Retrieval of Chlorophyll-a Concentrations in the Coastal Waters of the Beibu Gulf in Guangxi Using a Gradient-Boosting Decision Tree Model

Abstract

Remote sensing for the monitoring of chlorophyll-a (Chl-a) is essential to compensate for the shortcomings of traditional water quality monitoring, strengthen red tide disaster monitoring and early warnings, and reduce marine environmental risks. In this study, a machine learning approach called the Gradient-Boosting Decision Tree (GBDT) was employed to develop an algorithm for estimating the Chl-a concentrations of the coastal waters of the Beibu Gulf in Guangxi, using Landsat 8 OLI image data as the image source in combination with field measurements of Chl-a concentrations. The GBDT model with B4, B3 + B4, B3, B1 − B4, B2 + B4, B1 + B4, and B2 − B4 as input features exhibited higher accuracy (MAE = 0.998 μg/L, MAPE = 19.413%, and RMSE = 1.626 μg/L) compared with different physics models, providing a new method for remote sensing inversion of water quality parameters. The GBDT model was used to study the spatial distribution and temporal variation of Chl-a concentrations in the coastal sea surface of the Beibu Gulf of Guangxi from 2013 to 2020. The results showed a spatial distribution with high concentrations in nearshore waters and low concentrations in offshore waters. The Chl-a concentration exhibited seasonal changes (concentration in summer > autumn > spring ≈ winter).

Study the Impact of the Anthropogenic Activities on the Marine Environment of Fujairah Offshore Waters of UAE Based on Baseline Surveys and Buoy Data

“…But none of these readings suggested the formation of phytoplankton blooms. The nearshore chlorophyll-a concentration was higher from August to January due to the desalination plants byproducts causing nutrient enrichment mainly in the nitrogen and phosphorus contents in the presence of high intensity sunlight [8], which exaggerate the eutrophication process [9], leading to an increase in the phytoplankton biomass (chlorophylla). Similarly, the offshore site exhibits a sudden increase in the chlorophyll-a concentration for the month of January 2021.…”

A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years

“…In a study by Yong Sung Kwon et al [96], machine learning techniques utilizing bands from 1 to 4 obtained from Landsat-8 Operational Land Imager satellite images demonstrated satisfactory performance, highlighting the effectiveness of combining remote sensing and machine learning for estimating chlorophyll-a concentration. Huanmei Yao et al [97] utilized the Gradient Boosting Decision Tree model to estimate Chl-a concentrations, combining Landsat 8 OLI satellite data with a nominal 30 m spatial resolution from the United States Geological Survey with field measurements. The Gradient Boosting Decision Tree model exhibited a higher accuracy (MAE = 0.998 µg/L, MAPE = 19.413%, and RMSE = 1.626 µg/L) compared to different physics models.…”

Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression

“…For the first stage, inspired by Zebari et al [57], the significant assessment and stepwise regression were used to select explanatory factors and deal with multicollinearity since they preserved the physical meaning of the factors for subsequent analysis. For the second stage, a grid search method with 10-fold cross-validation (i.e., dividing all pixels into ten groups; nine groups at a time for training and the rest for validation) [58], was applied to determine the number of decision trees and the loss function. Ultimately, 100 and the minimum absolute deviation were determined as the final number of decision trees and the loss function, respectively.…”