Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2024

Abstract

Landslides pose significant and ever-threatening risks to human life and infrastructure worldwide. Landslide susceptibility modelling is an emerging field of research seeking to determine contributing factors of these events. Yet, previous studies rarely explored the spatial variation of different landslide factors. Hence, this study aims to demonstrate the potential contribution of spatial nonstationarity in landslide susceptibility modelling using Global Logistic Regression (GLR) and Geographically Weighted Logistic Regression (GWLR). The second objective of this study is to demonstrate the important role of data preparation, data sampling, variable sensing, and variable selections in landslide susceptibility modelling. Using Valtellina Valley in Northern Italy as the study area, our study shows that by incorporating spatial heterogeneity and modelling spatial relationships, the measures of Goodness-of-fit of GWLR outperform the traditional GLR. Furthermore, the model outputs of GWLR reveal statistically significant factors contributing to landslides and the spatial variation of these factors in the form of coefficient maps and a landslide susceptibility map.

Keywords

Landslide Susceptibility, Geographically Weighted Logistic Regression, Logistic Regression, Explanatory Modelling

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 24th International Conference on Computational Science and Its Applications, Hanoi, Vietnam, July 1-4

First Page

221

Last Page

238

ISBN

9783031646041

Identifier

10.1007/978-3-031-64605-8_16

Publisher

Springer

City or Country

Cham

Additional URL

https://doi.org/10.1007/978-3-031-64605-8_16

Share

COinS