Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning

Fluorescent dissolved organic matter (fDOM), a fluorescent component of dissolved organic matter (DOM), plays a crucial role in tracing pollution pathways in marine environments. While remote sensing has been used to monitor fDOM changes, the impact of multi-source interference has often been overlo...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruiwu Zhang, Ruru Deng, Jun Ying, Jiayi Li, Yu Guo, Junying Yang, Cong Lei
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Science of Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666017225000665
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730286831534080
author Ruiwu Zhang
Ruru Deng
Jun Ying
Jiayi Li
Yu Guo
Junying Yang
Cong Lei
author_facet Ruiwu Zhang
Ruru Deng
Jun Ying
Jiayi Li
Yu Guo
Junying Yang
Cong Lei
author_sort Ruiwu Zhang
collection DOAJ
description Fluorescent dissolved organic matter (fDOM), a fluorescent component of dissolved organic matter (DOM), plays a crucial role in tracing pollution pathways in marine environments. While remote sensing has been used to monitor fDOM changes, the impact of multi-source interference has often been overlooked, limiting the accuracy of inversion results. In this study, based on fDOM measurements from Admiralty Bay and from the perspective of optical physical mechanisms, we eliminated atmospheric effects, surface reflection, solar-induced fluorescence (SIF), Raman scattering, and particle absorption from remote sensing reflectance (Rrs(λ)). This preprocessing improved the stability of Rrs(λ), enhancing the reliability of subsequent fDOM inversion. Based on the corrected reflectance, three sensitive wavelengths highly correlated with fDOM were selected. Five machine learning models—Random Forest (RF), XGBoost, Classification and Regression Trees (CART), Gradient Boosting Regression (GBR), and AdaBoost—were then applied for fDOM inversion, with XGBoost achieving the best performance. The inversion results revealed that fDOM concentrations in Admiralty Bay were highest in the western and coastal areas, gradually increasing toward the center, exhibiting a locally clustered distribution. This study demonstrates the effectiveness of combining physical and data-driven methods for fDOM inversion, providing a foundation for long-term monitoring of dissolved organic matter in polar marine environments.
format Article
id doaj-art-dc40cc200b7641eb8fdf7540fe736a8b
institution DOAJ
issn 2666-0172
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Science of Remote Sensing
spelling doaj-art-dc40cc200b7641eb8fdf7540fe736a8b2025-08-20T03:08:55ZengElsevierScience of Remote Sensing2666-01722025-12-011210026010.1016/j.srs.2025.100260Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learningRuiwu Zhang0Ruru Deng1Jun Ying2Jiayi Li3Yu Guo4Junying Yang5Cong Lei6School of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, 519082, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, 519082, China; Guangdong Engineering Research Center of Water Environment Remote Sensing Monitoring, Guangzhou, 510275, China; Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation, School of Geography and Planning, Guangzhou, 510275, China; Corresponding author. School of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China.Institute of Ecological Civilization and Institute of Carbon Neutrality, Zhejiang A&F University, Hangzhou, 311300, China; College of Landscape Architecture and Architecture, Zhejiang A&F University, Hangzhou, 311300, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, 519082, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, 519082, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, 519082, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou, 510006, China; Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, 519082, ChinaFluorescent dissolved organic matter (fDOM), a fluorescent component of dissolved organic matter (DOM), plays a crucial role in tracing pollution pathways in marine environments. While remote sensing has been used to monitor fDOM changes, the impact of multi-source interference has often been overlooked, limiting the accuracy of inversion results. In this study, based on fDOM measurements from Admiralty Bay and from the perspective of optical physical mechanisms, we eliminated atmospheric effects, surface reflection, solar-induced fluorescence (SIF), Raman scattering, and particle absorption from remote sensing reflectance (Rrs(λ)). This preprocessing improved the stability of Rrs(λ), enhancing the reliability of subsequent fDOM inversion. Based on the corrected reflectance, three sensitive wavelengths highly correlated with fDOM were selected. Five machine learning models—Random Forest (RF), XGBoost, Classification and Regression Trees (CART), Gradient Boosting Regression (GBR), and AdaBoost—were then applied for fDOM inversion, with XGBoost achieving the best performance. The inversion results revealed that fDOM concentrations in Admiralty Bay were highest in the western and coastal areas, gradually increasing toward the center, exhibiting a locally clustered distribution. This study demonstrates the effectiveness of combining physical and data-driven methods for fDOM inversion, providing a foundation for long-term monitoring of dissolved organic matter in polar marine environments.http://www.sciencedirect.com/science/article/pii/S2666017225000665Fluorescent dissolved organic matterOptical signalRemote sensing inversionWater reflectivityMachine learning model
spellingShingle Ruiwu Zhang
Ruru Deng
Jun Ying
Jiayi Li
Yu Guo
Junying Yang
Cong Lei
Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning
Science of Remote Sensing
Fluorescent dissolved organic matter
Optical signal
Remote sensing inversion
Water reflectivity
Machine learning model
title Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning
title_full Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning
title_fullStr Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning
title_full_unstemmed Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning
title_short Remote sensing monitoring of fluorescent dissolved organic matter in Admiralty Bay: fusion of multi-source signal removal and machine learning
title_sort remote sensing monitoring of fluorescent dissolved organic matter in admiralty bay fusion of multi source signal removal and machine learning
topic Fluorescent dissolved organic matter
Optical signal
Remote sensing inversion
Water reflectivity
Machine learning model
url http://www.sciencedirect.com/science/article/pii/S2666017225000665
work_keys_str_mv AT ruiwuzhang remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning
AT rurudeng remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning
AT junying remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning
AT jiayili remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning
AT yuguo remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning
AT junyingyang remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning
AT conglei remotesensingmonitoringoffluorescentdissolvedorganicmatterinadmiraltybayfusionofmultisourcesignalremovalandmachinelearning