Remote Sensing of Turbidity for Lakes in Northeast China Using Sentinel-2 Images With Machine Learning Algorithms

Abstract

Monitoring water quality of inland lakes and reservoirs is a great concern for the public and government in China. Water turbidity is a reliable and direct indicator that can reflect the water quality. Remote sensing has become an efficient technology for monitoring large-scale water turbidity. This study aims to search an optimal regression model to accurately predict water turbidity using remote sensing data. To achieve this goal, 187 water samples were collected from field campaigns across Northeast China in 2018, of which the samples were gathered within ±6 days of Sentinel-2 overpasses. The spectral reflectance data was used as independent variables for modeling. The simple regression (SR), partial least squares regression (PLSR), support vector regression (SVR), extreme learning machine (ELM), back-propagation neural network (BP), classification and regression tree (CART), gradient boosting decision tree (GBDT), random forest (RF), and K-nearest neighbor (KNN) were used to compare. From model validation, we identified GBDT as the best regression model (R 2 =0.88, RMSE=9.90 NTU, MAE=6.71 NTU). We applied GBDT to retrieve the water turbidity and obtained a satisfactory result. Feature selection technique from tree-based ensemble method was also tested. We selected B2, B3, B4, and B5 as the important variables because of their high ability to explain the variation of turbidity. These results demonstrated the significance of using a promising method to retrieve water turbidity using Sentinel-2 imagery at the regional scale. It is beneficial to monitor the spatial-temporal distribution of water turbidity; support water quality management and inland water environment protection.

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

“…Analysis of the Landsat-8 images resulted in a more successful fit using a two-band algorithm where an exponential model best fits the data, reaching a coefficient of determination of 0.64 for the calibration and an RMSE of 0.9 for the validation. In previous research, two-band models have been widely used to detect the high turbidity levels as typified by Ma et al [66]. For instance, the index of 550 nm and 850 nm was used in France's Gironde Estuary (TSS: 13-985 mg/L) [67], the index of 551 nm and 678 nm was used in China's Yellow River (TSS: 2-1897 mg/L) [68], and the index of 555 nm and 645 nm was used in China's Yangtze River (TSS: 1-300 mg/L) [69].…”

Mapping Invasive Aquatic Plants in Sentinel-2 Images Using Convolutional Neural Networks Trained With Spectral Indices

“…Remote sensing has been widely used for water support management in recent years. For instance, the work developed in [1] supports water quality management, monitoring the spatial-temporal distribution of water turbidity. In [2], coastal ecosystem health status is evaluated.…”

Lake Turbidity Mapping Using an OWTs-bp Based Framework and Sentinel-2 Imagery

“…Satellite data have been used in mapping water turbidity since Moore (1980) [10] assessed the feasibility of satellite data. The remote sensing of turbidity has been employed as an early alert for changes in lake ecosystems [11,12]. The advantage of remote sensing is the ability to survey large spatial extent and hard to access areas [13].…”