机器学习在新污染物研究中的应用进展

Research Progress on the Application of Machine Learning in New Pollutants Studies

摘要

新污染物（New Pollutants，NP）分布广泛，在海洋、土壤、大气、饮用水中都频繁检出。随着 NP 在环境中的持续累积和扩散，其潜在的生态与健康风险日益凸显，引起了学术界和公众的高度关注。目前，国内外学者围绕NP的识别检测、迁移转化规律、生态毒理效应及高效去除技术等方面开展了大量的系统性研究。机器学习作为一种先进的数据建模与分析方法，能够通过大数据预测，显著提升NP研究的时效性与预测准确性。本文综述了机器学习在持久性有机污染物、内分泌干扰物、抗生素、微塑料的识别、分布、毒性效应等方面的应用现状，并对未来研究方向做出展望，如探索开发可解释的机器学习模型、建立数据共享平台、实时监控污染物、建立传统-新兴污染物的关联模型等。

Abstract

New Pollutants (NP) are widely distributed and frequently detected in oceans, soil, the atmosphere, and drinking water. With their persistent accumulation and diffusion in the environment, the potential ecological and health risks of NP have become increasingly prominent, drawing significant attention from both academia and the public. Currently, researchers worldwide have conducted extensive systematic studies on the identification and detection of NP, their migration and transformation patterns, ecotoxicological effects, and efficient removal technologies.Machine Learning, as an advanced data modeling and analysis method, can significantly enhance the timeliness and predictive accuracy of NP research through big data-driven forecasting. This review summarizes the current applications of ML in the identification, distribution, and toxicological effects of persistent organic pollutants, endocrine disrupting chemicals, antibiotics and microplastics. Additionally, it provides insights into future research directions, such as exploring interpretable ML models, establishing data-sharing platforms, enabling real-time pollutant monitoring and establishing an association model between traditional and new pollutants.

关键词

机器学习 / 新污染物 / 识别 / 分布 / 毒性

Key words

Machine Learning / Emerging Contaminants / Identification / Distribution / Toxicity

参考文献

[1] Khan S, Naushad M, Govarthanan M, et al. Emerging contaminants of high concern for the environment: Current trends and future research[J]. Environmental Research, 2022, 207: 112609.

[2] Yu Y, Wang S, Yu P, et al. A bibliometric analysis of emerging contaminants (ECs)(2001−2021): Evolution of hotspots and research trends[J]. Science of The Total Environment, 2024, 907: 168116.

[3] 王亚韡, 张秋瑞, 于南洋, 等 . 新污染物[J]. 化学进展, 2024, 36(11): 1607-1784.

[4] Chen B, Zhang Z, Wang T, et al. Global distribution of marine microplastics and potential for biodegradation[J]. Journal of Hazardous Materials, 2023, 451: 131198.

[5] Wang Y, Yang Y, Liu X, et al. Interaction of microplastics with antibiotics in aquatic environment: distribution, adsorption, and toxicity[J]. Environmental science & technology, 2021, 55(23): 15579-15595.

[6] Jia W L, Song C, He L Y, et al. Antibiotics in soil and water: Occurrence, fate, and risk[J]. Current Opinion in Environmental Science & Health, 2023, 32: 100437.

[7] Shen M, Yu B, Hu Y, et al. Occurrence and health risk assessment of sulfonamide antibiotics in different freshwater fish in northeast China[J]. Toxics, 2023, 11(10): 835.

[8] Ali M, Xu D, Yang X, et al. Microplastics and PAHs mixed contamination: an in—depth review on the sources, co—occurrence, and fate in marine ecosystems[J]. Water Research, 2024: 121622.

[9] Bostan N, Ilyas N, Akhtar N, et al. Toxicity assessment of microplastic (MPs); a threat to the ecosystem[J]. Environmental Research, 2023: 116523.

[10] Omar T F T, Ahmad A, Aris A Z, et al. Endocrine disrupting compounds (EDCs) in environmental matrices: Review of analytical strategies for pharmaceuticals, estrogenic hormones, and alkylphenol compounds[J]. TrAC Trends in Analytical Chemistry, 2016, 85: 241-259.

[11] Jordan M I, Mitchell T M . Machine learning: Trends, perspectives, and prospects. Science, 2015, 349: 255-260

[12] Gao P. Chasing "Emerging" Contaminants: An Endless Journey toward Environmental Health[J]. Environmental Science & Technology, 2024, 58(4): 1790-1792.

[13] 刘思思, 张波, 李星颖, 等 . 机器学习在环境分析检测中的应用研究进展[J]. 分析测试学报, 2024, 43: 1-14.

[14] 武子豪, 吴礼滨, 洪伟, 等 . 机器学习在生态环境损害鉴定评估领域的应用前景[J]. 农业环境科学学报, 2023, 42(12): 2860-2868.

[15] Zhong S, Zhang K, Bagheri M, et al. Machine learning: new ideas and tools in environmental science and engineering[J]. Environmental science & technology, 2021, 55(19): 12741-12754.

[16] Chen J, Zhu S, Wang P, et al. Predicting particulate matter, nitrogen dioxide, and ozone across Great Britain with high spatiotemporal resolution based on random forest models[J]. Science of The Total Environment, 2024, 926: 171831.

[17] Chen K, Chen H, Zhou C, et al. Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data[J]. Water research, 2020, 171: 115454.

[18] Ashraf M A . Persistent organic pollutants (POPs): a global issue, a global challenge[J]. Environmental Science and Pollution Research, 2017, 24: 4223-4227.

[19] Jones K C . Persistent organic pollutants (POPs) and related chemicals in the global environment: some personal reflections[J]. Environmental Science & Technology, 2021, 55(14): 9400-9412.

[20] Jiang L, Lv J, Jones K C, et al. Soil's hidden power: The stable soil organic carbon pool controls the burden of persistent organic pollutants in background soils[J]. Environmental Science & Technology, 2024, 58(19): 8490-8500.

[21] Du X, Sun G, Yuan B, et al. Unveiling Chlorinated Paraffin Emissions via Tire Wear and Airborne Release from Various Types of Tires[J]. Environmental Science & Technology Letters, 2024, 12(1): 92-97.

[22] Wang Y, Zhong H, Luo Y, et al. Temporal trends of novel brominated flame retardants in mollusks from the Chinese Bohai Sea (2011—2018)[J]. Science of the Total Environment, 2021, 777: 146101.

[23] Sun Y, Ruan T, Yan B, et al. Rethinking the Carcinogenic Classification of Perfluorooctanoic Acid (PFOA)[J]. Environmental Science & Technology, 2025.

[24] Chen Y, Yang Y, Cui J, et al. Decoding PFAS contamination via Raman spectroscopy: A combined DFT and machine learning investigation[J]. Journal of Hazardous Materials, 2024, 465: 133260.

[25] Mu H, Yang Z, Chen L, et al. Suspect and nontarget screening of per—and polyfluoroalkyl substances based on ion mobility mass spectrometry and machine learning techniques[J]. Journal of Hazardous Materials, 2024, 461: 132669.

[26] Matta K, Vigneau E, Cariou V, et al. Associations between persistent organic pollutants and endometriosis: A multipollutant assessment using machine learning algorithms[J]. Environmental Pollution, 2020, 260: 114066.

[27] Wang T, Yang J, Han Y, et al. Unveiling the intricate connection between per—and polyfluoroalkyl substances and prostate hyperplasia[J]. Science of The Total Environment, 2024, 932: 173085.

[28] Diamanti—Kandarakis E, Bourguignon J P, Giudice L C, et al. Endocrine—disrupting chemicals: an Endocrine Society scientific statement[J]. Endocrine reviews, 2009, 30(4): 293-342.

[29] Muñoz J P . The impact of endocrine—disrupting chemicals on stem cells: Mechanisms and implications for human health[J]. Journal of Environmental Sciences, 2023.

[30] Gorga M, Insa S, Petrovic M, et al. Occurrence and spatial distribution of EDCs and related compounds in waters and sediments of Iberian rivers[J]. Science of the Total Environment, 2015, 503: 69-86.

[31] Vandenberg L N, Chahoud I, Heindel J J, et al. Urinary, circulating, and tissue biomonitoring studies indicate widespread exposure to bisphenol A[J]. Ciencia & saude coletiva, 2012, 17: 407-434.

[32] Wang Y, Zhang X, Guo F, et al. Estimating the temporal and spatial distribution and threats of bisphenol A in temperate lakes using machine learning models[J]. Ecotoxicology and Environmental Safety, 2024, 269: 115750.

[33] Ding B, Yang F, Han W, et al. Unveiling Hidden Health Risks: Machine Learning Enhanced Modeling of Plastic Additive Release Kinetics in Fresh Produce Packaging[J]. Environmental Science & Technology, 2025.

[34] Heo S K, Safder U, Yoo C K . Deep learning driven QSAR model for environmental toxicology: effects of endocrine disrupting chemicals on human health[J]. Environmental Pollution, 2019, 253: 29-38.

[35] Safder U, Nam K J, Kim D, et al. Quantitative structure—property relationship (QSPR) models for predicting the physicochemical properties of polychlorinated biphenyls (PCBs) using deep belief network[J]. Ecotoxicology and environmental safety, 2018, 162: 17-28.

[36] Hong Y, Xie H, Jin X, et al. Prediction of HC5s for phthalate esters by use of the QSAR—ICE model and ecological risk assessment in Chinese surface waters[J]. Journal of Hazardous Materials, 2024, 467: 133642.

[37] Collins S P, Barton—Maclaren T S . Novel machine learning models to predict endocrine disruption activity for high—throughput chemical screening[J]. Frontiers in toxicology, 2022, 4: 981928.

[38] Zhang X, Han X, Xiang T, et al. From High Resolution Tandem Mass Spectrometry to Pollutant Toxicity AI—Based Prediction: A Case Study of 7 Endocrine Disruptors Endpoints[J]. Environmental Science & Technology, 2025, 59(9): 4505-4517.

[39] Lyu J, Yang L, Zhang L, et al. Antibiotics in soil and water in China—a systematic review and source analysis[J]. Environmental Pollution, 2020, 266: 115147.

[40] Klein E Y, Van Boeckel T P, Martinez E M, et al. Global increase and geographic convergence in antibiotic consumption between 2000 and 2015[J]. Proceedings of the National Academy of Sciences, 2018, 115(15): E3463-E3470.

[41] Carvalho I T, Santos L . Antibiotics in the aquatic environments: a review of the European scenario[J]. Environment international, 2016, 94: 736-757.

[42] Mai Z, Xiong X, Hu H, et al. Occurrence, distribution, and ecological risks of antibiotics in Honghu Lake and surrounding aquaculture ponds, China[J]. Environmental Science and Pollution Research, 2023, 30(17): 50732-50742.

[43] Jia W L, Song C, He L Y, et al. Antibiotics in soil and water: Occurrence, fate, and risk[J]. Current Opinion in Environmental Science & Health, 2023, 32: 100437.

[44] Felis E, Kalka J, Sochacki A, et al. Antimicrobial pharmaceuticals in the aquatic environment—occurrence and environmental implications[J]. European Journal of Pharmacology, 2020, 866: 172813.

[45] Su S, Li C, Yang J, et al. Distribution of antibiotic resistance genes in three different natural water bodies—a lake, river and sea[J]. International journal of environmental research and public health, 2020, 17(2): 552.

[46] Zhou Z C, Lin Z J, Shuai X Y, et al. Temporal variation and sharing of antibiotic resistance genes between water and wild fish gut in a peri—urban river[J]. Journal of Environmental Sciences, 2021, 103: 12-19.

[47] Wu J, Wang J, Li Z, et al. Antibiotics and antibiotic resistance genes in agricultural soils: A systematic analysis[J]. Critical Reviews in Environmental Science and Technology, 2023, 53(7): 847-864.

[48] He P, Wu Y, Huang W, et al. Characteristics of and variation in airborne ARGs among urban hospitals and adjacent urban and suburban communities: a metagenomic approach[J]. Environment international, 2020, 139: 105625.

[49] Huang Y, Chen J, Duan Q, et al. A fast antibiotic detection method for simplified pretreatment through spectra—based machine learning[J]. Frontiers of Environmental Science & Engineering, 2022, 16: 1-12.

[50] Wang M, Cetó X, Del Valle M . A sensor array based on molecularly imprinted polymers and machine learning for the analysis of fluoroquinolone antibiotics[J]. ACS sensors, 2022, 7(11): 3318-3325.

[51] Xu L, Zhang H, Xiong P, et al. Occurrence, fate, and risk assessment of typical tetracycline antibiotics in the aquatic environment: A review[J]. Science of the total Environment, 2021, 753: 141975.

[52] Zhu H, He J, Wu Y, et al. Assessment of global antibiotic exposure risk for crops: incorporating soil adsorption via machine learning[J]. Environmental Science & Technology, 2024, 58(30): 13327-13336.

[53] Mu Y, Tang B, Cheng X, et al. Source apportionment and predictable driving factors contribute to antibiotics profiles in Changshou Lake of the Three Gorges Reservoir area, China[J]. Journal of Hazardous Materials, 2024, 466: 133522.

[54] Zhang Z, Zhang Q, Wang T, et al. Assessment of global health risk of antibiotic resistance genes[J]. Nature communications, 2022, 13(1): 1-11.

[55] Zheng D, Yin G, Liu M, et al. Global biogeography and projection of soil antibiotic resistance genes[J]. Science Advances, 2022, 8(46): eabq8015.

[56] Hendriksen R S, Munk P, Njage P, et al. Global monitoring of antimicrobial resistance based on metagenomics analyses of urban sewage[J]. Nature communications, 2019, 10(1): 1124.

[57] Zhang J, Li W, Chen J, et al. Effect of hydraulic conditions on the prevalence of antibiotic resistance in water supply systems[J]. Chemosphere, 2019, 235: 354-364.

[58] Abunada Z, Alazaiza M Y D, Bashir M J K . An overview of per—and polyfluoroalkyl substances (PFAS) in the environment: Source, fate, risk and regulations[J]. Water, 2020, 12(12): 3590.

[59] Chen B, Zhang Z, Wang T, et al. Global distribution of marine microplastics and potential for biodegradation[J]. Journal of Hazardous Materials, 2023, 451: 131198.

[60] Geyer, R.; Jambeck, J. R.; Law, K. L. Production, use, and fate of all plastics ever made. Science Advances. 2017, 3 (7), 25-29.

[61] Brahney J, Mahowald N, Prank M, et al. Constraining the atmospheric limb of the plastic cycle[J]. Proceedings of the National Academy of Sciences, 2021, 118(16): e2020719118.

[62] Zhang S, Sun J, Zhou Q, et al. Microplastic contamination in Chinese topsoil from 1980 to 2050[J]. Science of The Total Environment, 2024: 176918.

[63] Obbard, R. W., S. Sadri, Y. Q. Wong, A. A.Khitun, I. Baker, and R. C. Thompson, Global warming releasesmicroplastic legacy frozen in Arctic Seaice, Earth's Future, 2014, 315-320.

[64] Yao Y, Lili W, Shufen P, et al. Can microplastics mediate soil properties, plant growth and carbon/nitrogen turnover in the terrestrial ecosystem?[J]. Ecosystem Health and Sustainability, 2022, 8(1): 2133638.

[65] Li F, Liu D, Guo X, et al. Identification and visualization of environmental microplastics by Raman imaging based on hyperspectral unmixing coupled machine learning[J]. Journal of Hazardous Materials, 2024, 465: 133336.

[66] Liu Y, Yao W, Qin F, et al. Spectral classification of large—scale blended (Micro) plastics using FT—IR raw spectra and image—based machine learning[J]. Environmental Science & Technology, 2023, 57(16): 6656-6663.

[67] Luo Y, Su W, Xu D, et al. Component identification for the SERS spectra of microplastics mixture with convolutional neural network[J]. Science of The Total Environment, 2023, 895: 165138.

[68] Li W, Li X, Tong J, et al. Effects of environmental and anthropogenic factors on the distribution and abundance of microplastics in freshwater ecosystems[J]. Science of The Total Environment, 2023, 856: 159030.

[69] Qiu Y, Li Z, Zhang T, et al. Predicting aqueous sorption of organic pollutants on microplastics with machine learning[J]. Water Research, 2023, 244: 120503.

[70] Xie L, Luo S, Liu Y, et al. Automatic identification of individual nanoplastics by Raman spectroscopy based on machine learning[J]. Environmental Science & Technology, 2023, 57(46): 18203-18214.

基金资助

最高人民检察院检察技术信息研究中心基本科研课题(JBKY20200906)

最高人民检察院检察技术信息研究中心基本科研课题(JBKY20241005)

最高人民检察院检察技术信息研究中心基本科研课题(JBKY20241006)