Analysis of formation mechanism of black-odor water bodies by combining dissolved organic matter data with machine learning

LIU Zhong; WU Rui; GU Nitao; WANG Xilei; XU Jiafeng; LUO Yan; MA Haichuan; DUAN Niangming; YU Xubiao

doi:10.13205/j.hjgc.202508026

Volume 43 Issue 8

Aug. 2025

Turn off MathJax

Article Contents

Article Navigation > ENVIRONMENTAL ENGINEERING > 2025 > 43(8): 280-291

LIU Zhong, WU Rui, GU Nitao, WANG Xilei, XU Jiafeng, LUO Yan, MA Haichuan, DUAN Niangming, YU Xubiao. Analysis of formation mechanism of black-odor water bodies by combining dissolved organic matter data with machine learning[J]. ENVIRONMENTAL ENGINEERING , 2025, 43(8): 280-291. doi: 10.13205/j.hjgc.202508026

Citation:

LIU Zhong, WU Rui, GU Nitao, WANG Xilei, XU Jiafeng, LUO Yan, MA Haichuan, DUAN Niangming, YU Xubiao. Analysis of formation mechanism of black-odor water bodies by combining dissolved organic matter data with machine learning[J]. ENVIRONMENTAL ENGINEERING , 2025, 43(8): 280-291. doi: 10.13205/j.hjgc.202508026

Citation:

LIU Zhong, WU Rui, GU Nitao, WANG Xilei, XU Jiafeng, LUO Yan, MA Haichuan, DUAN Niangming, YU Xubiao. Analysis of formation mechanism of black-odor water bodies by combining dissolved organic matter data with machine learning[J]. ENVIRONMENTAL ENGINEERING , 2025, 43(8): 280-291. doi: 10.13205/j.hjgc.202508026

PDF( 0 KB)

Analysis of formation mechanism of black-odor water bodies by combining dissolved organic matter data with machine learning

doi: 10.13205/j.hjgc.202508026

1. Ningbo Research Institute of Ecological and Environmental Science, Ningbo 315012, China;
2. Ningbo Yonghuanyuan Environmental Protection Engineering Technology Co., Ltd., Ningbo 315000, China;
3. School of Civil & Environmental Engineering and Geography Science, Ningbo University, Ningbo 315211, China

Received Date: 2024-04-07
Accepted Date: 2024-10-11
Rev Recd Date: 2024-05-24

Abstract

Abstract

The systematic resolution of black-odor water issues in urban and rural areas is a critical task in current efforts to improve ecological environmental quality. Faced with the complex water quality evolution patterns during the formation of black-odor water bodies， accurately understanding their formation mechanisms and implementing early intervention are key to achieving precise governance. This study analyzed 179 water bodies with varying pollution levels in Ningbo City， employing the three-dimensional fluorescence region integration （EEM-FRI） method to rapidly assess the composition of dissolved organic matter （DOM）. Principal component analysis combined with Kmeans clustering （PCA-Kmeans） and random forest （RF） machine learning algorithms were applied to analyze DOM data， exploring the formation mechanisms and key indicative factors of black-odor water bodies. The PCA-Kmeans model， based on EEM-FRI data， classified the samples into five groups according to pollution levels. The grouping results showed high consistency with the gradients of major pollutants， such as total nitrogen， total phosphorus， and COD. The accumulation of protein substances generated by microbial activity （Φ_IV） was identified as a key indicative factor of pollution levels in black-odor water bodies. Meanwhile， anthropogenic protein substances （Φ_I and Φ_II） reflect the content of easily degradable organic carbon. Furthermore， the results of the RF model indicated that Φ_IV had a significant impact on the formation of black-odor water bodies （with a SHAP value contribution ratio of 11.16%）. Its influence was more continuous and precise compared to that of total dissolved organic carbon （DOC）. Within the range of 0.9×10⁶ < Φ_IV< 1.0×10⁶， SHAP values significantly increased from negative to positive， reflecting the important indicative significance of Φ_IV for early detection of water body blackening and odor evolution. This study demonstrates that the combination of DOM data and machine learning can provide robust data support for the precise governance of black-odor water bodies.
- dissolved organic matter,
- artificial intelligence,
- precision pollution control,
- three-dimensional fluorescence,
- region integration method

FullText(HTML)

References(66)

References

[1]	住房城乡建设部,生态环境部,城市黑臭水体整治工作指南[S].2015.Ministry of Housing and Urban-Rural Development,Ministry of Ecology and Environment.Guidelines for the remediation of urban black-odor water bodies[S].2015.
[2]	生态环境部,水利部,农业农村部.农村黑臭水体治理工作指南[S].2024.Ministry of Ecology and Environment,Ministry of Water Resources,Ministry of Agriculture and Rural Affairs.Guidelines for the remediation of rural black-odor water bodies[S].2024.
[3]	徐祖信,徐晋,金伟,等.我国城市黑臭水体治理面临的挑战与机遇[J].给水排水,2019,55(3):1-5 ,77.XU Z X,XU J,JIN W,et al.Challenges and opportunities in the remediation of urban black-odor water bodies in China[J].Water&Wastewater Engineering,2019,55(3):1-5,77.
[4]	吕佳佳,杨娇艳,廖卫芳,等.黑臭水形成的水质和环境条件研究[J].华中师范大学学报(自然科学版),2014,48(5):711-716.LÜ J J,YANG J Y,LIAO W F,et al.Study on water quality and environmental conditions for black-odor water formation[J].Journal of Central China Normal University (Natural Sciences),2014,48(5):711-716.
[5]	孙韶玲,盛彦清,孙瑞川,等.河流水体黑臭演化过程及恶臭硫化物的产生机制[J].环境科学与技术,2018,41(3):15-22. SUN S L,SHENG Y Q,SUN R C,et al.Evolution process of black-odor in river water bodies and generation mechanism of malodorous sulfides[J].Environmental Science&Technology (China),2018,41(3):15-22.
[6]	韩文龙,赵起超,金永涛,等.基于"高分二号"卫星影像的黑臭水体识别[J].航天返回与遥感,2022,43(1):120-128. HAN W L,ZHAO Q C,JIN Y.T.,et al.Identification of blackodor water bodies based on GF-2 satellite images[J].Spacecraft Recovery&Remote Sensing,2022,43(1):120-128.
[7]	温爽,王桥,李云梅,等.基于高分影像的城市黑臭水体遥感识别:以南京为例[J].环境科学,2018,39(1):57-67. WEN S,WANG Q,LI Y M,et al.Remote sensing identification of urban black-odor water bodies based on gaofen images:a case study of Nanjing[J].Environmental Science,2018,39(1):57-67.
[8]	申茜,朱利,曹红业.城市黑臭水体遥感监测与筛查研究进展[J].应用生态学报,2017,28(10):3433-3439. SHEN Q,ZHU L,CAO H Y.Research progress on remote sensing monitoring and screening of urban black-odor water bodies[J].Chinese Journal of Applied Ecology,2017,28(10):3433-3439.
[9]	李玲玲,李云梅,吕恒,等.基于决策树的城市黑臭水体遥感分级[J].环境科学,2020,41(11):5060-5072. LI L L,LI Y M,LÜ H,et al.Remote sensing classification of urban black-odor water bodies based on decision tree[J].Environmental Science,2020,41(11):5060-5072.
[10]	CAI X L,WU L Y,LI Y M,et al.Remote sensing identification of urban water pollution source types using hyperspectral data[J].Journal of Hazardous Materials,2023,459.
[11]	XU H C,GUO L D.Molecular size-dependent abundance and composition of dissolved organic matter in river,lake and sea waters[J].Water Research,2017,117:115-126.
[12]	MIAO S,LYU H,XU J,et al.Characteristics of the chromophoric dissolved organic matter of urban black-odor rivers using fluorescence and UV-visible spectroscopy[J].Environmental Pollution,2021,268.
[13]	ZHAO C,XU X Y,CHEN H M,et al.Exploring the complexities of dissolved organic matter photochemistry from the molecular level by using machine learning approaches[J].Environmental Science&Technology,2023,57(46):17889.
[14]	WEISHAAR J L,AIKEN G R,BERGAMASCHI B A,et al.Evaluation of specific ultraviolet absorbance as an indicator of the chemical composition and reactivity of dissolved organic carbon[J].Environmental Science&Technology,2003,37(20):4702-4708.
[15]	MCKNIGHT D M,BOYER E W,WESTERHOFF P K,et al.Spectrofluorometric characterization of dissolved organic matter for indication of precursor organic material and aromaticity[J].Limnology and Oceanography,2001,46(1):38-48.
[16]	FELLMAN J B,HOOD E,SPENCER R G M.Fluorescence spectroscopy opens new windows into dissolved organic matter dynamics in freshwater ecosystems:a review[J].Limnology and Oceanography,2010,55(6):2452-2462.
[17]	HUGUET A,VACHER L,RELEXANS S,et al.Properties of fluorescent dissolved organic matter in the Gironde Estuary[J].Organic Geochemistry,2009,40(6):706-719.
[18]	张运林,秦伯强,龚志军.太湖有色可溶性有机物荧光的空间分布及其与吸收的关系[J].农业环境科学学报,2006(5):1337-1342.ZHANG Y L,QIN B Q,GONG Z J.Spatial distribution of fluorescent chromophoric dissolved organic matter in lake taihu and its relationship with absorption[J].Journal of AgroEnvironment Science,2006 ,25(5):1337-1342.
[19]	PARLANTI E,WöRZ K,GEOFFROY L,et al.Dissolved organic matter fluorescence spectroscopy as a tool to estimate biological activity in a coastal zone submitted to anthropogenic inputs[J].Organic Geochemistry,2000,31(12):1765-1781.
[20]	WILSON H F,XENOPOULOS M A.Effects of agricultural land use on the composition of fluvial dissolved organic matter[J].Nature Geoscience,2009,2(1):37-41.
[21]	CHEN W,WESTERHOFF P,LEENHEER J A,et al.Fluorescence excitation-Emission matrix regional integration to quantify spectra for dissolved organic matter[J].Environmental Science& Technology,2003,37(24):5701-5710.
[22]	李昊.基于k-means算法的非监督学习入侵检测模型和方法的研究[D].哈尔滨:哈尔滨师范大学,2023. LI H. Research on an Unsupervised intrusion detection model and method based on k-means algorithm[D]. Harbin:Harbin Normal University,2023.
[23]	夏晓圣,陈菁菁,王佳佳,等.基于随机森林模型的中国PM_{2. 5}浓度影响因素分析[J].环境科学,2020,41(5):2057-2065. XIA X S,CHEN J J,WANG J J,et al. Analysis of influencing factors of PM 2. 5 concentration in China based on Random Forest model[J]. Environmental Science,2020,41(5):2057-2065.
[24]	PALUSZY S A. Structure mining and knowledge extraction from random forest with applications to The Cancer Genome Atlas project[C],2017.
[25]	马朝君,彭巨擘,袁海滨,等.基于灰狼优化支持向量机回归与SHAP值的锡冶炼能耗预测[J].有色金属(冶炼部分), 2024(2):1-7. MA C J,PENG J B,YUAN H B,et al. Energy consumption prediction of tin smelting based on grey wolf optimized support vector machine regression and SHAP values[J]. Nonferrous Metals (Extractive Metallurgy),2024(2):1-7.
[26]	董佳奇,胡冬梅,闫雨龙,等.基于可解释性机器学习的城市O 3驱动因素挖掘[J].环境科学,2023,44(7):3660-3668. DONG J Q,HU D M,YAN Y L,et al. Mining driving factors of urban O 3 based on interpretable machine learning[J]. Environmental Science,2023,44(7):3660-3668.
[27]	YU F B,WEI C H,DENG P,et al. Deep exploration of random forest model boosts the interpretability of machine learning studies of complicated immune responses and lung burden of nanoparticles[J]. Science Advances,2021,7(22).
[28]	ZHOU S Q,LIU Z Y,WANG M,et al. Impacts of building configurations on urban stormwater management at a block scale using XGBoost[J]. Sustainable Cities and Society,2022,87.
[29]	PENG Y M,UNLUER C. Interpretable machine learning-based analysis of hydration and carbonation of carbonated reactive magnesia cement mixes[J]. Journal of Cleaner Production, 2024,434.
[30]	WU W C,ZHANG M H,ZHAO L,et al. CFD-DPM data-driven GWO-SVR for fast prediction of nitrate decomposition in blast furnaces with nozzle arrangement optimization[J]. Process Safety and Environmental Protection,2023,176:438-449.
[31]	WANG S Y,REN Y,XIA B S. PM_{2. 5} and O₃ concentration estimation based on interpretable machine learning[J]. Atmospheric Pollution Research,2023,14(9).
[32]	HE B H,ZHAO Y H,MAO W,et al. Explainable artificial intelligence reveals environmental constraints in seagrass distribution[J]. Ecological Indicators,2022,144. DOI:10. 1016/ j. ecolind. 2022. 109523.
[33]	TRAN V. Hybrid gradient boosting with meta-heuristic algorithms prediction of unconfined compressive strength of stabilized soil based on initial soil properties,mix design and effective compaction[J]. Journal of Cleaner Production, 2022,355.
[34]	ZHANG Z C,XU B,XU W M,et al. Machine learning combined with the PMF model reveal the synergistic effects of sources and meteorological factors on PM pollution[J]. Environmental Research,2022,212.
[35]	LI T S,ZHANG Q Z,PENG Y B,et al. Contributions of various driving factors to air pollution events:Interpretability analysis from Machine learning perspective[J]. Environment International,2023,173.
[36]	朱秋丽. 基于BP神经网络-模糊数学的汾河太原城区段黑臭评价研究[D]. 太原:太原理工大学,2010. ZHU Q L. Evaluation of black-odor in the Fenhe River taiyuan urban section based on BP Neural network-fuzzy mathematics[D]. Taiyuan:Taiyuan University of Technology,2010.
[37]	LI M M,KONG F L,LI Y,et al. Ecological indication based on source,content,and structure characteristics of dissolved organic matter in surface sediment from Dagu River estuary,China[J]. Environmental Science and Pollution Research,2020,27(36): 45499-45512.
[38]	CARSTEA E M, BRIDGEMAN J, BAKER A, et al. Fluorescence spectroscopy for wastewater monitoring:A review[J]. Water Research,2016,95:205-219.
[39]	HANSEN A M,KRAUS T E C,PELLERIN B A,et al. Optical properties of dissolved organic matter (DOM): Effects of biological and photolytic degradation[J]. Limnology and Oceanography,2016,61(3):1015-1032.
[40]	WANG Q, REN X N, SUN Y, et al. Improvement of the composition and humification of different animal manures by black soldier fly bioconversion[J]. Journal of Cleaner Production, 2021,278.
[41]	GUO X J,LI C W,ZHU Q L,et al. Characterization of dissolved organic matter from biogas residue composting using spectroscopic techniques[J]. Waste Management,2018,78:301-309.
[42]	秦纪洪,王姝,刘琛,等. 海拔梯度上川西高山土壤溶解性有机质(DOM)光谱特征[J]. 中国环境科学,2019,39(10): 4321-4328. QIN J H,WANG S,LIU C,et al. Spectral characteristics of dissolved organic matter (DOM) in alpine soils along an altitude gradient in Western Sichuan[J]. China Environmental Science, 2019,39(10):4321-4328.
[43]	韩成卫,李忠佩,刘丽,等. 去除溶解性有机质对红壤水稻土碳氮矿化的影响[J]. 中国农业科学,2007(1):107-113. HAN C W,LI Z P,LIU L,et al. Effect of removing dissolved organic matter on carbon and nitrogen mineralization in red paddy soil[J]. Scientia Agricultura Sinica,2007 ,40(1):107-113.
[44]	赵彦龙,李心清,丁文慈,等. 水中有机质矿化作用的生物地球化学室内模拟研究[J]. 地球与环境,2007(3):233-238. ZHAO Y L,LI X Q,DING W C,et al. Laboratory simulation study on biogeochemical mineralization of organic matter in water[J]. Earth and Environment,2007 ,35(3):233-238.
[45]	王鹏,刘梅,翁益松,等. 河道水体黑臭前后微生物种群变化研究[J]. 安徽农业科学,2019,47(22):47-51. WANG P, LIU M, WENG Y S, et al. Study on microbial community changes in river water before and after black-odor occurrence[J]. Anhui Agricultural Science,2019,47(22): 47-51.
[46]	于莉莉,钟晔,孙福红,等. pH值对滇池水体溶解性有机质(DOM)光降解作用的影响[J]. 光谱学与光谱分析,2019,39(08):2533-2539. YU L L, ZHONG Y, SUN F H, et al. Effect of pH on photodegradation of dissolved organic matter (DOM) in Dianchi Lake Water[J]. Spectroscopy and Spectral Analysis,2019,39(8):2533-2539.
[47]	HE X-S,FAN Q-D. Investigating the effect of landfill leachates on the characteristics of dissolved organic matter in groundwater using excitation - emission matrix fluorescence spectra coupled with fluorescence regional integration and self-organizing map[J]. Environmental Science and Pollution Research,2016,23(21):21229-21237.
[48]	YU G H,LUO Y H,WU M J,et al. PARAFAC modeling of fluorescence excitation-emission spectra for rapid assessment of compost maturity[J]. Bioresource Technology,2010,101(21): 8244-8251.
[49]	WANG Z W,WU Z C,TANG S J. Characterization of dissolved organic matter in a submerged membrane bioreactor by using three-dimensional excitation and emission matrix fluorescence spectroscopy[J]. Water Research,2009,43(6):1533-1540.
[50]	WANG Y L,HU Y Y,YANG C M,et al. Variations of DOM quantity and compositions along WWTPs-river-lake continuum: Implications for watershed for environmental management[J]. Chemosphere,2019,218:468-476.
[51]	ZHANG S H,CHEN Z Q,WEN Q X,et al. Assessment of maturity during co-composting of penicillin mycelial dreg via fluorescence excitation-emission matrix spectra:Characteristics of chemical and fluorescent parameters of water-extractable organic matter[J]. Chemosphere,2016,155:358-366.
[52]	WEI D,YAN T,ZHANG K Y,et al. Qualitative and quantitative analysis of extracellular polymeric substances in partial nitrification and full nitrification reactors[J]. Bioresource Technology,2017,240:171-176.
[53]	GUO L,LU M M,LI Q Q,et al. Three-dimensional fluorescence excitation-emission matrix (EEM) spectroscopy with regional integration analysis for assessing waste sludge hydrolysis treated with multi-enzyme and thermophilic bacteria[J]. Bioresource Technology,2014,171:22-28.
[54]	MAQBOOL T,LY Q V,ASIF M B,et al. Fate and role of fluorescence moieties in extracellular polymeric substances during biological wastewater treatment:a review[J]. Science of the Total Environment,2020,718.
[55]	刘辉,周琼芝,朱嘉浩,等. 有机碳源对微生物代谢所致水体黑臭现象形成的影响机制[J]. 净水技术 ,2022,41(7): 111-118. LIU H,ZHOU Q Z,ZHU J H,et al. Mechanism of black-odor water formation caused by microbial metabolism induced by organic carbon sources[J]. Water Purification Technology, 2022,41(7):111-118.
[56]	李翔,李致春,汪旋,等. 蓝藻衰亡过程中上覆水溶解性有机物变化特征[J]. 环境科学,2021,42(7):3281-3290. LI X,LI Z C,WANG X,et al. Variation characteristics of dissolved organic matter in overlying water during cyanobacteria decay[J]. Environmental Science,2021,42(7):3281-3290.
[57]	张圣洁,蔡中华,朱伟胜,等. 藻际环境中胞外聚合物的研究进展[J]. 微生物学报,2020,60(8):1521-1533. ZHANG S J,CAI Z H,ZHU W S,et al. Research progress on extracellular polymeric substances in algal micro-environments[J]. Acta Microbiologica Sinica,2020,60(8):1521-1533.
[58]	WANG Y,GONG X Y,HUANG D Y,et al. The binding effect and photooxidation on oxytetracycline with algal extracellular polymeric substances and natural organic matter[J]. Chemosphere,2022,307.
[59]	逄勇,颜润润,余钟波,等. 风浪作用下的底泥悬浮沉降及内源释放量研究[J]. 环境科学,2008(9):2456-2464. PANG Y, YAN R R, YU Z B, et al. Study on sediment resuspension and internal release under wind-wave action[J]. Environmental Science,2008 ,29(9):2456-2464.
[60]	胡明,刘心远,薛娇,等. 水深和扰动对北运河沉积物释放的模拟研究[J]. 环境科学学报,2021,41(1):174-180. HU M,LIU X Y,XUE J,et al. Simulation study on the release of sediments from the north canal under different water depths and disturbances[J]. Acta Scientiae Circumstantiae,2021,41(1): 174-180.
[61]	LI P,YE J F,ZHANG W C,et al. The blackening process of black-odor water: Substance types determination and crucial roles analysis[J]. Journal of Hazardous Materials,2023,443.
[62]	LI P,YE J F,ZHANG J Y,et al. Evaluation of levels of black in black-odor waters through absorption coefficient method[J]. Science of the Total Environment,2022,820.
[63]	赵秀云,赵昕宇,杨津津,等. 堆肥过程中木质素的降解机理及影响因素研究进展[J]. 环境工程,2021,39(6):128-136. ZHAO X Y,ZHAO X Y,YANG J J,et al. Research progress on degradation mechanism and influencing factors of lignin during composting[J]. Environmental Engineering, 2021, 39(6): 128-136.
[64]	PéREZ J, MUñOZ-DORADO J, DE LA RUBIA T, et al. Biodegradation and biological treatments of cellulose, hemicellulose and lignin: an overview[J]. International Microbiology,2002,5(2):53-63.
[65]	邓科. 城市生活污水有机成分与ASM水质特性参数关系研究[D]. 上海:同济大学,2006. DENG K. Study on the relationship between organic components of municipal wastewater and ASM water quality parameters[D]. Shanghai:Tongji University,2006.
[66]	XU W H,WANG W W,DENG B B,et al. A review of the formation conditions and assessment methods of black and odorous water[J]. Environmental Monitoring and Assessment,2024,196(1). DOI:10. 1007/s10661-023-12222-5.