Most previous studies on collision impacts at wind facilities have taken place at the site-specific level and have only examined small-scale influences on mortality. In this study, we examine landscape-level influences using a hierarchical spatial model combined with existing datasets and life history knowledge for: Horned Lark, Red-eyed Vireo, Mallard, American Avocet, Golden Eagle, Whooping Crane, red bat, silver-haired bat, and hoary bat. These species were modeled in the central United States within Bird Conservation Regions 11, 17, 18, and 19. For the bird species, we modeled bird abundance from existing datasets as a function of habitat variables known to be preferred by each species to develop a relative abundance prediction for each species. For bats, there are no existing abundance datasets so we identified preferred habitat in the landscape for each species and assumed that greater amounts of preferred habitat would equate to greater abundance of bats. The abundance predictions for bird and bats were modeled with additional exposure factors known to influence collisions such as visibility, wind, temperature, precipitation, topography, and behavior to form a final mapped output of predicted collision risk within the study region. We reviewed published mortality studies from wind farms in our study region and collected data on reported mortality of our focal species to compare to our modeled predictions. We performed a sensitivity analysis evaluating model performance of 6 different scenarios where habitat and exposure factors were weighted differently. We compared the model performance in each scenario by evaluating observed data vs. our model predictions using spearmans rank correlations. Horned Lark collision risk was predicted to be highest in the northwestern and west-central portions of the study region with lower risk predicted elsewhere. Red-eyed Vireo collision risk was predicted to be the highest in the eastern portions of the study region and in the forested areas of the western portion; the lowest risk was predicted in the treeless portions of the northwest portion of the study area. Mallard collision risk was predicted to be highest in the eastern central portion of the prairie potholes and in Iowa which has a high density of pothole wetlands; lower risk was predicted in the more arid portions of the study area. Predicted collision risk for American Avocet was similar to Mallard and was highest in the prairie pothole region and lower elsewhere. Golden Eagle collision risk was predicted to be highest in the mountainous areas of the western portion of the study area and lowest in the eastern portion of the prairie potholes. Whooping Crane predicted collision risk was highest within the migration corridor that the birds follow through in the central portion of the study region; predicted collision risk was much lower elsewhere. Red bat collision risk was highly driven by large tracts of forest and river corridors which made up most of the areas of higher collision risk. Silver-haired bat and hoary bat predicted collision risk were nearly identical and driven largely by forest and river corridors as well as locations with warmer temperatures, and lower average wind speeds. Horned Lark collisions were mostly influenced by abundance and predictions showed a moderate correlation between observed and predicted mortality (r = 0.55). Red bat, silver-haired bat, and hoary bat predictions were much higher and shown a strong correlations with observed mortality with correlations of 0.85, 0.90, and 0.91 respectively. Red bat collisions were influenced primarily by habitat, while hoary bat and silver-haired bat collisions were influenced mainly by exposure variables. Stronger correlations between observed and predicted collision for bats than for Horned Larks can likely be attributed to stronger habitat associations and greater influences of weather on behavior for bats. Although the collision predictions cannot be compared among species, our model outputs provide a convenient and easy landscape-level tool to quickly screen for siting issues at a high level. The model resolution is suitable for state or multi-county siting but users are cautioned against using these models for micrositing. The U.S. Fish and Wildlife Service recently released voluntary land-based wind energy guidelines for assessing impacts of a wind facility to wildlife using a tiered approach. The tiered approach uses an iterative approach for assessing impacts to wildlife in levels of increasing detail from landscape-level screening to site-specific field studies. Our models presented in this paper would be applicable to be used as tools to conduct screening at the tier 1 level and would not be appropriate to complete smaller scale tier 2 and tier 3 level studies. For smaller scale screening ancillary field studies should be conducted at the site-specific level to validate collision predictions.
