Preprints
https://doi.org/10.5194/egusphere-2025-2764
https://doi.org/10.5194/egusphere-2025-2764
30 Jun 2025
 | 30 Jun 2025
Status: this preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).

Feature Selection for Landslide Forecasting Models in Southern Andes

Manuel Labbe, Millaray Curilem, Ivo Fustos-Toribio, and Mario Pooley

Abstract. Rainfall-induced landslide (RIL) forecasting is crucial for early warning systems developed to mitigate the devastating impacts of these events on human lives, infrastructure, and the environment. Currently, dense instrumental networks for early warning require large datasets to identify precursor patterns in current machine learning models. Topographic, lithological, vegetation, soil moisture, and climatic characteristics are among the most commonly used variables for training these models. However, there are no universal designs, so it is necessary to adapt the requirements to each context and to the available variables that characterise it. To develop a RIL forecasting model for the Southern Andes, this study gathers data from various local soil and climate databases to identify the most relevant variables. Feature selection is crucial for improving the design of machine learning models, reducing the dimensionality of input data, enhancing computational efficiency, and preventing overfitting. We assessed the impact of various features, both individually and in combination, on the performance of predictive models. Methods such as Classification and Regression Tree and Genetic Algorithms are employed to perform the feature selection. A national landslide database was enriched using techniques such as buffer control sampling, PU Bagging, and clustering methods to incorporate negative examples (non-landslide) data. Various predictive models were tested. The results reveal some consistent variables as the most significant in forecasting landslides in four southern Chilean regions.

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 paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Manuel Labbe, Millaray Curilem, Ivo Fustos-Toribio, and Mario Pooley

Status: open (until 06 Sep 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-2764', Anonymous Referee #1, 31 Jul 2025 reply
Manuel Labbe, Millaray Curilem, Ivo Fustos-Toribio, and Mario Pooley
Manuel Labbe, Millaray Curilem, Ivo Fustos-Toribio, and Mario Pooley

Viewed

Total article views: 433 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
356 66 11 433 9 17
  • HTML: 356
  • PDF: 66
  • XML: 11
  • Total: 433
  • BibTeX: 9
  • EndNote: 17
Views and downloads (calculated since 30 Jun 2025)
Cumulative views and downloads (calculated since 30 Jun 2025)

Viewed (geographical distribution)

Total article views: 440 (including HTML, PDF, and XML) Thereof 440 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 03 Sep 2025
Download
Short summary
We investigated methods to improve the prediction of landslides triggered by heavy rainfall in southern Chile, utilising local soil and climate data. We tested different models and selected the most critical environmental factors. We improved the process for making forecasts in areas with limited monitoring. Our results help create faster and more reliable warnings and can guide safety planning in other mountain regions facing similar risks.
Share