Species specific mean projections and uncertainty estimates (coefficient of variation) of80 boreal-breeding songbird species generated using boosted regression tree models for the current period (based on climate data from 1961-1990) and three future time periods (2011–2040, 2041­–2070, 2071–2100).

Tables representing species specific mean density(males/ha) by region and landcover classes. Models for each bird conservation regions (BCRs) intersecting Canadian jurisdictional boundaries were based on covariates such as tree species biomass (local and landscape scale), forest age, topography, land use, and climate. We used a post-hoc stratification (‘post-stratification’) approach to estimate land cover based density estimates (males per ha) for each species and regions (Canada and subunits). We classified the predictive maps according to the 2005 MODIS-based North American landcover map into major land cover types (Conifer, Taiga Conifer, Deciduous, Mixedwood, Shrub, Grass, Arctic Shrub, Arctic Grass, Wetland, Cropland) and calculated the mean of the pixel level predicted densities. Uncertainty was based on the 5th and 95th percentiles of the bootstrap distribution.

Maps of density (males/ha) in relation to environmental covariates, using the Boreal Avian Modelling Project database of point-count surveys.