Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb;30(7):18617-18630.
doi: 10.1007/s11356-022-23431-9. Epub 2022 Oct 10.

Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms

Shang Tian  1 , Hongwei Guo  1 , Wang Xu  2 , Xiaotong Zhu  1 , Bo Wang  1 , Qinghuai Zeng  2 , Youquan Mai  2 , Jinhui Jeanne Huang  3
Affiliations

Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms

Shang Tian et al. Environ Sci Pollut Res Int. 2023 Feb.

Abstract

Remote sensing has long been an effective method for water quality monitoring because of its advantages such as high coverage and low consumption. For non-optically active parameters, traditional empirical and analytical methods cannot achieve quantitative retrieval. Machine learning has been gradually used for water quality retrieval due to its ability to capture the potential relationship between water quality parameters and satellite images. This study is based on Sentinel-2 images and compared the ability of four machine learning algorithms (eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Random Forest (RF), and Artificial Neural Network (ANN)) to retrieve chlorophyll-a (Chl-a), dissolved oxygen (DO), and ammonia-nitrogen (NH3-N) for inland reservoirs. The results indicated that XGBoost outperformed the other three algorithms. We used XGBoost to reconstruct the spatial-temporal patterns of Chl-a, DO, and NH3-N for the period of 2018-2020 and further analyzed the interannual, seasonal, and spatial variation characteristics. This study provides an efficient and practical way for optically and non-optically active parameters monitoring and management at the regional scale.

Keywords: Inland waters; Machine learning; Non-optically active parameters; Remote sensing; Sentinel-2; Water quality.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

References

    1. Achmad AR, Syifa M, Park SJ et al (2019) Geomorphological transition research for affecting the coastal environment due to the volcanic eruption of Anak Krakatau by satellite imagery. J Coast Res 90:214. https://doi.org/10.2112/SI90-026.1 - DOI
    1. Alcantara E, Bernardo N, Rodrigues T et al (2017) Modeling the spatio-temporal dissolved organic carbon concentration in Barra Bonita reservoir using OLI/Landsat-8 images. Model Earth Syst Environ 3:11. https://doi.org/10.1007/s40808-017-0275-2 - DOI
    1. Barnes BB, Hu C (2016) Dependence of satellite ocean color data products on viewing angles: a comparison between SeaWiFS, MODIS, and VIIRS. Remote Sens Environ. https://doi.org/10.1016/j.rse.2015.12.048
    1. Bierman P, Lewis M, Ostendor B et al (2011) A review of methods for analysing spatial and temporal patterns in coastal water quality. Ecol Indic 11:103–114. https://doi.org/10.1016/j.ecolind.2009.11.001 - DOI
    1. Botchkarev A (2018) Performance metrics (error measures) in machine learning regression, forecasting and prognostics: properties and typology. Interdiscip J Inf Knowl Manag 14:45–79. https://doi.org/10.28945/4184

LinkOut - more resources