Preprints
https://doi.org/10.5194/nhess-2024-76
https://doi.org/10.5194/nhess-2024-76
22 May 2024
 | 22 May 2024
Status: a revised version of this preprint is currently under review for the journal NHESS.

Predicting the thickness of shallow landslides in Switzerland using machine learning

Christoph Schaller, Luuk Dorren, Massimiliano Schwarz, Christine Moos, Arie C. Seijmonsbergen, and E. Emiel van Loon

Abstract. Landslide thickness is a key parameter in various types of models used to simulate landslide susceptibility. In this study, we developed a model providing improved predictions of potential shallow landslide thickness in Switzerland. We tested three machine learning models based on random forests, generalized additive model, and linear regression and compared the results to three existing models that link soil thickness to slope and elevation. The models were calibrated using data from two field inventories in Switzerland ("HMDB" with 709 records and "KtBE" with 517 records). We explored 37 different covariates including metrics on terrain, geomorphology, vegetation height, and lithology at three different cell sizes. To train the machine learning models, 21 variables were chosen based on the variable importance derived from random forest models and expert judgement. Our results show that the machine learning models consistently outperformed the existing models by reducing the mean absolute error by at least 17 %. The random forests models produced a mean absolute error of 0.25 m for the HMDB and 0.19 m for the KtBE data. Models based on machine learning substantially improve the prediction of landslide thickness, offering refined input for enhancing the performance of slope stability simulations.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Christoph Schaller, Luuk Dorren, Massimiliano Schwarz, Christine Moos, Arie C. Seijmonsbergen, and E. Emiel van Loon

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2024-76', Anonymous Referee #1, 23 Jun 2024
    • AC1: 'Reply on RC1', Christoph Schaller, 29 Jul 2024
  • RC2: 'Comment on nhess-2024-76', Anonymous Referee #2, 24 Jun 2024
    • AC1: 'Reply on RC1', Christoph Schaller, 29 Jul 2024
Christoph Schaller, Luuk Dorren, Massimiliano Schwarz, Christine Moos, Arie C. Seijmonsbergen, and E. Emiel van Loon

Model code and software

HAFL-WWI/Landslide_Thickness_Prediction: Release for Predicting shallow landslide thickness using ML v0.1.1 Christoph Schaller https://doi.org/10.5281/zenodo.11032083

Christoph Schaller, Luuk Dorren, Massimiliano Schwarz, Christine Moos, Arie C. Seijmonsbergen, and E. Emiel van Loon

Viewed

Total article views: 737 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
457 145 135 737 24 22
  • HTML: 457
  • PDF: 145
  • XML: 135
  • Total: 737
  • BibTeX: 24
  • EndNote: 22
Views and downloads (calculated since 22 May 2024)
Cumulative views and downloads (calculated since 22 May 2024)

Viewed (geographical distribution)

Total article views: 710 (including HTML, PDF, and XML) Thereof 710 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Oct 2024
Download
Short summary
We developed a machine learning-based approach to predict the potential thickness of shallow landslides to generate improved inputs for slope stability models. We selected 21 explanatory variables including metrics on terrain, geomorphology, vegetation height, and lithology and used data from two Swiss field inventories to calibrate and test the models. The best performing machine learning model consistently reduced the mean average error by least 17 % compared to previously existing models.
Altmetrics