Satellite Remote Sensing-Implemented Nontargeted Screening of Emerging Contaminant Fingerprints in a River-to-Ocean Continuum through Interpretable Machine Learning: The Pivotal Intermediary Role of Dissolved Organic Matter

被引：0

作者：

Zhang, Chao ^{[1
,2
,3
,4
,5
,6
]}

Zhu, Junyu ^{[1
,2
,3
,4
,5
]}

Mai, Wenjie ^{[1
,2
,3
,4
,5
]}

Chen, Zhenguo ^{[1
,2
,3
,4
,5
]}

Xie, Yue ^{[1
,2
,3
,4
,5
]}

Fu, Shuna ^{[7
]}

Xia, Di ^{[8
]}

Cai, Chun ^{[1
,2
,3
,4
,5
]}

Zheng, Wanbing ^{[1
,2
,3
,4
,5
]}

Liu, Jinxin ^{[1
,2
,3
,4
,5
]}

Yang, Lianmiao ^{[1
,2
,3
,4
,5
]}

Zhang, Zhe ^{[9
]}

Huang, Mingzhi ^{[1
,2
,3
,4
,5
]}

Wu, Fengchang ^{[10
]}

机构：

[1] South China Normal Univ, Guangdong Prov Engn Res Ctr Intelligent Low Carbon, Sch Environm, Guangzhou 510006, Peoples R China

[2] South China Normal Univ, Sch Environm, Guangdong Prov Key Lab Chem Pollut & Environm Safe, Guangzhou 510006, Peoples R China

[3] South China Normal Univ, Sch Environm, Key Lab Theoret Chem Environm, MOE, Guangzhou 510006, Peoples R China

[4] South China Normal Univ, SCNU NANAN Greenand Low carbon Innovat Ctr, Quanzhou 362300, Peoples R China

[5] South China Normal Univ, Nanan SCNU Inst Green & Low carbon Res, Quanzhou 362300, Peoples R China

[6] Karlsruhe Inst Technol, EnglerBunte Inst, Water Chem & Water Technol, D-76131 Karlsruhe, Germany

[7] Agilent Technol China Co Ltd, Guangzhou 510005, Peoples R China

[8] Minist Ecol & Environm, South China Inst Environm Sci, Guangzhou 510655, Peoples R China

[9] Univ Cincinnati, Dept Chem & Environm Engn ChEE, Cincinnati, OH 45221 USA

[10] Chinese Res Inst Environm Sci, State Key Lab Environm Criteria & Risk Assessment, Beijing 100012, Peoples R China

来源：

ENVIRONMENTAL SCIENCE & TECHNOLOGY | 2025年

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Emerging Contaminants; Nontargeted Screening; Interpretable Machine Learning; Satellite Remote Sensing; river-to-ocean continua; Dissolved Organic Matter; WATER;

D O I：

10.1021/acs.est.4c14425

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Emerging contaminants (ECs) can exert irreversible health impacts on humans, even at trace concentrations. Currently, nontargeted screening of ECs has been developed for their assessment, which requires sophisticated instrumentation. Although satellite remote sensing is a cost-effective technology for water quality assessment, accurately measuring ECs in a river-to-ocean continuum remains a significant challenge due to their trace levels. To address this challenge, we innovate a strategy utilizing satellite remote sensing to achieve high-resolution nontargeted EC screening. By employing DOM as an intermediary variable, bridging the gap between satellite remote sensing and ECs in river-to-ocean continua. DOM, including the total sum of ECs, reflects their distribution and spectral sensitivity, enabling satellite sensing to capture their unique fingerprints. In this study, this strategy has enhanced the accuracy of nontargeted EC screening from 32.2 to 95.7% using machine learning. Interpretable machine learning causal inference and SHAP models reveal that shortwave infrared (SWIR) S2-B11 is crucial for EC screening while emphasizing the importance of avoiding multicollinearity with similar SWIR band S2-B12. Additionally, the band reflectance is influenced by the proportion of polarity-related heterogeneity in the ECs. Furthermore, we developed a real-time remote sensing surveillance system featuring interactive maps for nontargeted screening of ECs and GPT-based contamination interpretation.

引用

页数：13