View in EDS HTML Full Text PDF Full Text

Enhancing accuracy and reliability of landslide susceptibility maps through machine learning with non-landslide sampling strategies.

Saved in:
Bibliographic Details
Title: Enhancing accuracy and reliability of landslide susceptibility maps through machine learning with non-landslide sampling strategies.
Authors: Trinh, Thanh1 (AUTHOR) thanh.trinh@phenikaa-uni.edu.vn, Van Pham, Son2 (AUTHOR) sontdc2007@gmail.com, Emara, Tamer Z3 (AUTHOR) temara@du.edu.eg, Patwary, M Jamshed Alam4 (AUTHOR) jamshed@cuet.ac.bd, Nguyen, Duong Huy2 (AUTHOR) nguyenhuyduong112358@gmail.com, Luu, Binh Thanh5 (AUTHOR) luubinh282007@gmail.com, Khanh, Linh Nguyen Hoang6 (AUTHOR) nhklinh@hueuni.edu.vn
Source: Journal of Earth System Science. Jun2026, Vol. 135 Issue 2, p1-28. 28p.
Subject Terms: *Machine learning, *Sampling (Process), *Random forest algorithms, *Reliability in engineering, *Statistical accuracy, *Landslide hazard analysis, *Support vector machines
Geographic Terms: Vietnam
Abstract: Landslide hazards cause human fatalities and damage infrastructure in hilly areas worldwide. Establishing landslide susceptibility maps (LSMs) is a critical step in assessing and reducing landslide-related risk. Landslide prediction models have been extensively studied to produce LSMs for many years. However, the models often focus on comparing accuracy metrics, while the reliability of the LSMs they yield is often ignored. Moreover, non-landslide samples still need a thorough study. To address this research gap, we first present a study on non-landslide samples, which are combined from areas with low slopes and high slopes, and an evaluation of machine learning models in terms of accuracy metrics. We then also employ two statistical metrics to assess the reliability of LSMs. Our study was conducted in the Tam Chung area, Vietnam. We collected 13 influence factors and a landslide inventory of 173 landslide points and 55 delineated landslide polygons. We constructed five datasets, including landslide samples and non-landslide samples. Support vector machine (SVM), K-nearest neighbours (KNN), Logistic regression (LR), and random forest (RF) were used to build landslide prediction models. Empirical results have indicated that RF is the best method for accuracy metrics. However, LSMs yielded by SVM are the best choice in terms of accuracy and reliability, and the ratio of area with low slope and area with high slope for non-landslide samples is recommended to be 3:1. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 193197814
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Enhancing accuracy and reliability of landslide susceptibility maps through machine learning with non-landslide sampling strategies.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Trinh%2C+Thanh%22">Trinh, Thanh</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> thanh.trinh@phenikaa-uni.edu.vn</i><br /><searchLink fieldCode="AR" term="%22Van+Pham%2C+Son%22">Van Pham, Son</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> sontdc2007@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Emara%2C+Tamer+Z%22">Emara, Tamer Z</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> temara@du.edu.eg</i><br /><searchLink fieldCode="AR" term="%22Patwary%2C+M+Jamshed+Alam%22">Patwary, M Jamshed Alam</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> jamshed@cuet.ac.bd</i><br /><searchLink fieldCode="AR" term="%22Nguyen%2C+Duong+Huy%22">Nguyen, Duong Huy</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> nguyenhuyduong112358@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Luu%2C+Binh+Thanh%22">Luu, Binh Thanh</searchLink><relatesTo>5</relatesTo> (AUTHOR)<i> luubinh282007@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Khanh%2C+Linh+Nguyen+Hoang%22">Khanh, Linh Nguyen Hoang</searchLink><relatesTo>6</relatesTo> (AUTHOR)<i> nhklinh@hueuni.edu.vn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Earth+System+Science%22">Journal of Earth System Science</searchLink>. Jun2026, Vol. 135 Issue 2, p1-28. 28p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Sampling+%28Process%29%22">Sampling (Process)</searchLink><br />*<searchLink fieldCode="DE" term="%22Random+forest+algorithms%22">Random forest algorithms</searchLink><br />*<searchLink fieldCode="DE" term="%22Reliability+in+engineering%22">Reliability in engineering</searchLink><br />*<searchLink fieldCode="DE" term="%22Statistical+accuracy%22">Statistical accuracy</searchLink><br />*<searchLink fieldCode="DE" term="%22Landslide+hazard+analysis%22">Landslide hazard analysis</searchLink><br />*<searchLink fieldCode="DE" term="%22Support+vector+machines%22">Support vector machines</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Vietnam%22">Vietnam</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Landslide hazards cause human fatalities and damage infrastructure in hilly areas worldwide. Establishing landslide susceptibility maps (LSMs) is a critical step in assessing and reducing landslide-related risk. Landslide prediction models have been extensively studied to produce LSMs for many years. However, the models often focus on comparing accuracy metrics, while the reliability of the LSMs they yield is often ignored. Moreover, non-landslide samples still need a thorough study. To address this research gap, we first present a study on non-landslide samples, which are combined from areas with low slopes and high slopes, and an evaluation of machine learning models in terms of accuracy metrics. We then also employ two statistical metrics to assess the reliability of LSMs. Our study was conducted in the Tam Chung area, Vietnam. We collected 13 influence factors and a landslide inventory of 173 landslide points and 55 delineated landslide polygons. We constructed five datasets, including landslide samples and non-landslide samples. Support vector machine (SVM), K-nearest neighbours (KNN), Logistic regression (LR), and random forest (RF) were used to build landslide prediction models. Empirical results have indicated that RF is the best method for accuracy metrics. However, LSMs yielded by SVM are the best choice in terms of accuracy and reliability, and the ratio of area with low slope and area with high slope for non-landslide samples is recommended to be 3:1. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=193197814
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s12040-026-02773-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 1
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Sampling (Process)
        Type: general
      – SubjectFull: Random forest algorithms
        Type: general
      – SubjectFull: Reliability in engineering
        Type: general
      – SubjectFull: Statistical accuracy
        Type: general
      – SubjectFull: Landslide hazard analysis
        Type: general
      – SubjectFull: Support vector machines
        Type: general
      – SubjectFull: Vietnam
        Type: general
    Titles:
      – TitleFull: Enhancing accuracy and reliability of landslide susceptibility maps through machine learning with non-landslide sampling strategies.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Trinh, Thanh
      – PersonEntity:
          Name:
            NameFull: Van Pham, Son
      – PersonEntity:
          Name:
            NameFull: Emara, Tamer Z
      – PersonEntity:
          Name:
            NameFull: Patwary, M Jamshed Alam
      – PersonEntity:
          Name:
            NameFull: Nguyen, Duong Huy
      – PersonEntity:
          Name:
            NameFull: Luu, Binh Thanh
      – PersonEntity:
          Name:
            NameFull: Khanh, Linh Nguyen Hoang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 02534126
          Numbering:
            – Type: volume
              Value: 135
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Journal of Earth System Science
              Type: main
ResultId 1