Preprints
https://doi.org/10.5194/nhess-2021-168
https://doi.org/10.5194/nhess-2021-168

  08 Jul 2021

08 Jul 2021

Review status: this preprint is currently under review for the journal NHESS.

Automated landslide detection outperforms manual mapping for several recent large earthquakes

David Graham Milledge1, Dino G. Bellugi2, Jack Watt3, and Alexander Logan Densmore3 David Graham Milledge et al.
  • 1School of Engineering, Newcastle University, Newcastle upon Tyne, UK
  • 2Department of Geography, University of California, Berkeley, CA, USA
  • 3Institute of Hazard, Risk, and Resilience and Department of Geography, Durham University, Durham, UK

Abstract. Earthquakes in mountainous areas can trigger thousands of co-seismic landslides, causing significant damage, hampering relief efforts, and rapidly redistributing sediment across the landscape. Efforts to understand the controls on these landslides rely heavily on manually mapped landslide inventories, but these are costly and time-consuming to collect, and their reproducibility is not typically well constrained. Here we develop a new automated landslide detection algorithm (ALDI) based on pixel-wise NDVI differencing of Landsat time series within Google Earth Engine accounting for seasonality. We compare classified inventories to manually mapped inventories from five recent earthquakes: 2005 Kashmir, 2007 Aisen, 2008 Wenchuan, 2010 Haiti, and 2015 Gorkha. We test the ability of ALDI to recover landslide locations (using ROC curves) and landslide sizes (in terms of landslide area-frequency statistics). We find that ALDI more skilfully identifies landslides than published inventories in 10 of 14 cases when ALDI is locally optimised, and in 8 of 14 cases both when ALDI is globally optimised and in holdback testing. These results reflect both good performance of the automated approach but also surprisingly poor performance of manual mapping, which has implications not only for how future classifiers are tested but also for the interpretations that are based on these inventories. We conclude that ALDI already represents a viable alternative to manual mapping in terms of its ability to identify landslide-affected image pixels. Its fast run-time, cost-free image requirements and near-global coverage make it an attractive alternative with the potential to significantly improve the coverage and quantity of landslide inventories. Its simplicity (pixel-wise analysis only) and parsimony of inputs (optical imagery only) suggests that considerable further improvement should be possible.

David Graham Milledge et al.

Status: open (until 19 Aug 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

David Graham Milledge et al.

David Graham Milledge et al.

Viewed

Total article views: 301 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
207 91 3 301 16 3 6
  • HTML: 207
  • PDF: 91
  • XML: 3
  • Total: 301
  • Supplement: 16
  • BibTeX: 3
  • EndNote: 6
Views and downloads (calculated since 08 Jul 2021)
Cumulative views and downloads (calculated since 08 Jul 2021)

Viewed (geographical distribution)

Total article views: 274 (including HTML, PDF, and XML) Thereof 274 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 01 Aug 2021
Download
Short summary
Earthquakes can trigger thousands of landslides, causing severe and widespread damage. Efforts to understand what controls these landslides rely heavily on costly and time-consuming manual mapping from satellite imagery. We developed a new method that automatically detects landslides triggered by an earthquake using thousands of free satellite images. We found that in the majority of cases, it was better able to identify the locations of landslides than the manual maps that we tested it against.
Altmetrics