Item: HUMAN VS. MACHINE - COMPARING MODEL PREDICTIONS AND HUMAN FORECASTS OF AVALANCHE DANGER AND SNOW INSTABILITY IN THE SWISS ALPS
-
-
Title: HUMAN VS. MACHINE - COMPARING MODEL PREDICTIONS AND HUMAN FORECASTS OF AVALANCHE DANGER AND SNOW INSTABILITY IN THE SWISS ALPS
Proceedings: International Snow Science Workshop 2024, Tromsø, Norway
Authors:
- Frank Techel [ WSL Institut for Snow and Avalanche Research SLF, Davos, Switzerland ]
- Andrea Helfenstein [ WSL Institut for Snow and Avalanche Research SLF, Davos, Switzerland ]
- Stephanie Mayer [ WSL Institut for Snow and Avalanche Research SLF, Davos, Switzerland ]
- Cristina Pérez-Guillén [ WSL Institut for Snow and Avalanche Research SLF, Davos, Switzerland ]
- Ross Purves [ University of Zurich, Zurich, Switzerland ]
- Marc Ruesch [ WSL Institut for Snow and Avalanche Research SLF, Davos, Switzerland ]
- Günter Schmudlach [ Skitourenguru GmbH, Switzerland ]
- Katia Soland [ University of Zurich, Zurich, Switzerland ]
- Kurt Winkler [ WSL Institut for Snow and Avalanche Research SLF, Davos, Switzerland ]
Date: 2024-09-23
Abstract: In recent years, the integration of physical snowpack models coupled with machine-learning techniques has become more prevalent in public avalanche forecasting. When combined with spatial interpolation methods, these approaches enable fully data- and model-driven predictions of snowpack stability or avalanche danger at any given location. This prompts the question: Are such highly detailed spatial model predictions sufficiently accurate for operational use? To explore this, we assess the performance of interpolated, model-based predictions of snowpack stability and avalanche danger, comparing them to human-generated public avalanche forecasts during the 2023/2024 winter season in Switzerland. To do so, we compare human forecasts and model predictions for locations in avalanche terrain (considering coordinates, aspect, elevation) where skiers triggered avalanches (244 events) or which were skied but where no avalanche was triggered (non-events, 3177 data points from GPX tracks). While this data reflects human behavior to some extent, we consider the event ratio as a proxy for the probability of avalanche release due to human load. We observed that with increasing model-predicted danger level or decreasing model-predicted snowpack stability, the event ratio increased. Comparing model predictions with human-made forecasts showed that the predictive performance of two operationally used models was similar to the performance of human avalanche forecasts: both predicted a strong increase in the probability of human-triggered avalanches. In summary, our results indicate that models capture regional patterns of snowpack (in)stability or avalanche danger well, and that these model chains should therefore be systematically integrated in the forecasting process.
Object ID: ISSW2024_O1.6.pdf
Language of Article: English
Presenter(s): Frank Techel
Keywords: public avalanche forecasting, forecast verification, machine learning, model-driven predictions
Page Number(s): 31 - 38
-