Understanding the spatiotemporal patterns of water quality is crucial because it provides essential information for water pollution control. The spatiotemporal variations in water quality for the Nanxi River in the Taihu watershed of China were evaluated by a water quality index (WQI) and multivariate statistical techniques; additionally, the potential sources of contamination were identified. The data set included 22 water quality parameters collected during the monitoring period from 2015 to 2020 for 14 monitoring stations. WQI assessment revealed that approximately 85% of monitoring stations were classified as “medium-low” water quality, and most showed continuous improvement in water quality. Cluster analysis divided the 14 monitoring stations into three clusters (low contamination, medium contamination and high contamination). Discriminant analysis identified pH, petroleum, volatile phenol, chemical oxygen demand, total phosphorus, F, S, fecal coliform, SO4, Cl, NO3-N, total hardness, NO2-N and NH3 as important parameters affecting spatial variations. Factor analysis identified four potential contamination source types: nutrient, organics, feces and oil. This study demonstrated the usefulness of multivariate statistical techniques in assessing large data sets, identifying contamination source types, and better understanding spatiotemporal variations in water quality to restore and protect water resources.

Multispectral remote sensing technology using unmanned aerial vehicles (UAVs) is able to provide fast, large-scale, and dynamic monitoring and management of water environments. We here select multiple water-body indices based on their spectral reflection characteristics, analyze correlations between the reflectance values of water body indices and the water quality parameters of synchronous measured sampling points, and obtain an optimal water body index. A representative selection, such as statistical analysis methods, neural networks, random forest, XGBoost and other schemes are then used to build water-quality parameter inversion models. Results show that the XGBoost model has the highest accuracy for dissolved oxygen parameters (R2 = 0.812, RMSE = 0.414 mg L−1, MRE = 0.057) and the random forest model has the highest accuracy for turbidity parameters (R2 = 0.753, RMSE = 0.732 NTU, MRE = 0.065). Finally, spatial distribution maps of dissolved oxygen and turbidity of water bodies in the experimental domain are drawn to visualize water-quality parameters. This study provides a detailed comparative analysis of multiple inversion methods, including parameter quantity, processing speed, algorithm rigor, solution accuracy, robustness, and generalization, and further evaluates the technical characteristics and applicability of several inversion methods. Our results can provide guidance for improved small- and medium-sized surface-water quality monitoring, and provide an intuitive data analysis basis for urban water environment management.