The key problem in the reasonable management of water is identifying the effective radius of surface water pollution. Remote sensing and three-dimensional fluorescence technologies were used to evaluate the effects of land use/cover on surface water pollution. The PARAFAC model and self-organizing map (SOM) neural network model were selected for this study. The results showed that four fluorescence components, microbial humic-like (C1), terrestrial humic-like organic (C2, C4), and protein-like organic (C3) substances, were successfully extracted by the PARAFAC factor analysis. Thirty water sampling points were selected to build 5 buffer zones. We found that the most significant relationships between land use and fluorescence components were within a 200 m buffer, and the maximum contributions to pollution were mainly from urban and salinized land sources. The clustering of land-use types and three-dimensional fluorescence peaks by the SOM neural network method demonstrated that the three-dimensional fluorescence peaks and land-use types could be grouped into 4 clusters. Principal factor analysis was selected to extract the two main fluorescence peaks from the four clustered fluorescence peaks; this study found that the relationships between salinized land, cropland and the fluorescence peaks of C1, W2, and W7 were significant by the stepwise multiple regression method.