AUTHOR=Li Jiang , Wang Jie , Wu Yanlan , Cui Yuhuan , Yan Shijiang 

TITLE=Remote sensing monitoring of total nitrogen and total phosphorus concentrations in the water around Chaohu Lake based on geographical division

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.1014155

DOI=10.3389/fenvs.2022.1014155

ISSN=2296-665X

ABSTRACT=Remote sensing is useful for quantifying water quality parameters for managing inland water systems. However, the single water quality retrieval model usually has poor universality in large regions. To solve the issue of low retrieval accuracy of water quality parameters in large-scale rivers, the study area herein is geographically divided into rural rivers and urban rivers according to the proportion of land types in the riparian zones. Further, the machine learning regression algorithms are used to construct the retrieval models suitable for the total nitrogen (TN) and total phosphorus (TP) concentrations, based on the measured water quality data and the simultaneous Sentinel-2 MSI images. Additionally, the optical retrieval models are applied to MSI images acquired in different dates to analyze the variations of TN and TP concentrations in the rivers around Chaohu Lake. The results show that the three accuracy indices of determination coefficient (R²), mean square error (MSE), and mean absolute percentage error (MAPE) of the TN concentration retrieval models for rural rivers and urban rivers were 0.67, 0.37 mg/L, 36.81% and 0.78, 0.34 mg/L, and 8.34%, respectively, while those of the TP concentration retrieval model for rural rivers and urban rivers reached 0.46, 0.0034 mg/L, 38.60% and 0.58, 0.018 mg/L, and 37.57%, respectively. The accuracy of the TN and TP concentration retrieval model constructed using geographic division in our study is significantly better than that which does not use geographic division. According to the retrieval results from MSI images, the TN and TP concentrations in urban rivers are higher than those in rural rivers. TN and TP concentrations in urban river is stable throughout the year, peaks in December, while those of rural rivers are the highest in March and the lowest in November. The method proposed in this study can provide a new idea for improving the retrieval accuracy of water quality parameters in large-scale inland water, and the relevant conclusion can provide a theoretical basis for water pollution control and prevention strategies in agricultural basins.