Water function zone: A method to improve the accuracy of remote sensing retrieval of water bodies

•The subdivided dataset have better inversion accuracy in the Fuyang river.•The adaptable feature extraction was selected at 8 categories of feature methods.•ERT and Catboost have great usability in water quality inversion of Fuyang River.•Human factors such as industrial emissions will reduce the inversion accuracy. In water monitoring, it is always a hot issue to exploring a method to improve the accuracy of remote sensing inversion. To this end, based on the actual investigation of the surrounding environment and water quality characteristics of the Fuyang river, this study has established five distinct water functional zones: reservoir (RS), village river (VR), industrial river (IR), artificial lake (AL), and urban river (UR), which are considered as subdivided datasets. Meanwhile, considering that lakes and reservoirs typically contain relatively stationary or slow-moving water bodies, while river channels are characterized by moving water bodies, three multi-type datasets have been constructed for comparison. These are based on the morphological and flow characteristics of different regions within the Fuyang river and include river channel (R), lake (L), and whole basin (W). Based on multi-spectral images of unmanned aerial vehicle (UAV) and measured water quality data, ten types of inversion models were to invert six kinds of water quality parameters, and compare and analyze the performance of the optimal inversion model of the corresponding data sets. The results show that the multivariate regression model is superior to the univariate regression model, and the mean coefficient of determination (R2) of the subdivided data set is 0.936, and the root mean square error (RMSE) and mean absolute error (MAE) appear decrease in different degrees compared with the W with 3.573 and 2.662, respectively. The mean ratio performance to interquartile (RPIQ) of the corresponding model in UR and VR are 3.963 and 2.748, respectively. Extremely Randomized Trees (ERT) model is more suitable for the inversion of multi-type data sets lacking obvious water quality characteristics and with complex components, while Categorical Boosting (CatBoost) model is more suitable for the inversion of subdivided data sets with obvious water quality characteristics. The current method has practical guiding significance for improving the application level of water monitoring technology in ecological environment protection and urban water resources protection.