Data-Driven Landslide Nowcasting at the Global Scale

Abstract

Landslides affect nearly every country in the world each year. To better understand this global hazard, the Landslide Hazard Assessment for Situational Awareness (LHASA) model was developed previously. LHASA version 1 combines satellite precipitation estimates with a global landslide susceptibility map to produce a gridded map of potentially hazardous areas from 60° North-South every 3 h. LHASA version 1 categorizes the world’s land surface into three ratings: high, moderate, and low hazard with a single decision tree that first determines if the last seven days of rainfall were intense, then evaluates landslide susceptibility. LHASA version 2 has been developed with a data-driven approach. The global susceptibility map was replaced with a collection of explanatory variables, and two new dynamically varying quantities were added: snow and soil moisture. Along with antecedent rainfall, these variables modulated the response to current daily rainfall. In addition, the Global Landslide Catalog (GLC) was supplemented with several inventories of rainfall-triggered landslide events. These factors were incorporated into the machine-learning framework XGBoost, which was trained to predict the presence or absence of landslides over the period 2015–2018, with the years 2019–2020 reserved for model evaluation. As a result of these improvements, the new global landslide nowcast was twice as likely to predict the occurrence of historical landslides as LHASA version 1, given the same global false positive rate. Furthermore, the shift to probabilistic outputs allows users to directly manage the trade-off between false negatives and false positives, which should make the nowcast useful for a greater variety of geographic settings and applications. In a retrospective analysis, the trained model ran over a global domain for 5 years, and results for LHASA version 1 and version 2 were compared. Due to the importance of rainfall and faults in LHASA version 2, nowcasts would be issued more frequently in some tropical countries, such as Colombia and Papua New Guinea; at the same time, the new version placed less emphasis on arid regions and areas far from the Pacific Rim. LHASA version 2 provides a nearly real-time view of global landslide hazard for a variety of stakeholders.

Estimating global landslide susceptibility and its uncertainty through ensemble modelling

“…For Africa, Broeckx et al (2018) found a (limited) impact of the presence of unconsolidated sediments and siliclastic sedimentary rocks on LSS. Stanley et al (2021) found the lithology (regrouped from GLiM) to be the least important factor. While local lithology plays a vital role for landslide occurrence, the large data uncertainty and often very broad definitions (as for example elaborated by Campforts et al (2020) in a different context) hinder meaningful contributions to LSS assessment, even for smaller scale studies.…”

“…We use reported hydrologically triggered landslide occurrences from the most recent version of the GLC (https://landslides.nasa.gov/viewer, accessed 8th February 2021). The GLC is a landslide inventory based on media reports (Kirschbaum et al, 2010(Kirschbaum et al, , 2015, which has been supplemented with the citizen science based Landslide Reporter Catalog (LRC) data (Juang et al, 2019), see Stanley et al (2021) for details. Any reference to the GLC hereafter refers to this combined data product.…”

Strategies for landslide detection using open-access synthetic aperture radar backscatter change in Google Earth Engine

“…Kirschbaum and Stanley (2018) identified potential landslide activity with the Landslide Hazard Assessment for Situational Awareness (LHASA) model, which combines satellite-based precipitation estimates from GPM with a global landslide susceptibility map. A second version upgraded LHASA from categorical to probabilistic outputs (Stanley et al, 2021). LHASA version 2.0 also estimates the potential exposure of population and roads to landslide disasters (Emberson et al, 2020).…”

“…Satellite-based optical imagery provides high quality information for landslide mapping. Many studies have leveraged these data with manual (e.g., Harp and Jibson, 1996;Liao and Lee, 2000;Massey et al, 2020) and semi-automated/automated mapping techniques to identify landslides (e.g., Amatya et al, 2019Amatya et al, , 2021Ghorbanzadeh et al, 2019;Hölbling et al, 2015;Lu et al, 2019;Mondini et al, 2011Mondini et al, , 2013Stumpf and Kerle, 2011). While optical imagery provides high quality data, it is often limited in rapid response efforts because optical imagery requires daylight as well as shadow-and cloud-free conditions for accurately identifying landslides.…”

Comment on nhess-2021-283

“…Satellite-based optical imagery provides high quality information for landslide mapping. Many studies have leveraged these data with manual (e.g., Harp and Jibson, 1996;Liao and Lee, 2000;Massey et al, 2020) and semi-automated/automated mapping techniques to identify landslides (e.g., Amatya et al, 2019Amatya et al, , 2021Ghorbanzadeh et al, 2019;Hölbling et al, 2015;Lu et al, 2019;Mondini et al, 2011Mondini et al, , 2013Stumpf and Kerle, 2011). While optical imagery provides high quality data, it is often limited in rapid response efforts because optical imagery requires daylight as well as shadow-and cloud-free conditions for accurately identifying landslides.…”