Preprints
https://doi.org/10.5194/egusphere-2023-2948
https://doi.org/10.5194/egusphere-2023-2948
22 Jan 2024
 | 22 Jan 2024

A three-stage model pipeline predicting regional avalanche danger in Switzerland (RAvaFcast v1.0.0): a decision-support tool for operational avalanche forecasting

Alessandro Maissen, Frank Techel, and Michele Volpi

Abstract. Despite the increasing use of physical snow-cover simulations in regional avalanche forecasting, avalanche forecasting is still an expert-based decision-making process. However, recently, it has become possible to obtain fully automated avalanche danger level predictions with satisfying accuracy by combining physically-based snow-cover models with machine learning approaches. These predictions are made at the location of automated weather stations close to avalanche starting zones. To bridge the gap between these local predictions and fully data- and model-driven regional avalanche danger maps, we developed and evaluated a three-stage model pipeline (RAvaFcast v1.0.0), involving the steps classification, interpolation, and aggregation. More specifically, we evaluated the impact of various terrain features on the performance of a Gaussian process-based model for interpolation of local predictions to unobserved locations on a dense grid. Aggregating these predictions using an elevation-based strategy, we estimated the regional danger level and the corresponding elevation range for predefined warning regions, resulting in a forecast similar to the human-made avalanche forecast in Switzerland. The best-performing model matched the human-made forecasts with a mean day accuracy of approximately 66 % for the entire forecast domain, and 70 % specifically for the Alps. However, the performance depended strongly on the classifier's accuracy (i.e., a mean day accuracy of 68 %) and the density of local predictions available for the interpolation task. Despite these limitations, we believe that the proposed three-stage model pipeline has the potential to improve the interpretability of machine-made danger level predictions and has, thus, the potential to assist avalanche forecasters during forecast preparation, for instance, by being integrated in the forecast process in the form of an independent virtual forecaster.

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.
Alessandro Maissen, Frank Techel, and Michele Volpi

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-2948', Simon Horton, 02 Mar 2024
    • AC1: 'Reply on RC1', Alessandro Maissen, 13 Jun 2024
  • RC2: 'Comment on egusphere-2023-2948', Anonymous Referee #2, 17 May 2024
    • AC2: 'Reply on RC2', Alessandro Maissen, 13 Jun 2024
  • EC1: 'Further review comments', Fabien Maussion, 21 May 2024
    • AC3: 'Reply on EC1', Alessandro Maissen, 13 Jun 2024
Alessandro Maissen, Frank Techel, and Michele Volpi
Alessandro Maissen, Frank Techel, and Michele Volpi

Viewed

Total article views: 492 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
362 103 27 492 24 15 14
  • HTML: 362
  • PDF: 103
  • XML: 27
  • Total: 492
  • Supplement: 24
  • BibTeX: 15
  • EndNote: 14
Views and downloads (calculated since 22 Jan 2024)
Cumulative views and downloads (calculated since 22 Jan 2024)

Viewed (geographical distribution)

Total article views: 491 (including HTML, PDF, and XML) Thereof 491 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 22 Jun 2024
Download
Short summary
By harnessing AI-models, this work enables processing large amounts of data, including weather conditions, snowpack characteristics, and historical avalanche data, to predict human-like avalanche forecasts in Switzerland. Our proposed model can significantly assist avalanche forecasters in their decision-making process, and thereby facilitating more efficient and accurate predictions crucial for ensuring safety in Switzerland's avalanche-prone regions.