Preprints
https://doi.org/10.5194/nhess-2022-141
https://doi.org/10.5194/nhess-2022-141
 
20 May 2022
20 May 2022
Status: this preprint is currently under review for the journal NHESS.

Landsifier v1.0: a Python library to estimate likely triggers of mapped landslides

Kamal Rana1,2,3, Nishant Malik4, and Ugur Ozturk1,3 Kamal Rana et al.
  • 1Helmholtz-Centre Potsdam–GFZ German Research Centre for Geosciences, Potsdam, Germany
  • 2Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY, USA
  • 3Institute of Environmental Science and Geography, University of Potsdam, Potsdam, Germany
  • 4School of Mathematical Sciences, Rochester Institute of Technology, Rochester, NY, USA

Abstract. Landslide hazard models aim at mitigating landslide impact by providing probabilistic forecasting, and the accuracy of these models hinges on landslide databases for model training and testing. Landslide databases at times lack information on the underlying triggering mechanism, making these inventories almost unusable in hazard models. We developed a Python-based library, landsifier, that contains three different Machine-Learning frameworks for assessing the likely triggering mechanisms of individual landslides or entire inventories based on landslide geometry. Two of these methods only use the 2D landslide planforms, and the third utilizes the 3D shape of landslides relying on an underlying Digital Elevation Model (DEM). The base method extracts geometric properties of landslide polygons as a feature space for the shallow learner—Random Forest (RF). An alternative method extracts topological properties of 3D landslides through Topological Data Analysis (TDA) and then feeds these properties as a feature space to the Random Forest classifier. The last framework relies on landslide-planform images as an input for the deep learning algorithm—Convolutional Neural Network (CNN). We tested all three interchangeable methods on several inventories with known triggers spread over the Japanese archipelago. To demonstrate the effectiveness of developed methods, we used two testing configurations. The first configuration merges all the available data for the k-fold cross-validation, whereas the second configuration excludes one inventory during the training phase to use as the sole testing inventory. Classification accuracies for different testing schemes vary between 70 % and 95 %. Finally, we implemented the three methods on an inventory without any triggering information to showcase a real-world application.

Kamal Rana et al.

Status: open (extended)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2022-141', Anonymous Referee #1, 09 Jun 2022 reply

Kamal Rana et al.

Kamal Rana et al.

Viewed

Total article views: 328 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
237 83 8 328 2 4
  • HTML: 237
  • PDF: 83
  • XML: 8
  • Total: 328
  • BibTeX: 2
  • EndNote: 4
Views and downloads (calculated since 20 May 2022)
Cumulative views and downloads (calculated since 20 May 2022)

Viewed (geographical distribution)

Total article views: 293 (including HTML, PDF, and XML) Thereof 293 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 03 Jul 2022
Download
Short summary
The landslide hazard models assist in mitigating losses due to landslides. However, these models depend on landslide databases, which often have missing triggering information, lending these databases unusable for landslide hazard models. In this work, we developed a python library, "Landsifier" consisting of three different methods to identify the triggers of landslides. These methods can classify landslide triggers with high accuracy using only landslide polygon shapefile as an input.
Altmetrics