| Proper management of stormwater runoff is required to protect receiving water quality since most wastewater sources have been treated to secondary standards or beyond. Urban stormwater runoff has become the primary source of many pollutants, which is caused by runoff from highly developed, impervious land use, and managing stormwater has become the primary objective of new regulatory efforts. However, monitoring and modeling is inherently difficult, and empirical methods to estimate stormwater pollution have been developed using land use data. Conventional land use data collecting methods from ground surveys are expensive and time consuming, and may not be available.;This study demonstrated alternative approaches to use satellite image classification using Bayesian networks. The Bayesian network structure shows the most influential input variables for classification. The network also reveals the relationships among variables, which is useful when dealing with missing information. First, urban land use in the given area was classified and converted to corresponding stormwater pollutant loading maps based on the existing relationships between land use and the pollutant loads. Secondly, the pollutant loads for each water quality parameter were estimated directly from satellite imagery. The resulting thematic maps spatially estimated stormwater pollutant loadings, which identified areas generating high stormwater pollutant emissions. The results show that stormwater pollutants are highly correlated to impervious areas because of their high runoff coefficients, even when they had low event mean concentrations. These results are useful in developing best management strategies for stormwater pollution and in establishing total maximum daily loads in the watershed. |
