Identifying and quantifying multiple pollution sources in estuaries using fluorescence spectra and gradient-based deep learning

被引:0
作者
Zhao, Zhuangming [1 ,2 ]
Xu, Min [1 ]
Yan, Yu [1 ]
Yan, Shibo [1 ]
Lin, Qiaoyun [1 ]
Xu, Juan [1 ]
Yang, Jing [1 ,2 ]
Chen, Zhonghan [1 ]
机构
[1] Minist Ecol & Environm PRC, South China Inst Environm Sci, Guangzhou 510655, Peoples R China
[2] Southern Marine Sci & Engn Guangdong Lab, Zhuhai 519085, Peoples R China
基金
中国国家自然科学基金;
关键词
Multi-source pollution; Estuary; Fluorescence spectroscopy; Deep learning; Convolutional neural network (CNN); DISSOLVED ORGANIC-MATTER; DERIVATIVE SPECTROSCOPY; SOURCE IDENTIFICATION; WASTE; EXCITATION; INDEXES; QUALITY; RIVER;
D O I
10.1016/j.marpolbul.2024.117254
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This study developed an intelligent method for identifying and quantifying water pollution sources in estuarine areas. It characterized the excitation-emission matrix (EEM) fluorescence spectra from seven end-members, including seawater, rainwater, and five pollution sources typical of these areas. A deep learning model was established to identify and quantify these pollution sources in mixed water bodies. The model was fed either the original EEM or a combined EEM and gradient input. The results indicated that the combined input enhanced classification and quantification accuracy; Although model accuracy declined with an increasing number of mixed pollution sources, the combined input still improved classification accuracy by 3.1 % to 6.8 %; When the proportion of rainwater and seawater was below 70 %, the model maintained a classification accuracy of 57.4 % with original input and 61.3 % with combined input, with root mean square error values for the pollution source proportion being 12.2 % and 11.4 %, respectively.
引用
收藏
页数:11
相关论文
共 48 条
[21]   Fluorescence analysis of dissolved organic matter in natural, waste and polluted waters - A review [J].
Hudson, Naomi ;
Baker, Andy ;
Reynolds, Darren .
RIVER RESEARCH AND APPLICATIONS, 2007, 23 (06) :631-649
[22]   Properties of fluorescent dissolved organic matter in the Gironde Estuary [J].
Huguet, A. ;
Vacher, L. ;
Relexans, S. ;
Saubusse, S. ;
Froidefond, J. M. ;
Parlanti, E. .
ORGANIC GEOCHEMISTRY, 2009, 40 (06) :706-719
[23]   The Reproducibility and Reliability of UV-vis Higher-Order Derivative Spectroscopy for Quantitative Analysis of Spectral Changes [J].
Ichimura, Kunihiro .
BULLETIN OF THE CHEMICAL SOCIETY OF JAPAN, 2017, 90 (04) :411-418
[24]   Innovative approach to reveal source contribution of dissolved organic matter in a complex river watershed using end-member mixing analysis based on spectroscopic proxies and multi-isotopes [J].
Kim, Min-Seob ;
Lim, Bo Ra ;
Jeon, Pilyong ;
Hong, Seoyeon ;
Jeon, Darae ;
Park, Si Yeong ;
Hong, Sunhwa ;
Yoo, Eun Jin ;
Kim, Hyoung Seop ;
Shin, Sunkyoung ;
Yoon, Jeong Ki .
WATER RESEARCH, 2023, 230
[25]   Natural organic matter (NOM) fouling in low pressure membrane filtration - effect of membranes and operation modes [J].
Lee, Eun Kyung ;
Chen, Vicki ;
Fane, A. G. .
DESALINATION, 2008, 218 (1-3) :257-270
[26]   Comparing optical versus chromatographic descriptors of dissolved organic matter (DOM) for tracking the non-point sources in rural watersheds [J].
Lee, Mi-Hee ;
Lee, Seung Yoon ;
Yoo, Ha-Young ;
Shin, Kyung-Hoon ;
Hur, Jin .
ECOLOGICAL INDICATORS, 2020, 117
[27]   Using fluorescence index (FI) of dissolved organic matter (DOM) to identify non-point source pollution: The difference in FI between soil extracts and wastewater reveals the principle [J].
Lin, Yuye ;
Hu, En ;
Sun, Changshun ;
Li, Ming ;
Gao, Li ;
Fan, Linhua .
SCIENCE OF THE TOTAL ENVIRONMENT, 2023, 862
[28]   Aqueous Fluorescence Fingerprint Characteristics and Discharge Source Identification of a River in Southern China [J].
Liu Chuan-yang ;
Chai Yi-di ;
Xu Xian-gen ;
Zhou Jun ;
Lu Sen-sen ;
Shen Jian ;
He Miao ;
Wu Jing .
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41 (07) :2142-2147
[29]   Characterizing dissolved organic matter in eroded sediments from a loess hilly catchment using fluorescence EEM-PARAFAC and UV-Visible absorption: Insights from source identification and carbon cycling [J].
Liu, Chun ;
Li, Zhongwu ;
Berhe, Asmeret Asefaw ;
Xiao, Haibing ;
Liu, Lin ;
Wang, Danyang ;
Peng, Hao ;
Zeng, Guangming .
GEODERMA, 2019, 334 :37-48
[30]   Spectrofluorometric characterization of dissolved organic matter for indication of precursor organic material and aromaticity [J].
McKnight, DM ;
Boyer, EW ;
Westerhoff, PK ;
Doran, PT ;
Kulbe, T ;
Andersen, DT .
LIMNOLOGY AND OCEANOGRAPHY, 2001, 46 (01) :38-48