摘要：We evaluated a novel tool that predicts possible maternity den habitat of the polar bear (Ursus maritimus) based on a physical snow transport model, a digital terrain model and weather data. We observed and compared den locations in three important denning areas in east Svalbard (Kongsøya, n = 288; Svenskøya, n = 86; Hopen, n = 115) with modelled snowdrift distributions for 24 years. Accounting for a likely position uncertainty of 100 m, 69% of all dens were located within year-specific modelled snowdrifts. These covered on average 1.8%, 2.1% and 24.7% of the three study islands, respectively. Our snowdrift model accurately predicted maternity den positions (R2 = 0.42, area under the receiving operating characteristic curve [AUC] = 0.85). A model based on slope and altitude, also predicted den positions reasonably well (R2 = 0.35, AUC = 0.88). Habitat maps identifying both current and future areas for maternity denning will become important in managing the Barents Sea population as well as other Arctic populations where changes in sea-ice conditions alter the accessibility to traditional denning areas.
