Assessment of Sentinel-2 and Landsat-8 OLI for Small-Scale Inland Water Quality Modeling and Monitoring Based on Handheld Hyperspectral Ground Truthing

Abstract

This study investigates the best available methods for remote monitoring inland small-scale waterbodies, using remote sensing data from both Landsat-8 and Sentinel-2 satellites, utilizing a handheld hyperspectral device for ground truthing. Monitoring was conducted to evaluate water quality indicators: chlorophyll-a (Chl-a), colored dissolved organic matter (CDOM), and turbidity. Ground truthing was performed to select the most suitable atmospheric correction technique (ACT). Several ACT have been tested: dark spectrum fitting (DSF), dark object subtraction (DOS), atmospheric and topographic correction (ATCOR), and exponential extrapolation (EXP). Classical sampling was conducted first; then, the resulting concentrations were compared to those obtained using remote sensing analysis by the above-mentioned ACT. This research revealed that DOS and DSF achieved the best performance (an advantage ranging between 29% and 47%). Further, we demonstrated the appropriateness of the use of Sentinel-2 red and vegetation red edge reciprocal bands $\left(1/\left(\text{B}4\times \text{B}6\right)\right)$ for estimating Chl-a ( $R^2=0.82$ , $\text{RMSE}=14.52\text{mg}/{\text{m}}^3$ ). As for Landsat-8, red to near-infrared ratio ( $\text{B}4/\text{B}5$ ) produced the best performing model ( $R^2=0.71$ , $\text{RMSE}=39.88\text{mg}/{\text{m}}^3$ ), but it did not perform as well as Sentinel-2. Regarding turbidity, the best model ( $R^2=0.85$ , $\text{RMSE}=0.87$ NTU) obtained by Sentinel-2 utilized a single band (B4), while the best model (with $R^2=0.64$ , $\text{RMSE}=0.90$ NTU) using Landsat-8 was performed by applying two bands ( $\text{B}1/\text{B}3$ ). Mapping the water quality parameters using the best performance biooptical model showed the significant effect of the adjacent land on the boundary pixels compared to pixels of deeper water.