Abstract
Abstract. We used continuous data from a seismic monitoring system to automatically determine the avalanche activity at a remote field site above Davos, Switzerland. The approach is based on combining a machine learning algorithm with array processing techniques to provide an operational method capable of near real-time classification. First, we used a recently developed method based on hidden Markov models (HMMs) to automatically identify events in continuous seismic data using only a single training event. For the 2016–2017 winter period, this resulted in 117 events. Second, to eliminate falsely classified events such as airplanes and local earthquakes, we implemented an additional HMM-based classifier at a second array 14 km away. By cross-checking the results of both arrays, we reduced the number of classifications by about 50 %. In a third and final step we used multiple signal classification (MUSIC), an array processing technique, to determine the direction of the source. As snow avalanches recorded at our arrays typically generate signals with small changes in source direction, events with large changes were dismissed. From the 117 initially detected events during the 4-month period, our classification workflow removed 96 events. The majority of the remaining 21 events were on 9 and 10 March 2017, in line with visual avalanche observations in the Davos region. Our results suggest that the classification workflow presented could be used to identify major avalanche periods and highlight the importance of array processing techniques for the automatic classification of avalanches in seismic data.
Highlights
During the winter seasons, snow avalanches are a common threat in mountainous regions
The classification workflow we presented used hidden Markov models (HMMs) to automatically detect avalanches in data from seismic systems deployed above Davos, Switzerland
The approach builds on the work of Heck et al (2018), who adapted the HMM method developed by Hammer et al (2017) to detect avalanches in continuous seismic data from a small aperture geophone array
Summary
Snow avalanches are a common threat in mountainous regions. To assess the danger, warning services rely on information about the snowpack, the amount of new snow, the weather conditions and avalanche activity (e.g., McClung and Schaerer, 2006). Rubin et al (2012) compared 12 machine learning algorithms, 10 of which were able to detect at least 90 % of all manually identified avalanches. While these machine learning methods perform reasonably well in terms of detecting confirmed avalanche events, a large training data set is typically re-
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
