid></control><display><type>article</type><title>Advancing flood susceptibility modeling using stacking ensemble machine learning: A multi-model approach</title><source>SpringerNature Journals</source><creator>Yang, Huilin ; Yao, Rui ; Dong, Linyao ; Sun, Peng ; Zhang, Qiang ; Wei, Yongqiang ; Sun, Shao ; Aghakouchak, Amir</creator><creatorcontrib>Yang, Huilin ; Yao, Rui ; Dong, Linyao ; Sun, Peng ; Zhang, Qiang ; Wei, Yongqiang ; Sun, Shao ; Aghakouchak, Amir</creatorcontrib><description>Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning (ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following: (1) The stacking ensemble learning, using RF-XGB-CB-LR model, significantly enhances flood susceptibility simulation. (2) In addition to rainfall, key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland. (3) In the northeast of the study area, heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.</description><identifier>ISSN: 1009-637X</identifier><identifier>EISSN: 1861-9568</identifier><identifier>DOI: 10.1007/s11442-024-2259-2</identifier><language>eng</language><publisher>Heidelberg: Science Press</publisher><subject>Agricultural land ; Earth and Environmental Science ; Environmental risk ; Flood forecasting ; Floods ; Geographical Information Systems/Cartography ; Geography ; Machine learning ; Nature Conservation ; Physical Geography ; Precipitation ; Remote Sensing/Photogrammetry ; Risk management</subject><ispartof>Journal of geographical sciences, 2024-08, Vol.34 (8), p.1513-1536</ispartof><rights>Science Press 2024</rights><rights>Science Press 2024.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c198t-d775cbb8631405bb3eaacd5530da3a096d24f3da82730187461e0cb356129bf93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11442-024-2259-2$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11442-024-2259-2$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>315,782,786,27931,27932,41495,42564,51326</link.rule.ids></links><search><creatorcontrib>Yang, Huilin</creatorcontrib><creatorcontrib>Yao, Rui</creatorcontrib><creatorcontrib>Dong, Linyao</creatorcontrib><creatorcontrib>Sun, Peng</creatorcontrib><creatorcontrib>Zhang, Qiang</creatorcontrib><creatorcontrib>Wei, Yongqiang</creatorcontrib><creatorcontrib>Sun, Shao</creatorcontrib><creatorcontrib>Aghakouchak, Amir</creatorcontrib><title>Advancing flood susceptibility modeling using stacking ensemble machine learning: A multi-model approach</title><title>Journal of geographical sciences</title><addtitle>J. Geogr. Sci</addtitle><description>Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning (ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following: (1) The stacking ensemble learning, using RF-XGB-CB-LR model, significantly enhances flood susceptibility simulation. (2) In addition to rainfall, key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland. (3) In the northeast of the study area, heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.</description><subject>Agricultural land</subject><subject>Earth and Environmental Science</subject><subject>Environmental risk</subject><subject>Flood forecasting</subject><subject>Floods</subject><subject>Geographical Information Systems/Cartography</subject><subject>Geography</subject><subject>Machine learning</subject><subject>Nature Conservation</subject><subject>Physical Geography</subject><subject>Precipitation</subject><subject>Remote Sensing/Photogrammetry</subject><subject>Risk management</subject><issn>1009-637X</issn><issn>1861-9568</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp1UMtKxDAUDaLgOPoB7gquozdJmzTuhsEXCG4U3IW8OtOxL5NWmL83dQRXbu49cF5wELokcE0AxE0kJM8pBppjSguJ6RFakJITLAteHicMIDFn4v0UncW4A2Ay53SBtiv3pTtbd5usavreZXGK1g9jbeqmHvdZ2zvfzOwU5xtHbT9m4LvoW9P4rNV2W3c-a7wOXWJus1XWTs1Y4x9rpoch9Elzjk4q3UR_8fuX6O3-7nX9iJ9fHp7Wq2dsiSxH7IQorDElZySHwhjmtbauKBg4zTRI7mheMadLKhiQUuSceLCGFZxQaSrJlujqkJtqPycfR7Xrp9ClSsVAEkpKECKpyEFlQx9j8JUaQt3qsFcE1DyoOgyq0qBqHlTR5KEHT0zabuPDX_L_pm_KKXm1</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>Yang, Huilin</creator><creator>Yao, Rui</creator><creator>Dong, Linyao</creator><creator>Sun, Peng</creator><creator>Zhang, Qiang</creator><creator>Wei, Yongqiang</creator><creator>Sun, Shao</creator><creator>Aghakouchak, Amir</creator><general>Science Press</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20240801</creationdate><title>Advancing flood susceptibility modeling using stacking ensemble machine learning: A multi-model approach</title><author>Yang, Huilin ; Yao, Rui ; Dong, Linyao ; Sun, Peng ; Zhang, Qiang ; Wei, Yongqiang ; Sun, Shao ; Aghakouchak, Amir</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c198t-d775cbb8631405bb3eaacd5530da3a096d24f3da82730187461e0cb356129bf93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Agricultural land</topic><topic>Earth and Environmental Science</topic><topic>Environmental risk</topic><topic>Flood forecasting</topic><topic>Floods</topic><topic>Geographical Information Systems/Cartography</topic><topic>Geography</topic><topic>Machine learning</topic><topic>Nature Conservation</topic><topic>Physical Geography</topic><topic>Precipitation</topic><topic>Remote Sensing/Photogrammetry</topic><topic>Risk management</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yang, Huilin</creatorcontrib><creatorcontrib>Yao, Rui</creatorcontrib><creatorcontrib>Dong, Linyao</creatorcontrib><creatorcontrib>Sun, Peng</creatorcontrib><creatorcontrib>Zhang, Qiang</creatorcontrib><creatorcontrib>Wei, Yongqiang</creatorcontrib><creatorcontrib>Sun, Shao</creatorcontrib><creatorcontrib>Aghakouchak, Amir</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of geographical sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yang, Huilin</au><au>Yao, Rui</au><au>Dong, Linyao</au><au>Sun, Peng</au><au>Zhang, Qiang</au><au>Wei, Yongqiang</au><au>Sun, Shao</au><au>Aghakouchak, Amir</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Advancing flood susceptibility modeling using stacking ensemble machine learning: A multi-model approach</atitle><jtitle>Journal of geographical sciences</jtitle><stitle>J. Geogr. Sci</stitle><date>2024-08-01</date><risdate>2024</risdate><volume>34</volume><issue>8</issue><spage>1513</spage><epage>1536</epage><pages>1513-1536</pages><issn>1009-637X</issn><eissn>1861-9568</eissn><abstract>Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning (ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following: (1) The stacking ensemble learning, using RF-XGB-CB-LR model, significantly enhances flood susceptibility simulation. (2) In addition to rainfall, key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland. (3) In the northeast of the study area, heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.</abstract><cop>Heidelberg</cop><pub>Science Press</pub><doi>10.1007/s11442-024-2259-2</doi><tpages>24</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1009-637X
ispartof Journal of geographical sciences, 2024-08, Vol.34 (8), p.1513-1536
issn 1009-637X
1861-9568
language eng
recordid cdi_proquest_journals_3091218077
source SpringerNature Journals
subjects Agricultural land
Earth and Environmental Science
Environmental risk
Flood forecasting
Floods
Geographical Information Systems/Cartography
Geography
Machine learning
Nature Conservation
Physical Geography
Precipitation
Remote Sensing/Photogrammetry
Risk management
title Advancing flood susceptibility modeling using stacking ensemble machine learning: A multi-model approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T13%3A21%3A51IST&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=Advancing%20flood%20susceptibility%20modeling%20using%20stacking%20ensemble%20machine%20learning:%20A%20multi-model%20approach&rft.jtitle=Journal%20of%20geographical%20sciences&rft.au=Yang,%20Huilin&rft.date=2024-08-01&rft.volume=34&rft.issue=8&rft.spage=1513&rft.epage=1536&rft.pages=1513-1536&rft.issn=1009-637X&rft.eissn=1861-9568&rft_id=info:doi/10.1007/s11442-024-2259-2&rft_dat=%3Cproquest_cross%3E3091218077%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3091218077&rft_id=info:pmid/&rfr_iscdi=true