Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models

The objective of this study is to investigate and compare the results of three data mining approaches, the support vector machines (SVM), decision tree (DT), and Naïve Bayes (NB) models for spatial prediction of landslide hazards in the Hoa Binh province (Vietnam). First, a landslide inventory map s...

Full description

Bibliographic Details
Main Authors: Tien Bui, Dieu, Pradhan, Biswajeet, Lofman, Owe, Revhaug, Inge
Format: Article
Language:English
Published: Hindawi Publishing Corporation 2012
Online Access:http://psasir.upm.edu.my/id/eprint/40275/
http://psasir.upm.edu.my/id/eprint/40275/1/974638.pdf
_version_ 1848849379040952320
author Tien Bui, Dieu
Pradhan, Biswajeet
Lofman, Owe
Revhaug, Inge
author_facet Tien Bui, Dieu
Pradhan, Biswajeet
Lofman, Owe
Revhaug, Inge
author_sort Tien Bui, Dieu
building UPM Institutional Repository
collection Online Access
description The objective of this study is to investigate and compare the results of three data mining approaches, the support vector machines (SVM), decision tree (DT), and Naïve Bayes (NB) models for spatial prediction of landslide hazards in the Hoa Binh province (Vietnam). First, a landslide inventory map showing the locations of 118 landslides was constructed from various sources. The landslide inventory was then randomly partitioned into 70% for training the models and 30% for the model validation. Second, ten landslide conditioning factors were selected (i.e., slope angle, slope aspect, relief amplitude, lithology, soil type, land use, distance to roads, distance to rivers, distance to faults, and rainfall). Using these factors, landslide susceptibility indexes were calculated using SVM, DT, and NB models. Finally, landslide locations that were not used in the training phase were used to validate and compare the landslide susceptibility maps. The validation results show that the models derived using SVM have the highest prediction capability. The model derived using DT has the lowest prediction capability. Compared to the logistic regression model, the prediction capability of the SVM models is slightly better. The prediction capability of the DT and NB models is lower.
first_indexed 2025-11-15T09:49:27Z
format Article
id upm-40275
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T09:49:27Z
publishDate 2012
publisher Hindawi Publishing Corporation
recordtype eprints
repository_type Digital Repository
spelling upm-402752015-09-15T06:48:32Z http://psasir.upm.edu.my/id/eprint/40275/ Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models Tien Bui, Dieu Pradhan, Biswajeet Lofman, Owe Revhaug, Inge The objective of this study is to investigate and compare the results of three data mining approaches, the support vector machines (SVM), decision tree (DT), and Naïve Bayes (NB) models for spatial prediction of landslide hazards in the Hoa Binh province (Vietnam). First, a landslide inventory map showing the locations of 118 landslides was constructed from various sources. The landslide inventory was then randomly partitioned into 70% for training the models and 30% for the model validation. Second, ten landslide conditioning factors were selected (i.e., slope angle, slope aspect, relief amplitude, lithology, soil type, land use, distance to roads, distance to rivers, distance to faults, and rainfall). Using these factors, landslide susceptibility indexes were calculated using SVM, DT, and NB models. Finally, landslide locations that were not used in the training phase were used to validate and compare the landslide susceptibility maps. The validation results show that the models derived using SVM have the highest prediction capability. The model derived using DT has the lowest prediction capability. Compared to the logistic regression model, the prediction capability of the SVM models is slightly better. The prediction capability of the DT and NB models is lower. Hindawi Publishing Corporation 2012 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/40275/1/974638.pdf Tien Bui, Dieu and Pradhan, Biswajeet and Lofman, Owe and Revhaug, Inge (2012) Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models. Mathematical Problems in Engineering, 2012. art. no. 974638. pp. 1-26. ISSN 1024-123X; ESSN: 1563-5147 http://www.hindawi.com/journals/mpe/2012/974638/ 10.1155/2012/974638
spellingShingle Tien Bui, Dieu
Pradhan, Biswajeet
Lofman, Owe
Revhaug, Inge
Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models
title Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models
title_full Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models
title_fullStr Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models
title_full_unstemmed Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models
title_short Landslide susceptibility assessment in Vietnam using support vector machines, decision tree, and nave bayes models
title_sort landslide susceptibility assessment in vietnam using support vector machines, decision tree, and nave bayes models
url http://psasir.upm.edu.my/id/eprint/40275/
http://psasir.upm.edu.my/id/eprint/40275/
http://psasir.upm.edu.my/id/eprint/40275/
http://psasir.upm.edu.my/id/eprint/40275/1/974638.pdf