Influence of landslide inventory timespan and data selection on slope unit-based susceptibility models

Sofie Rolain, Massimiliano Alvioli, Quoc Dinh Nguyen, Thanh Long Nguyen, Lies Jacobs, Matthieu Kervyn

Onderzoeksoutput: Articlepeer review


Key advantages of modelling landslide susceptibility at the level of slope units—homogeneous landscape elements bound by drainage and divide lines—instead of grid cells have recently been highlighted. However, there has been limited investigation into the sensitivity of a slope unit landslide susceptibility approach to the characteristics of the landslide inventory used for calibration and the modelling approach. Here, a slope unit landslide susceptibility assessment is conducted for the Da Bac district, Vietnam, based on a multi-temporal landslide inventory, using logistic regression and support vector machine classification algorithms and a set of environmental and anthropogenic controlling factors. A landslide inventory for the period 2013–2020 was created using Google Earth© imagery, including large landslide events in 2018 and 2019. Results highlight that models calibrated from a sample of a single-year inventory and validated with a later year have the same accuracy as those calibrated with a random sample of the entire inventory. Regardless of the calibration data used, the support vector machine algorithm consistently outperforms logistic regression. This is evident from the lower standard deviation of susceptibility values observed when compared to those obtained using logistic regression. The landslide susceptibility models for slope units remain reliable, even when calibrated using a temporally short and event-specific landslide inventory.
Originele taal-2English
Pagina's (van-tot)2227–2244
Aantal pagina's18
TijdschriftNatural Hazards
Nummer van het tijdschrift3
StatusPublished - 11 jul 2023

Bibliografische nota

Funding Information:
This article is a contribution to the 2020-2022 VLIR UOS South Initiative project called “Building capacity for disaster management for the mountainous region of the Da Bac district, Hoa Binh Province, Vietnam” (VN2020SIN316A), between the VUB and the Vietnamese Institute of Geoscience and Mineral Resources (VIGMR), with the Flemish Inter-University Council for Development Cooperation (VLIR UOS) for financial support. The project aims at a better understanding of landslide hazards and their impacts on the population of the Da Bac district. We would like to thank Alisa Spriet for having produced the first version of the landslide inventory in her bachelor paper, and the VIGMR staff for conducting the partial field validation of the landslide data set.

Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer Nature B.V.

Copyright 2023 Elsevier B.V., All rights reserved.


Duik in de onderzoeksthema's van 'Influence of landslide inventory timespan and data selection on slope unit-based susceptibility models'. Samen vormen ze een unieke vingerafdruk.

Citeer dit