Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models

By D. Tien Bui, Biswajeet Pradhan, O. Lofman, Inge Revhaug. 2012

563 citations recorded by the source corpus.

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 Naive 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.

Subfields: Global and Planetary Change, Management, Monitoring, Policy and Law, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/04fdfc47feeb4405a8705cc3dfdf1faf91b9616e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Global and Planetary Change

In Management, Monitoring, Policy and Law

In Mechanical Engineering

Citations in the corpus

Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province, Iran (2013, methodology): “…Gomez and Kavzoglu 2005; Nefeslioglu et al. 2008; Pradhan et al. 2010b; Pradhan and Lee 2009, 2010a, b; Yilmaz 2009a, b, 2010a, b; Zare et al. 2012; Bui et al. 2012b), neuro-fuzzy (Pradhan et al. 2010a; Vahidnia et al. 2010; Sezer et al. 2011; Oh and Pradhan 2011; Bui et al. 2012a), decision tree…”
Prediction of Slope Stability using Naive Bayes Classifier (2018, methodology): “Although NBCs have been applied to assess the susceptibility of landslides (Bui et al., 2012; Pham et al., 2015; Song et al., 2012; Tsangaratos and Ilia, 2016), they have not been employed to predict slope stability.”
Spatial prediction of landslide susceptibility by combining evidential belief function, logistic regression and logistic model tree (2019, methodology): “What is more, the degree of fracturing and weathering also were affected by faults (Tien Bui et al. 2012b).”
A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India) (2016, methodology): “In addition, Tien Bui et al. (2012a) reported that results derived from SVM can produce better landslide susceptibility map compared to decision tree, and naïve bayes methods.”
Machine Learning for the Developing World (2018, background): “A number of researchers have studied the susceptibility for flooding or landslides in Southeast Asia (Tehrany et al. 2014; Tien Bui et al. 2012).”
Landslide susceptibility modelling using different advanced decision trees methods (2018, methodology): “Pp is the proportion of correctly classified instances as ‘landslide’ or ‘non-landslide’ and Pexp is the expected agreements (Tien Bui et al. 2012).”