Past and future changes in avalanche problems in northern Norway estimated with machine-learning models

Abstract. Snow-avalanche hazard in mountainous areas may change in frequency and severity due to climatic change, especially in Arctic regions such as northern Norway experiencing Arctic temperature amplification. Building on earlier work, we train machine-learning models on dynamically downscaled reanalysis and model future projection data including snow-cover simulations to predict a binary avalanche danger metric (avalanche day/non-avalanche day) for the Troms county in northern Norway. Due to incomplete avalanche observations, we construct the metric from the avalanche danger warnings published in the Norwegian avalanche bulletin. The frequency of avalanche days is hindcasted for the period 1970 to 2024 (reanalysis) and projected into the future for the 21st century (climate model simulations). The results confirm earlier studies showing that while multi-decadal linear trends are marginal, the interannual variability of the avalanche-day frequency is linked to the Arctic Oscillation. The projected future changes indicate a general decrease of avalanche danger, especially for dry-snow avalanches. In contrast, wet-snow avalanche danger exhibits changes dependent on elevation, increasing at all elevations until mid-century, but thereafter continuing the increase only at higher elevation, while at lower elevation a decrease sets in. Our results are in line with an emerging consensus of a general decline of avalanche danger in the 21st century, however showing a shift in avalanche characteristics towards fewer dry and more wet-snow avalanches.