High-resolution snow depth prediction using Random Forest algorithm with topographic parameters: A case study in the Greiner watershed, Nunavut

Increased surface temperatures (0.7 degrees 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 (S-x), 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%) (R-2 = 0.79) at 10 m resolution for an arctic watershed (1500 km(2)) in western Nunavut, Canada.

Automated summary

Increasing surface temperatures in the Arctic have reduced the extent and duration of annual snow cover, affecting polar ecosystems. Accurate monitoring of these ecosystems requires detailed information on snow cover properties at resolutions below 100 meters. In this study, a machine learning method using topographic parameters and the Random Forest algorithm was applied to an arctic landscape, providing predictions of snow depth distributions with good accuracy.