Understanding the abiotic and biotic drivers of species distribution is critical for climate-informed ecosystem management. We aimed to understand habitat selection of Northern fur sealsin the Eastern Bering Sea, a declining population that is also a key predator of walleye pollock, the target species for the largest U.S. commercial fishery. We developed species distribution models using random forest models by combining satellite telemetry data from lactating female fur seals tagged at different rookery complexes on the Pribilof Islands in the Eastern Bering Sea with regional ocean model simulations. We exploredhow data aggregation at two spatial scales (Pribilof-wide and complex-specific) impacted modelperformance and predicted distributions. Spatial predictions under hindcasted (1992 - 2018) and projected (2050 - 2059) physical and biological conditions were used to identify areas of core habitat, overlap with commercial fishery catches, and potential changes in future habitat suitability. The most important environmental predictor variables across all models were bathymetry, bottom temperature, and surface temperature. The Pribilof-wide model both under- and overrepresented the importance of specific areas, while complex-specific models exhibited considerable variability in transferability performance. The majority of core habitat occurred on the continental shelf in areas that overlapped with commercial catches of walleye pollock during the “B” season (June - October), with an average of 76% of the total percentage of the catch occurring in core fur seal habitat within the foraging range of lactating females. Projections revealed that considerable changes in fur seal habitat suitability may occur in the coming decades, with complex-specific variation in the magnitude and direction of changes. Our results illustrate the need to sample multiple sites whenever possible and consider spatial scale when extrapolating species distribution model output for central-place foragers, even when terrestrial sites are <10 km apart. The high overlap between suitable fur seal habitat and commercial fishery catches of pollock, coupled with projected changes in habitat suitability,underscore the need for targeted studies investigating fisheries impacts on this declining population.

Lactating adult female Northern fur seals from St. Paul (57.19º N, 170.25º W) and St. George Islands (56.60º N, 169.55º W) Alaska, USA were instrumented with satellite tags between 1992 and 2018. Tags remained on females for 1 - 14 foraging trips. Satellite telemetry data were analysed using a continuous-time correlated random walk model to generate hourly predicted locations for each trip. Pseudo-absences were generated using a first-order vector-autoregressive model that resulted in 100 simulated trips that mimicked the speed and duration of each original trip. Environmental data from a regional ocean simulation model for the Bering Sea were extracted at each presence and pseudo-absence, including bathymetry and dynamic physical (e.g., bottom temperature) and biological (e.g., phytoplankton biomass) variables. Absences and pseudo-absences were classified to a habitat type based on bathymetry (continental shelf or basin) and datasets were subsequently split by habitat type. Hourly locations were randomly downsampled to a single location per day. Daily locations from each foraging trip were paired with corresponding locations from a simulated trip so that each trip had the same number of presences and pseudo-absences. Ten replicate datasets were created for each habitat type to assess how different presences (randomly selected daily locations) or pseudo-absences (different simulated trips) affected model output. Additional details are provided in the manuscript associated with this dataset.