Traditional direct water quality methodologies limit the ability to spatially and temporally predict algal blooms in lotic systems due to the size and characteristics of large river systems. Algal blooms potentially can be predicted by knowing the spatial and temporal patterns of change in cyanobacteria concentrations at large scales. Remote sensing studies investigating freshwater algal blooms, some known to secrete harmful toxins, are primarily conducted on lentic systems while large lotic systems are greatly ignored. In this study I developed a chlorophyll concentration estimation model for the Ohio River using a satellite remote sensing approach. Ground-truth water quality measures, including temperature, dissolved oxygen, turbidity, as well as chlorophyll concentrations, were obtained through hand-samples on days the satellite flew over the study area. Concentrations of chlorophyll were correlated with spectral signatures from Landsat-8 OLI satellite imagery. Then a predictive model was developed using a two bands of Landsat 8 to predict chlorophyll a and the generated model has an R2 = 0.879 (Adj. R2 = 0.819) and a p-value = 0.015. Two other models were generated for estimating both chlorophyll a & b and total chlorophyll; however, the models were not as robust, R2 = 0.801 (Adj. R2 = 0.603), p-value = 0.141 and R2 = 0.764 (Adj. R2 = 0.528), p -value = 0.18, respectively.