View in EDS

Influence of non-landslide sampling extent on machine learning-based landslide susceptibility assessment, a case study of Wuyi County, China.

Saved in:
Bibliographic Details
Title: Influence of non-landslide sampling extent on machine learning-based landslide susceptibility assessment, a case study of Wuyi County, China.
Authors: Yang, Yongyong1,2 (AUTHOR), An, Ni1 (AUTHOR) anni2021@zju.edu.cn, Lü, Qing1 (AUTHOR) lvqing@zju.edu.cn, Zhang, Zhengwen2 (AUTHOR), Yan, Xin2 (AUTHOR), Zhu, Cheng3 (AUTHOR)
Source: Environmental Earth Sciences. Jul2026, Vol. 85 Issue 13, p1-22. 22p.
Subject Terms: *Random forest algorithms, *Nonprobability sampling, *Machine learning, *Landslide hazard analysis, *Counties, *Geographical positions, *Statistical measurement
Geographic Terms: China
Abstract: Non-landslide sample selection plays a critical role in Random Forest-based landslide susceptibility modeling, yet the spatial extent of non-landslide sampling has rarely been systematically quantified. Using Wuyi County (Zhejiang Province, China) as a case study, this study developed 22 non-landslide sampling scenarios with varying spatial extents based on frequency ratio-derived susceptibility zoning, and evaluated their performance using a Random Forest model. Results show that model performance, as measured by the area under the curve (AUC), improves as the non-landslide sampling extent decreases, whereas the lowest performance is consistently observed when the sampling zone approaches full coverage of the study area. By integrating model discrimination metrics with spatial pattern evaluation of susceptibility maps, an optimal non-landslide sampling proportion of 71.42%-89.92% is identified, achieving a balance between predictive accuracy and spatial realism. These findings highlight the sensitivity of susceptibility assessment to non-landslide sampling design and provide a quantitative basis for optimizing sampling strategies in regional landslide susceptibility assessment. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
FullText Text:
  Availability: 0
Header DbId: enr
DbLabel: Energy & Power Source
An: 196061820
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Influence of non-landslide sampling extent on machine learning-based landslide susceptibility assessment, a case study of Wuyi County, China.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Yongyong%22">Yang, Yongyong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22An%2C+Ni%22">An, Ni</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> anni2021@zju.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lü%2C+Qing%22">Lü, Qing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lvqing@zju.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zhengwen%22">Zhang, Zhengwen</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yan%2C+Xin%22">Yan, Xin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhu%2C+Cheng%22">Zhu, Cheng</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Environmental+Earth+Sciences%22">Environmental Earth Sciences</searchLink>. Jul2026, Vol. 85 Issue 13, p1-22. 22p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Random+forest+algorithms%22">Random forest algorithms</searchLink><br />*<searchLink fieldCode="DE" term="%22Nonprobability+sampling%22">Nonprobability sampling</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Landslide+hazard+analysis%22">Landslide hazard analysis</searchLink><br />*<searchLink fieldCode="DE" term="%22Counties%22">Counties</searchLink><br />*<searchLink fieldCode="DE" term="%22Geographical+positions%22">Geographical positions</searchLink><br />*<searchLink fieldCode="DE" term="%22Statistical+measurement%22">Statistical measurement</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22China%22">China</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Non-landslide sample selection plays a critical role in Random Forest-based landslide susceptibility modeling, yet the spatial extent of non-landslide sampling has rarely been systematically quantified. Using Wuyi County (Zhejiang Province, China) as a case study, this study developed 22 non-landslide sampling scenarios with varying spatial extents based on frequency ratio-derived susceptibility zoning, and evaluated their performance using a Random Forest model. Results show that model performance, as measured by the area under the curve (AUC), improves as the non-landslide sampling extent decreases, whereas the lowest performance is consistently observed when the sampling zone approaches full coverage of the study area. By integrating model discrimination metrics with spatial pattern evaluation of susceptibility maps, an optimal non-landslide sampling proportion of 71.42%-89.92% is identified, achieving a balance between predictive accuracy and spatial realism. These findings highlight the sensitivity of susceptibility assessment to non-landslide sampling design and provide a quantitative basis for optimizing sampling strategies in regional landslide susceptibility assessment. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=196061820
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s12665-026-13038-5
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 22
        StartPage: 1
    Subjects:
      – SubjectFull: Random forest algorithms
        Type: general
      – SubjectFull: Nonprobability sampling
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Landslide hazard analysis
        Type: general
      – SubjectFull: Counties
        Type: general
      – SubjectFull: Geographical positions
        Type: general
      – SubjectFull: Statistical measurement
        Type: general
      – SubjectFull: China
        Type: general
    Titles:
      – TitleFull: Influence of non-landslide sampling extent on machine learning-based landslide susceptibility assessment, a case study of Wuyi County, China.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Yongyong
      – PersonEntity:
          Name:
            NameFull: An, Ni
      – PersonEntity:
          Name:
            NameFull: Lü, Qing
      – PersonEntity:
          Name:
            NameFull: Zhang, Zhengwen
      – PersonEntity:
          Name:
            NameFull: Yan, Xin
      – PersonEntity:
          Name:
            NameFull: Zhu, Cheng
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 18666280
          Numbering:
            – Type: volume
              Value: 85
            – Type: issue
              Value: 13
          Titles:
            – TitleFull: Environmental Earth Sciences
              Type: main
ResultId 1