Future Avalanche Problems in Northern Norway Estimated with Machine-Learning Models

Snow avalanches are an important natural hazard and will likely change their characteristics under climate change. We train machine-learning models on dynamically downscaled reanalysis 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 projected into the future for the 21st century (climate model simulations). The projections indicate a general decrease of avalanche danger, especially for dry-snow avalanches. In contrast, wet-snow avalanche danger changes depend on elevation, generally increasing until mid-century, but thereafter continuing the increase only at higher elevation, while at lower elevation reversing to a decrease. Our results are in line with an emerging consensus of a general decline of avalanche danger in the 21st century and a shift in avalanche characteristics towards fewer dry and more wet-snow avalanches. Such a shift can be demanding as experience and knowledge of local avalanche challenges may no longer be sufficiently relevant and provide protection.