Multi-stressor Predictive Models of Invertebrate Condition in the Corn Belt, U.S.A.

Understanding the complex relations between multiple environmental stressors and ecological conditions in streams can help guide resource management decisions. During 14 weeks in Spring/Summer 2013, the U.S. Geological Survey and the U.S. Environmental Protection Agency sampled 98 wadeable streams across the Midwest Corn Belt region of the United States for water and sediment quality, physical and habitat characteristics, and ecological communities. Using these data, we developed independent predictive disturbance models for four macroinvertebrate metrics. The models were developed using boosted regression trees (BRT) for three stressor categories, land use/land cover (GIS), all instream stressors combined (nutrients, habitat and contaminants), and for GIS plus instream stressors. The GIS plus instream stressor models had the best overall performance with all of the models having R2 above 0.80. Overall, the models were generally consistent in the explanatory variables selected within each stressor group across the four invertebrate metrics modeled. Variables related to riparian condition, substrate size or embeddedness, velocity and channel shape, nutrients (primarily ammonia) and contaminants (pyrethroid degradates) were important variables describing the invertebrate metrics. Models based on all measured instream stressors performed comparably to models based on GIS landscape variables, suggesting that the instream stressor characterization reasonably represents the dominant factors affecting invertebrate communities and that GIS variables are acting as surrogates for instream stressors that directly affect instream biota.