The small scale distribution of the snowpack in mountain areas is highly heterogeneous, and is mainly controlled by the interactions between the atmosphere and local topography. However, the influence of different terrain features in controlling variations in the snow distribution depends on the characteristics of the study area. As this leads to uncertainties in high spatial resolution snowpack simulations, a deeper understanding of the role of terrain features on the small scale distribution of snow depth is required. This study applied random forest algorithms to investigate the temporal evolution of snow depth in complex alpine terrain using as predictors various topographical variables and in situ snow depth observations at a single location. The high spatial resolution (1 m x 1 m) snow depth distribution database used in training and evaluating the random forests was derived from terrestrial laser scanner (TLS) devices at three study sites, in the French Alps (2 sites) and the Spanish Pyrenees (1 site). The results show the major importance of two topographic variables, the topographic position index and the maximum upwind slope parameter. For these variables the search distances and directions depended on the characteristics of each site and the TLS acquisition date, but are consistent across sites and are tightly related to main wind directions. The weight of the different topographic variables on explaining snow distribution evolves while major snow accumulation events still take place and minor changes are observed after reaching the annual snow accumulation peak. Random forests have demonstrated good performance when predicting snow distribution for the sites included in the training set with R 2 values ranging from 0.82 to 0.94 and mean absolute errors always below 0.4 m. Oppositely, this algorithm failed when used to predict snow distribution for sites not included in the training set, with mean absolute errors above 0.8 m.

Increased surface temperatures (0.7°C per decade) in the Arctic affects polar ecosystems by reducing the extent and duration of annual snow cover. Monitoring of these important ecosystems needs detailed information on snow cover properties at resolutions (<100 m) that influence ecological habitats and permafrost thaw. A machine learning method using topographic parameters with the Random Forest (RF) algorithm previously developed in alpine environments was applied over an arctic landscape for the first time. The topographic parameters used in the RF algorithm were Topographic Position Index (TPI) and up‐wind slope index (Sx), which were estimated from the freely available Arctic DEM at 2 m resolution. Addition of an ecotype parameter (proxy for vegetation height) showed minimal predictive improvement. Using RF, snow depth distributions were predicted from topographic parameters with a root mean square error = 8 cm (23%) (R2 = 0.79) at 10 m resolution for an arctic watershed (1500 km2) in western Nunavut, Canada.