River Extraction under Bankfull Discharge Conditions Based on Sentinel-2 Imagery and DEM Data

Abstract

River discharge and width, as essential hydraulic variables and hydrological data, play a vital role in influencing the water cycle, driving the resulting river topography and supporting ecological functioning. Insights into bankfull river discharge and bankfull width at fine spatial resolutions are essential. In this study, 10-m Sentinel-2 multispectral instrument (MSI) imagery and digital elevation model (DEM) data, as well as in situ discharge and sediment data, are fused to extract bankfull river widths on the upper Yellow River. Using in situ cross-section morphology data and flood frequency estimations to calculate the bankfull discharge of 22 hydrological stations, the one-to-one correspondence relationship between the bankfull discharge data and the image cover data was determined. The machine learning (ML) method is used to extract water bodies from the Sentinel-2 images in the Google Earth Engine (GEE). The mean overall accuracy was above 0.87, and the mean kappa value was above 0.75. The research results show that (1) for rivers with high suspended sediment concentrations, the water quality index (SRMIR-Red) constitutes a higher contribution; the infrared band performs better in areas with greater amounts of vegetation coverage; and for rivers in general, the water indices perform best. (2) The effective river width of the extracted connected rivers is 30 m, which is 3 times the image resolution. The R2, root mean square error (RMSE), and mean bias error (MBE) of the estimated river width values are 0.991, 7.455 m, and −0.232 m, respectively. (3) The average river widths of the single-thread sections show linear increases along the main stream, and the R2 value is 0.801. The river width has a power function relationship with bankfull discharge and the contributing area, i.e., the downstream hydraulic geometry, with R2 values of 0.782 and 0.630, respectively. More importantly, the extracted river widths provide basic data to analyze the spatial distribution of bankfull widths along river networks and other applications in hydrology, fluvial geomorphology, and stream ecology.

Automatic Extraction of Mountain River Surface and Width Based on Multisource High-Resolution Satellite Images

“…However, the annual precipitation distribution in the basin is extremely uneven, and the precipitation in the flood season (June to September) accounts for 76% of the annual precipitation and 80% of the runoff [40]. The Huangfuchuan River basin has many tributaries and narrow river channels with river widths less than 90 m. We divided rivers narrower than 90 m in the Huangfuchuan River Basin into three categories based on existing studies [5,18] and the resolution of mainstream satellite imagery: narrower than 10 m tiny rivers, 10-30 m thin rivers, and 30-90 m small rivers. The others wider than 90 m are wide rivers.…”

“…Currently, the widely used data sources are medium-and high-resolution satellite images such as the US Landsat series, the European Space Agency Sentinel series, and the French SPOT series. There are still a few studies using high-resolution satellite images [4][5][6][7][8][9].…”

“…Automated methods based on machine learning have also been gradually applied to waterbody extraction. For example, the random forest algorithm (RF) can be robust in distinguishing large areas of simple objects, with high classification efficiency and accurate classification results [5,24]. Artificial neural networks (ANNs) show the advantages of self-learning and high-speed search for optimal solutions and have better classification results for areas with high ground object mixtures and rich texture features [25,26].…”

Comparative Analysis of Machine Learning Algorithms in Automatic Identification and Extraction of Water Boundaries

“…The development of remote sensing technology makes it possible to extract water information quickly and accurately, which is substantially different from conventional field survey methods employed in the past [7][8][9][10].…”

Sediment Transport Dynamism in the Confluence Area of Two Rivers Transporting Mainly Suspended Sediment Based on Sentinel-2 Satellite Images

“…The different water colours of the mixing waters could be exploited during the analysis of the mixing patterns in the confluence area. The suspended sediment transport, which is considered as one of the most important parameters for studying the mixing process, could be analysed by in situ campaigns [24,25], modelling [26,27], and remote sensing images [28][29][30][31][32][33][34][35][36][37][38][39]. As there is a great difference in suspended sediment transport during flood periods, a combination of linear and power models was developed to accommodate all the spectra of suspended sediment from dilute to hyper-concentrated levels [26].…”