Search

Maps of bottom type are essential to the management of marine resources and biodiversity because of their foundational role in characterizing species' habitats. They are also urgently needed as countries work to define marine protected areas. Current approaches are time consuming, focus largely on grain size, and tend to overlook shallow waters. Our random forest classification of almost 200,000 observations of bottom type is a timely alternative, providing maps of coastal substrate at a combination of resolution and extents not previously achieved. We correlated the observations with depth, depth-derivatives, and estimates of energy to predict marine substrate at 100 m resolution for Canada's Pacific shelf, a study area of over 135,000 km2. We built five regional models with the same data at 20 m resolution. In addition to standard tests of model fit, we used three independent data sets to test model predictions. We also tested for regional, depth, and resolution effects. We guided our analysis by asking: 1) does weighting for prevalence improve model predictions? 2) does model resolution influence model performance? And 3) is model performance influenced by depth? All our models fit the build data well with true skill statistic (TSS) scores ranging from 0.56 to 0.64. Weighting models with class prevalence improved fit and the correspondence with known spatial features. Class-based metrics showed differences across both resolutions and spatial regions, indicating non-stationarity across these spatial categories. Predictive power was lower (TSS from 0.10 to 0.36) based on independent data evaluation. Model performance was also a function of depth and resolution, illustrating the challenge of accurately representing heterogeneity. Our work shows the value of regional analyses to assessing model stationarity and how independent data evaluation and the use of error metrics can improve understanding of model performance and sampling bias., Competing Interests: This funding does not alter our adherence to PLOS ONE policies on sharing data and materials. The specific roles of these authors are articulated in the ‘author contributions’ section.

A leading hypothesis to explain the dramatic decline of Steller sea lions (Eumetopias jubatus) in western Alaska during the latter part of the 20th century is a change in prey availability due to commercial fisheries. We tested this hypothesis by exploring the relationships between sea lion population trends, fishery catches, and the prey biomass accessible to sea lions around 33 rookeries between 2000 and 2008. We focused on three commercially important species that have dominated the sea lion diet during the population decline: walleye pollock, Pacific cod and Atka mackerel. We estimated available prey biomass by removing fishery catches from predicted prey biomass distributions in the Aleutian Islands, Bering Sea and Gulf of Alaska; and modelled the likelihood of sea lions foraging at different distances from rookeries (accessibility) using satellite telemetry locations of tracked animals. We combined this accessibility model with the prey distributions to estimate the prey biomass accessible to sea lions by rookery. For each rookery, we compared sea lion population change to accessible prey biomass. Of 304 comparisons, we found 3 statistically significant relationships, all suggesting that sea lion populations increased with increasing prey accessibility. Given that the majority of comparisons showed no significant effect, it seems unlikely that the availability of pollock, cod or Atka mackerel was limiting sea lion populations in the 2000s.