Remotely observed variations of reservoir low concentration chromophoric dissolved organic matter and its response to upstream hydrological and meteorological conditions using Sentinel-2 imagery and Gradient Boosting Regression Tree

Abstract

Freshwater lakes are facing increasingly serious water quality problems. Remote sensing techniques are effective tools for monitoring spatiotemporal information of chromophoric dissolved organic matter (CDOM), a biochemical indicator for water quality. In this study, the Gradient Boosting Regressing Tree (GBRT) model and Sentinel-2A/B image were combined to estimate low CDOM concentrations (0.003 m−1 < aCDOM(440) <1.787 m−1) in Xin'anjiang Reservoir, an important drinking water resource in Zhejiang Province, China, providing the CDOM distributions and dynamics with high spatial (10 m) and temporal (5 days) resolutions. The possible environmental factors that may affect CDOM spatiotemporal patterns and dynamics were analyzed using Sentinel-2 image-observed data in 2018. Results showed that CDOM in the reservoir exhibited a clear increased gradient from its transition and lacustrine zones to the riverine zones, indicating that the rivers carried a substantial load of organic matter to the lake. The precipitation may increase CDOM concentrations but it has a delay effect, while it may also shortly decrease CDOM concentrations due to the rainwater dilution. We also found that the correlations between CDOM and water temperature, air pressure, and wind speed were very low, indicating that these factors may not have significant impacts on CDOM variations in the reservoir. This study demonstrated that the GBRT model and Sentinel-2 imagery have the potential to accurately monitor CDOM spatiotemporal variations in reservoirs with low CDOM concentrations, which advancing our understanding on the relations between the dissolved organic matter and its coupling environmental factors in river-reservoir systems.

Improving the Performance of Industrial Dyeing Recipe Models by Taking Log-Transform in the Data Pre-Processing

“…In our earlier work, we have reported the building of such a recommender based on a modular architecture structured system, in which individual gradient boosting regression trees (GBRT) are trained from dyeing manufacturing records for single types of fabric versus dye combinations [14]. GBRT can predict dye concentrations with prediction errors as good as ~7-10% [14], and have also been successfully applied into other applications with great model performance [15][16][17][18].…”