Abstract

<strong class="journal-contentHeaderColor">Abstract.</strong> Even today, the assessment of avalanche danger is by and large a subjective yet data-based decision-making process. Human experts analyse heterogeneous data volumes, diverse in scale, and conclude on the avalanche scenario based on their experience. Nowadays, modern machine learning methods and the rise in computing power in combination with physical snow cover modelling open up new possibilities for developing decision support tools for operational avalanche forecasting. Therefore, we developed a fully data-driven approach to assess the regional avalanche danger level, the key component in public avalanche forecasts, for dry-snow conditions in the Swiss Alps. Using a large data set of more than 20 years of meteorological data measured by a network of automated weather stations, which are located at the elevation of potential avalanche starting zones, and snow cover simulations driven with these input weather data, we trained two random forest (RF) classifiers. The first classifier (RF 1) was trained relying on the forecast danger levels published in the official Swiss avalanche bulletin. To reduce the uncertainty resulting from using the forecast danger level as target variable, we trained a second classifier (RF 2) that relies on a quality-controlled subset of danger level labels. We optimized the RF classifiers by selecting the best set of input features combining meteorological variables and features extracted from the simulated profiles. The accuracy of the models, i.e. the percentage of correct danger level predictions, ranged between 74 % and 76 % for RF 1 and between 72 % and 78 % for RF 2. We assessed the accuracy of forecasts with nowcast assessments of avalanche danger by well-trained observers. The performance of both models was similar to the agreement rate between forecast and nowcast assessments of the current experience-based Swiss avalanche forecasts (which is estimated to be 76 %). The models performed consistently well throughout the Swiss Alps, thus in different climatic regions, albeit with some regional differences. Our results suggest that the models may well have potential to become a valuable supplementary decision support tool for avalanche forecasters when assessing avalanche hazard.

Highlights

  • Avalanche forecasting, i.e. predicting current and future snow instability in time and space (McClung, 2000), is crucial to ensure safety and mobility in avalanche-prone areas

  • Using a large data set of more than 20 years of meteorological data measured by a network of automated weather stations, which are located at the elevation of potential avalanche starting zones, and snow cover simulations driven with these input weather data, we trained two random forest (RF) classifiers

  • We developed two random forests classifiers to predict the avalanche danger level based on data provided by a network of 595 automated weather stations in the Swiss Alps (Fig. 1)

Read more

Summary

Introduction

Avalanche forecasting, i.e. predicting current and future snow instability in time and space (McClung, 2000), is crucial to ensure safety and mobility in avalanche-prone areas. In many countries with snow-covered mountain regions, avalanche 25 warning services regularly issue forecasts to inform the public and local authorities about the avalanche hazard. Even today, these forecasts are prepared by human experts. To improve quality and consistency of avalanche forecasts, various statistical models (see Dkengne Sielenou et al (2021) for a recent review) and conceptual approaches were developed. The latter, for instance, include a proposition for a structured work-flow (Statham et al, 2018) and look-up tables (e.g. EAWS, 2017; Techel et al, 2020a), both aiding forecasters in the decision-making process of danger assessment. Avalanche catalogues are uncertain and incomplete (Schweizer et al, 2020) since they rely on visual observations that are not always possible or are delayed; the only solution is to use avalanche detection systems, but such data are still scarce and/or only locally available (e.g. Hendrikx et al, 2018; Heck et al, 2019; Mayer et al, 2020)

Objectives
Findings
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.