Dynamic rainfall-induced landslide susceptibility: a step towards a unified forecasting system

Abstract

The initial inception of the landslide susceptibility concept defined it as a static property of the landscape, explaining the proneness of certain locations to generate slope failures. Since the spread of data-driven probabilistic solutions though, the original susceptibility definition has been challenged to incorporate dynamic elements that would lead the occurrence probability to change both in space and in time. This is the starting point of this work, which combines the traditional strengths of the susceptibility framework together with the strengths typical of landslide early warning systems. Specifically, we model landslide occurrences in the norther sector of Vietnam, using a multi-temporal landslide inventory recently released by NASA. A set of static (terrain) and dynamic (cumulated rainfall) covariates are selected to explain the landslide presence/absence distribution via a Bayesian version of a binomial Generalized Additive Models (GAM). Thanks to the large spatiotemporal domain under consideration, we include a large suite of cross-validation routines, testing the landslide prediction through random sampling, as well as through stratified spatial and temporal sampling. We even extend the model test towards regions far away from the study site, to be used as external validation datasets. The overall performance appears to be quite high, with Area Under the Curve (AUC) values in the range of excellent model results, and very few localized exceptions. This model structure may serve as the basis for a new generation of early warning systems. However, the use of The Climate Hazards group Infrared Precipitation with Stations (CHIRPS) for the rainfall component limits the model ability in terms of future prediction. Therefore, we envision subsequent development to take this direction and move towards a unified dynamic landslide forecast. Ultimately, as a proof-of-concept, we have also implemented a potential early warning system in Google Earth Engine.

An ensemble neural network approach for space-time landslide predictive modelling

“…Here, we introduce an alternative based on three recent studies by Fang et al (2023), Moreno et al (2023) and Ahmed et al (2023). The first paper proposed treating rainfall as a continuous signal rather than simplifying it in a single value.…”

“…While several studies have focused on assessing the spatial landslide susceptibility in Vietnam (e.g. Bien et al, 2023;Le Minh et al, 2023;Ngyuen et al, 2023), few studies have attempted to link spatiotemporal patterns of the trigger to the landslide hazard (Ahmed et al, 2023;Moreno et al, 2023, Gian et al, 2017Nhu et al, 2019). For example, Tien et al ( 2013) introduced a 15-day cumulative rainfall threshold to develop spatial and temporal landslide probability maps, but besides rainfall no other environmental factor was used.…”

“…Furthermore, the rainfall data in that study was derived from rain gauge stations, which were not always near the landslide occurrence locations, thereby potentially poorly representing the rainfall characteristics. While the modelling framework employed by Ahmed et al (2023) accounted for interactions between the spatial and temporal components of the landslide hazard, the study focused exclusively on the northern part of Vietnam. In addition, the framework was based on a Bayesian version of a binomial Generalized Additive Model informed by the rainfall pattern as a function of scalar cumulative rainfall.…”