Using a , 1000 lake data set that spans the entire continental United States, we applied empirical modeling approaches to quantify the relative strength of nutrients and water temperature as predictors of cyanobacterial biomass (CBB). Given that cyanobacteria possess numerous traits providing competitive advantage under warmer conditions, we hypothesized that water temperature, in addition to nutrients, is a significant predictor of CBB. Total nitrogen (TN), water temperature, and total phosphorus were all significant predictors of CBB, with TN explaining the most variance. Using multiple linear regression analysis, we found that TN and water temperature provided the best model and explained 25% of the variance in CBB. However, when the data set was divided according to basin type, these same variables explained a higher amount of the variation in deep natural lakes (33%, n 5 253), whereas the least amount of variation was explained by these variables in shallow reservoirs (12%, n 5 307). Competing path models on the full data set using the best variables selected by multiple linear regression show that nitrogen and temperature are indirectly linked to cyanobacteria by association with total algal biomass, which likely reflects changes in light climate and other secondary factors. Our models also indicated that temperature was linked to cyanobacteria by a direct pathway. Under a scenario of atmospheric CO2 doubling from 1990 levels (resulting in an estimated 3.3uC increase of the maximum lake surface water), we predict on average a doubling of CBB.