Nutrient loading to aquatic systems has been linked to many issues including eutrophication, harmful algal blooms, and decreases in species diversity. In the Great Lakes, algal blooms continue to plague Lake Erie and Saginaw Bay despite reductions in point source loading. Here, methods for predicting nutrient sources using GIS are described to examine the link between watershed nutrient sources, landscape processes, and in-stream loads in the Lower Peninsula of Michigan. These models predict all significant nutrient sources to the landscape at 30 m resolution over a 144,000 km2 region, avoiding the tradeoff between scale and source detail common to many existing watershed nutrient models. The model results presented here indicate that there is a high degree of variability in nutrient landscape loading rates, even within the same land use class. Within all land use types, except unmanaged lands, loading rates for most major sources varied by at least an order of magnitude. This work provides valuable information that can be used by environmental managers regarding how and where to target efforts to reduce nutrient loads in surface water particularly in the Great Lakes region where management efforts have been ongoing since the 1960s.