Discussion on the tree-based machine learning model in the study of landslide susceptibility

被引:12
作者
Liu, Qiang [1 ]
Tang, Aiping [1 ]
Huang, Ziyuan [1 ]
Sun, Lixin [2 ]
Han, Xiaosheng [3 ]
机构
[1] Harbin Inst Technol, Sch Civil Engn, 73 Huanghe Rd, Harbin 150001, Peoples R China
[2] Tianjin Univ, Dept Engn Management, Tianjin 300072, Peoples R China
[3] China Univ Geosci Beijing, Sch Engn & Technol, Beijing 100083, Peoples R China
关键词
Machine learning; Factor importance; Map appearance; Heterogeneity investigation; SUPPORT VECTOR MACHINE; LOGISTIC-REGRESSION; SPATIAL PREDICTION; ROTATION FOREST; NEURAL-NETWORK; ENSEMBLE; AREA; SELECTION; COUNTY; BASIN;
D O I
10.1007/s11069-022-05329-4
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
This study reported an application of the tree-based models to landslide susceptibility. The landslide inventory and ten conditioning factors were first constructed, based on data availability and climate. Subsequently, three tree-based models, decision tree (DT), DT-Boosting, and random forest (RF), were established and compared with the support vector machine (SVM) to analyze the difference in model prediction. Finally, the effect and causes of tree-based algorithms on prediction results were explored based on the working mechanism of the susceptibility model. Results show that there is no multicollinearity among the conditioning factors. The predicted results produced by the tree-based model display the discontinuous distribution compared with the SVM, not only presented in the point-based prediction but the surface-based heterogeneity. Moreover, heterogeneity on the susceptibility map relates to the tree-based algorithm and factor grading, especially the classification of important factors. Besides, DT-Boosting appears the highest numerical features, with large values of AUC (0.981), specificity (0.960), sensitivity (0.956) and accuracy (0.958) in the training phase, and high prediction of AUC (0.862), specificity (0.759), sensitivity (0.843) and accuracy (0.801) in the validation phase. In terms of fluctuation, the RF is smaller than that of DT-Boosting. Further, the susceptibility map generated by RF, with the largest D-value of 7.81, can well capture the difference in landslide susceptibility. This study provides a deep understanding for the application of tree-based machine learning models to landslide susceptibility.
引用
收藏
页码:887 / 911
页数:25
相关论文
共 62 条
  • [1] How do machine learning techniques help in increasing accuracy of landslide susceptibility maps?
    Achour, Yacine
    Pourghasemi, Hamid Reza
    [J]. GEOSCIENCE FRONTIERS, 2020, 11 (03) : 871 - 883
  • [2] Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin), Turkey
    Akinci, Halil
    Zeybek, Mustafa
    [J]. NATURAL HAZARDS, 2021, 108 (02) : 1515 - 1543
  • [3] A comparative analysis of statistical landslide susceptibility mapping in the southeast region of Minas Gerais state, Brazil
    Barella, Cesar Falcao
    Sobreira, Frederico Garcia
    Zezere, Jose Luis
    [J]. BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (05) : 3205 - 3221
  • [4] A novel hybrid model of Bagging-based Naive Bayes Trees for landslide susceptibility assessment
    Binh Thai Pham
    Prakash, Indra
    [J]. BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (03) : 1911 - 1925
  • [5] A hybrid machine learning ensemble approach based on a Radial Basis Function neural network and Rotation Forest for landslide susceptibility modeling: A case study in the Himalayan area, India
    Binh Thai Pham
    Shirzadi, Ataollah
    Dieu Tien Bui
    Prakash, Indra
    Dholakia, M. B.
    [J]. INTERNATIONAL JOURNAL OF SEDIMENT RESEARCH, 2018, 33 (02) : 157 - 170
  • [6] A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India)
    Binh Thai Pham
    Pradhan, Biswajeet
    Bui, Dieu Tien
    Prakash, Indra
    Dholakia, M. B.
    [J]. ENVIRONMENTAL MODELLING & SOFTWARE, 2016, 84 : 240 - 250
  • [7] Exploring relationships between grid cell size and accuracy for debris-flow susceptibility models: a test in the Giampilieri catchment (Sicily, Italy)
    Cama, M.
    Conoscenti, C.
    Lombardo, L.
    Rotigliano, E.
    [J]. ENVIRONMENTAL EARTH SCIENCES, 2016, 75 (03) : 1 - 21
  • [8] Landslide susceptibility estimation by random forests technique: sensitivity and scaling issues
    Catani, F.
    Lagomarsino, D.
    Segoni, S.
    Tofani, V.
    [J]. NATURAL HAZARDS AND EARTH SYSTEM SCIENCES, 2013, 13 (11) : 2815 - 2831
  • [9] Novel hybrid artificial intelligence approach of bivariate statistical-methods-based kernel logistic regression classifier for landslide susceptibility modeling
    Chen, Wei
    Shahabi, Himan
    Shirzadi, Ataollah
    Hong, Haoyuan
    Akgun, Aykut
    Tian, Yingying
    Liu, Junzhi
    Zhu, A-Xing
    Li, Shaojun
    [J]. BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (06) : 4397 - 4419
  • [10] Spatial prediction of landslide susceptibility using data mining-based kernel logistic regression, naive Bayes and RBFNetwork models for the Long County area (China)
    Chen, Wei
    Yan, Xusheng
    Zhao, Zhou
    Hong, Haoyuan
    Bui, Dieu Tien
    Pradhan, Biswajeet
    [J]. BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2019, 78 (01) : 247 - 266