Glacier surface mass balance (SMB) modelling has traditionally focused on improving the determination of surface energy balance conditions. However, water routing in the firn including refreezing, as well as the complex patterns of surface accumulation caused by snow drift, are poorly, or not at all, represented in most SMB models. Studies in the literature have often noted the uncertainties due to neglecting such mechanisms. This sub-project aims to improve the model representation of (i) the internal water budget and (ii) the snow drift contribution to the SMB using deep learning.

Within this sub-project, we envisage to combine model-driven simulations of a coupled glacier system with data-driven machine learning techniques at specific benchmark sites in the Alps (e.g., Hintereisferner, Vernagtferner). A well-established ice-flow model will first be employed to produce observation-informed training and test data, which will then inform machine learning components that can replace such classical methods. The ultimate goal is to reduces computational efforts and prepare such hybrid techniques for long timescales and/or regional scales.

The retreat of glacier ice fundamentally changes stability of the surrounding rock and debris slopes due to the massive thermal, mechanical and hydrological change initiating massive creep and rock slope failures (Haeberli et al., 2010). Alpine and arctic polythermal glaciers develop permafrost below the upper cold-based glaciers and unfrozen rock below the warm based lower glacier parts. Glacier retreat and warming cause high rates of permafrost degradation and sometimes aggradation, sudden changes in hydro- and cryostatic pressures and fast changes in lateral ice-stresses on slopes (Krautblatter & Leith, 2015). In SP3.3, we will develop generic mechanical models that undergo rapid thermal, mechanical and hydrological change.