Large-scale Mapping of Landslide and Debris Flow using Flowr Model with Statistical and Machine Learning Methods

Abstract

The main purpose of this article is to establish a susceptibility zonation map of the landslides and debris flows in Phin Ngan commune, Bat Xat district, Lao Cai province on a large scale using statistical methods and machine learning combined with the FlowR model. First, the five Landslide Susceptibility Index (LSI) maps were established from two statistical models (Logistic Regression - LR, Discriminant Analysis – DA) and three machine learning models (Bayesian Network – BN, Artificial Neural Network – ANN, Support Vector Machine – SVM) were generated based on seven maps of landslide conditioning factors (slope, curvature, stream power index-SPI, topographic wetness index-TWI, sediment transportation index-STI, land use/land cover and weathering crust). Next, the five LSI maps will be evaluated for performance with the value of Area Under the Curve (AUC) according to the Receiver Operating Characteristic (ROC) curve. After that, a susceptibility map of debris flow established with FlowR software was combined with the five LSI maps created from five statistical and machine learning methods to generate a susceptibility zonation map of landslides and debris flows in the study area. The area percentage of the locations with ​​landslides and debris flows located in the zones of susceptibility (very low, low, medium, high, very high), which were created from five combined methods: BN-FlowR, LR-FlowR, DA-FlowR, ANN-FlowR, and SVM-FlowR, were compared and evaluated. The results indicate that the integrated models have given outputs with good forecasting ability. They are also very useful in land-use planning as well as the prevention and mitigation of risks due to landslides and debris flows in the research area and other similar mountainous areas.