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

TLDR

The study compares support vector machines, decision tree, and Naïve Bayes models for predicting landslide hazards in Vietnam’s Hoa Binh province. Using a 118‑landslide inventory, ten conditioning factors, and a 70/30 training–validation split, the authors computed susceptibility maps with SVM, DT, and NB and validated them on the remaining landslides. Validation revealed SVM achieved the highest prediction accuracy, DT the lowest, with SVM slightly outperforming logistic regression and both DT and NB performing worse.

Abstract

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.