The U.S. Geological Survey’s (USGS) SPAtially Referenced Regression On Watershed attributes (SPARROW) model was developed to aid in the interpretation of monitoring data and simulate water-quality conditions in streams across the Midcontinental Region of Canada and the Unites States. SPARROW is a hybrid empirical⁄process-based mass balance model that can be used to estimate the major sources and environmental factors that affect the long-term supply, transport, and fate of contaminants in streams. The spatially explicit model structure is defined by a river reach network coupled with contributing catchments. The model is calibrated by statistically relating watershed sources and transport-related properties to monitoring-based water-quality load estimates. This USGS data release, prepared in cooperation with the International Joint Commission and National Research Council Canada, includes output files representing 2002 SPARROW simulations of total nitrogen and total phosphorus in streams of the Midcontinent. Model calibration and results are described in Robertson and others (2019, https://doi.org/10.1111/1752-1688.12792). Geospatial data used for developing the Midcontinental SPARROW nutrient models are described in Vouk and others (2018, https://doi.org/10.4224/23004810). Model calibration targets used in the SPARROW models are described in Saad and others (2018, https://doi.org/10.3133/sir20185051).