Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression
Downscaling Chlorophyll-a (Chl-a) concentration derived from satellite image is crucial for refined applications such as water quality monitoring. However, the precision of downscaling is usually constrained by various environmental factors. In this paper, we develop a downscaling method for Chl-a c...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10207714/ |
| _version_ | 1827822368474529792 |
|---|---|
| author | Simin Zhang Nanfeng Liu Ming Luo Tao Jiang Ting On Chan Cynthia Sin Ting Yau Yeran Sun |
| author_facet | Simin Zhang Nanfeng Liu Ming Luo Tao Jiang Ting On Chan Cynthia Sin Ting Yau Yeran Sun |
| author_sort | Simin Zhang |
| collection | DOAJ |
| description | Downscaling Chlorophyll-a (Chl-a) concentration derived from satellite image is crucial for refined applications such as water quality monitoring. However, the precision of downscaling is usually constrained by various environmental factors. In this paper, we develop a downscaling method for Chl-a concentration to improve precision, especially for inland lakes with different surrounding environment. The method downscales the Sentinel-3 Chl-a concentration from 300 m to 30 m, based on the multivariate analysis (MVA) and the gradient boosting decision tree (GBDT) model. Firstly, we analyzed 21 Chl-a concentration related indices to identify optimal factors for Chl-a concentration variability. Secondly, a GBDT model is constructed to convey the non-linear relationship between the optimal factors and Chl-a concentration at coarse resolution. Finally, fine-resolution Chl-a concentrations were produced by employing the model to refine cofactors for 12 distinct lakes. The results indicated that the proposed MVA-GBDT method effectively inferred the variability of Chl-a concentration with a mean RMSE of 4.505 mg/m<sup>3</sup>, an improvement of 5%–39% over other methods. Furthermore, for lakes with large water quality heterogeneity, the method led to a cross validation RMSE and a difference in accuracy of 5.371 mg/m<sup>3</sup> and 0.866 mg/m<sup>3</sup>, respectively. In addition, this study examined the significance of the auxiliary factors and found that the NDCI and WST were the two most important factors for MVA-GBDT to detect Chl-a concentration distributions, particularly for NDCI in lakes with high nutrient contrasts. These findings contribute to the generation of fine-scale Chl-a concentrations in lakes and support related applications. |
| first_indexed | 2024-03-12T01:57:02Z |
| format | Article |
| id | doaj.art-3f40cda1d7f84b63b6d8353c85642d5c |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-12T01:57:02Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-3f40cda1d7f84b63b6d8353c85642d5c2023-09-07T23:00:13ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01167850786510.1109/JSTARS.2023.330179110207714Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees RegressionSimin Zhang0https://orcid.org/0009-0001-5644-460XNanfeng Liu1https://orcid.org/0000-0002-2575-0145Ming Luo2https://orcid.org/0000-0002-5474-3892Tao Jiang3Ting On Chan4https://orcid.org/0000-0002-3318-7540Cynthia Sin Ting Yau5https://orcid.org/0000-0003-4675-1398Yeran Sun6https://orcid.org/0000-0002-6847-614XSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Urbanization and Geo-Simulation, Sun Yat-sen University, Guangzhou, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Engineering Research Centre for Public Security and Disasters, Sun Yat-sen University, Guangzhou, ChinaDepartment of Ocean Science, Hong Kong University of Science and Technology, Hong Kong, SAR, ChinaDepartment of Geography, College of Science, University of Lincoln, Lincoln, U.K.Downscaling Chlorophyll-a (Chl-a) concentration derived from satellite image is crucial for refined applications such as water quality monitoring. However, the precision of downscaling is usually constrained by various environmental factors. In this paper, we develop a downscaling method for Chl-a concentration to improve precision, especially for inland lakes with different surrounding environment. The method downscales the Sentinel-3 Chl-a concentration from 300 m to 30 m, based on the multivariate analysis (MVA) and the gradient boosting decision tree (GBDT) model. Firstly, we analyzed 21 Chl-a concentration related indices to identify optimal factors for Chl-a concentration variability. Secondly, a GBDT model is constructed to convey the non-linear relationship between the optimal factors and Chl-a concentration at coarse resolution. Finally, fine-resolution Chl-a concentrations were produced by employing the model to refine cofactors for 12 distinct lakes. The results indicated that the proposed MVA-GBDT method effectively inferred the variability of Chl-a concentration with a mean RMSE of 4.505 mg/m<sup>3</sup>, an improvement of 5%–39% over other methods. Furthermore, for lakes with large water quality heterogeneity, the method led to a cross validation RMSE and a difference in accuracy of 5.371 mg/m<sup>3</sup> and 0.866 mg/m<sup>3</sup>, respectively. In addition, this study examined the significance of the auxiliary factors and found that the NDCI and WST were the two most important factors for MVA-GBDT to detect Chl-a concentration distributions, particularly for NDCI in lakes with high nutrient contrasts. These findings contribute to the generation of fine-scale Chl-a concentrations in lakes and support related applications.https://ieeexplore.ieee.org/document/10207714/Chlorophyll-a (Chl-a) concentrationdownscalinggradient boosting decision tree (GBDT)lake ecosystems |
| spellingShingle | Simin Zhang Nanfeng Liu Ming Luo Tao Jiang Ting On Chan Cynthia Sin Ting Yau Yeran Sun Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Chlorophyll-a (Chl-a) concentration downscaling gradient boosting decision tree (GBDT) lake ecosystems |
| title | Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression |
| title_full | Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression |
| title_fullStr | Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression |
| title_full_unstemmed | Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression |
| title_short | Downscaling Sentinel-3 Chlorophyll-a Concentration for Inland Lakes Based on Multivariate Analysis and Gradient Boosting Decision Trees Regression |
| title_sort | downscaling sentinel 3 chlorophyll a concentration for inland lakes based on multivariate analysis and gradient boosting decision trees regression |
| topic | Chlorophyll-a (Chl-a) concentration downscaling gradient boosting decision tree (GBDT) lake ecosystems |
| url | https://ieeexplore.ieee.org/document/10207714/ |
| work_keys_str_mv | AT siminzhang downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression AT nanfengliu downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression AT mingluo downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression AT taojiang downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression AT tingonchan downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression AT cynthiasintingyau downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression AT yeransun downscalingsentinel3chlorophyllaconcentrationforinlandlakesbasedonmultivariateanalysisandgradientboostingdecisiontreesregression |