基于人工智能技术的新污染物治理策略与路径研究
Strategies and Pathways for Emerging Pollutant Governance Based on Artificial Intelligence Technology
随着工业化、城市化的快速推进,不断涌现的新污染物给环境保护带来了全新挑战,也对人类健康构成了极大威胁。在此背景下,人工智能技术凭借高效、精准的优势,正逐步成为解决新污染物治理问题的关键工具。本文梳理了新污染物治理的现状及面临的主要挑战,提出了基于人工智能技术的新污染物治理框架:在筛选环节,借助深度学习、自然语言处理技术,从海量数据中挖掘潜在的新污染物,提高筛查速度与精度;在风险评估方面,运用机器学习模型对多维数据进行整合,构建动态评估体系,以实时量化污染物的环境行为和健康风险;在控制环节,通过人工智能技术开展智能化监测、技术优选、动态调控,推动新污染物治理方案的持续优化与提升。进一步构建了新污染物大模型框架,用于融合多模态环境数据,支持新污染物的识别、风险评估、治理方案优化。研究建议,构建智能化新污染物识别与监测体系、开发数据驱动的风险评估与预测平台、优化污染治理技术与管理平台、构建知识驱动的大模型辅助决策系统,以精准推动并全面深化基于人工智能技术的新污染物治理,为相关领域科研、行业应用、政策制定等提供参考。
With the rapid advancement of industrialization and urbanization, emerging pollutants has brought unprecedented challenges to environmental protection and posed significant threats to human health. In this context, artificial intelligence (AI), leveraging its efficiency and precision, is gradually becoming a critical tool for emerging pollutant governance. This study reviews the current status and major challenges regarding emerging pollutant governance, and proposes an AI-based framework for managing emerging pollutants. In the screening phase, deep learning and natural language processing technologies are utilized to identify potential emerging pollutants from vast amounts of data, enhancing screening speed and accuracy. In risk assessment, machine learning models integrate multidimensional data to construct a dynamic evaluation system that can quantitatively assess environmental behaviors and health risks of pollutants in real time. In the control phase, AI technology enables intelligent monitoring, optimal technology selection, and dynamic regulation, promoting continuous optimization of governance strategies. Furthermore, the study proposes a large model framework for emerging pollutants, aiming to integrate multimodal environmental data to assist in the identification, risk assessment, and optimization of governance strategies for emerging pollutants. Research recommendations include establishing an intelligent identification and monitoring system for emerging pollutants, developing a data-driven risk assessment and prediction platform, optimizing pollution control technology and management platforms, and building a knowledge-driven large-model-assisted decision-making system. These efforts aim to precisely improve AI-based governance of emerging pollutants, providing references for scientific research, industry applications, and policy-making in related fields.
新污染物 / 人工智能 / 大模型 / 环境保护 / 污染物治理
emerging pollutants / artificial intelligence / large model / environmental protection / pollutant governance
| [1] |
Wang B, Sui Q, Liu H J, et al. Promoting environmental risk assessment and control of emerging contaminants in China [J]. Engineering, 2024, 37: 13‒17. |
| [2] |
王佳钰, 王中钰, 陈景文, 环境新污染物治理与化学品环境风险防控的系统工程 [J]. 科学通报, 2022, 67(3): 267‒277. |
| [3] |
Wang J Y, Wang Z Y, Chen J W, et al. Environmental systems engineering consideration on treatment of emerging pollutants and risk prevention and control of chemicals [J]. Chinese Science Bulletin, 2022, 67(3): 267‒277. |
| [4] |
王腾. 面向新污染物风险治理的环境监管 [J]. 中国人口·资源与环境, 2024, 34(1): 106‒117. |
| [5] |
Wang T. Environmental regulation for new pollutant risk governance [J]. China Population, Resources and Environment, 2024, 34(1): 106‒117. |
| [6] |
邓启红, 于云江, 康乐. 新污染物健康风险需高度重视与有效防范 [J]. 科学通报, 2024, 69(6): 645‒647. |
| [7] |
Deng Q H, Yu Y J, Kang N. The health risks of new pollutants need to be highly valued and effectively prevented [J]. Chinese Science Bulletin, 2024, 69(6): 645‒647. |
| [8] |
王亚韡, 张秋瑞, 于南洋, 新污染物 [J]. 化学进展, 2024, 36(11): 1607‒1784. |
| [9] |
Wang Y W, Zhang Q R, Yu N Y, et al. Emerging pollutants [J]. Progress in Chemistry, 2024, 36(11): 1607‒1784. |
| [10] |
Puri M, Gandhi K, Kumar M S. Emerging environmental contaminants: A global perspective on policies and regulations [J]. Journal of Environmental Management, 2023, 332: 117344. |
| [11] |
陈玲, 杨潇, 张琳钰, 食品中环境新污染物危害管控研究 [J]. 中国工程科学, 2022, 24(6): 99‒106. |
| [12] |
Chen L, Yang X, Zhang L Y, et al. Hazard and management of emerging environmental pollutants in food of China [J]. Strategic Study of CAE, 2022, 24(6): 99‒106. |
| [13] |
Kumari S, Chowdhry J, Chandra Garg M. AI-enhanced adsorption modeling: Challenges, applications, and bibliographic analysis [J]. Journal of Environmental Management, 2024, 351: 119968. |
| [14] |
Ke H B, Gong S L, He J J, et al. Development and application of an automated air quality forecasting system based on machine learning [J]. Science of The Total Environment, 2022, 806: 151204. |
| [15] |
Mehmood K, Bao Y S, Saifullah, et al. Predicting the quality of air with machine learning approaches: Current research priorities and future perspectives [J]. Journal of Cleaner Production, 2022, 379: 134656. |
| [16] |
Jones K C. Persistent organic pollutants (POPs) and related chemicals in the global environment: Some personal reflections [J]. Environmental Science and Technology, 2021, 55(14): 9400‒9412. |
| [17] |
Reincke M, Arlt W, Damdimopoulou P, et al. Endocrine disrupting chemicals are a threat to hormone health: A commentary on behalf of the ESE [J]. Nature Reviews Endocrinology, 2024, 20(4): 187‒188. |
| [18] |
Olmo-Gilabert R, Fagiano V, Alomar C, et al. Plastic webs, the new food: Dynamics of microplastics in a Mediterranean food web, key species as pollution sources and receptors [J]. Science of The Total Environment, 2024, 918: 170719. |
| [19] |
MacLeod M, Arp H P H, Tekman M B, et al. The global threat from plastic pollution [J]. Science, 2021, 373(6550): 61‒65. |
| [20] |
Talukdar A, Bhattacharya S, Bandyopadhyay A, et al. Microplastic pollution in the Himalayas: Occurrence, distribution, accumulation and environmental impacts [J]. Science of The Total Environment, 2023, 874: 162495. |
| [21] |
张少轩, 陈安娜, 陈成康, 持久性、迁移性和潜在毒性化学品环境健康风险与控制研究现状及趋势分析 [J]. 环境科学, 2023, 44(6): 3017‒3023. |
| [22] |
Zhang S X, Chen A N, Chen C K, et al. Research status and trend analysis of environmental and health risk and control of persistent, mobile, and toxic chemicals [J]. Environmental Science, 2023, 44(6): 3017‒3023. |
| [23] |
Rayasam S D G, Koman P D, Axelrad D A, et al. Toxic substances control act (TSCA) implementation: How the amended law has failed to protect vulnerable populations from toxic chemicals in the United States [J]. Environmental Science & Technology, 2022, 56(17): 11969‒11982. |
| [24] |
Pistollato F, Madia F, Corvi R, et al. Current EU regulatory requirements for the assessment of chemicals and cosmetic products: Challenges and opportunities for introducing new approach methodologies [J]. Archives of Toxicology, 2021, 95(6): 1867‒1897. |
| [25] |
Hayashi T I, Furuhama A, Yokomizo H, et al. Quantitative analyses of misclassification rates in the hazard classification of environmental chemicals: Evaluation of procedures for deriving predicted no-effect concentrations in the Chemical Substance Control Law in Japan [J]. Risk Analysis, 2023, 43(4): 686‒699. |
| [26] |
马莹, 李想, 骆永明. 加强我国新污染物的环境控制技术与管理政策研究 [J]. 中国科学院院刊, 2025, 40(1): 181‒192. |
| [27] |
Ma Y, Li X, Luo Y M. Strengthen research on environmental control technologies and management policies for emerging contaminants in China [J]. Bulletin of Chinese Academy of Sciences, 2025, 40(1): 181‒192. |
| [28] |
Wang F, Xiang L L, Sze-Yin Leung K, et al. Emerging contaminants: A one health perspective [J]. The Innovation, 2024, 5(4): 100612. |
| [29] |
Ruan T, Li P Y, Wang H T, et al. Identification and prioritization of environmental organic pollutants: From an analytical and toxicological perspective [J]. Chemical Reviews, 2023, 123(17): 10584‒10640. |
| [30] |
Hardesty B D, Harari J, Isobe A, et al. Using numerical model simulations to improve the understanding of micro-plastic distribution and pathways in the marine environment [J]. Frontiers in Marine Science, 2017, 4: 30. |
| [31] |
Cui S X, Gao Y C, Huang Y Z, et al. Advances and applications of machine learning and deep learning in environmental ecology and health [J]. Environmental Pollution, 2023, 335: 122358. |
| [32] |
Han M, Jin B, Liang J, et al. Developing machine learning approaches to identify candidate persistent, mobile and toxic (PMT) and very persistent and very mobile (vPvM) substances based on molecular structure [J]. Water Research, 2023, 244: 120470. |
| [33] |
阮挺, 江桂斌. 新污染物筛查和评估系统方法 [J]. 科学通报, 2024, 69(6): 651‒652. |
| [34] |
Ruan T, Jiang G B. Systematic methodology for the screening and assessment of new pollutants [J]. Chinese Science Bulletin, 2024, 69(6): 651‒652. |
| [35] |
Dávila-Santiago E, Shi C, Mahadwar G, et al. Machine learning applications for chemical fingerprinting and environmental source tracking using non-target chemical data [J]. Environmental Science & Technology, 2022, 56(7): 4080‒4090. |
| [36] |
Hierlmeier V R, Gurten S, Freier K P, et al. Persistent, bioaccumulative, and toxic chemicals in insects: Current state of research and where to from here? [J]. Science of The Total Environment, 2022, 825: 153830. |
| [37] |
马妍, 王嘉毅, 陈祥强, 基于综合评分法和风险商值法筛选黄河流域特征污染物及风险污染物 [J]. 环境科学研究, 2024, 37(6): 1278‒1291. |
| [38] |
Ma Y, Wang J Y, Chen X Q, et al. Screening of characteristic pollutants and risk pollutants in the Yellow River Basin based on comprehensive evaluation and risk quotient methods [J]. Research of Environmental Sciences, 2024, 37(6): 1278‒1291. |
| [39] |
程诗洋, 闵浩, 刘春生, 发展基于机器学习的芳香醚类污染物氧脱烷基化反应的预测模型 [J]. 环境科学学报, 2024, 44(9): 366‒375. |
| [40] |
Cheng S Y, Min H, Liu C S, et al. Development of a predictive model for O-dealkylation of aromatic ether contaminants based on machine learning methods [J]. Acta Scientiae Circumstantiae, 2024, 44(9): 366‒375. |
| [41] |
李佳礼, 刘杰, 胡承志, 人工智能驱动的可持续环境基础研究系统 [J]. 环境工程学报, 2024, 18(5): 1205‒1218. |
| [42] |
Li J L, Liu J, Hu C Z, et al. AI-driven sustainable environmental foundation research system [J]. Chinese Journal of Environmental Engineering, 2024, 18(5): 1205‒1218. |
| [43] |
Bibri S E, Huang J, Krogstie J. Artificial intelligence of things for synergizing smarter eco-city brain, metabolism, and platform: Pioneering data-driven environmental governance [J]. Sustainable Cities and Society, 2024, 108: 105516. |
| [44] |
Nkinahamira F, Feng A Q, Zhang L J, et al. Machine learning approaches for monitoring environmental metal pollutants: Recent advances in source apportionment, detection, quantification, and risk assessment [J]. TrAC Trends in Analytical Chemistry, 2024, 180: 117980. |
| [45] |
Shah M I, Javed M F, Alqahtani A, et al. Environmental assessment based surface water quality prediction using hyper-parameter optimized machine learning models based on consistent big data [J]. Process Safety and Environmental Protection, 2021, 151: 324‒340. |
| [46] |
Sun X F, Zhang X M, Muir D C G, et al. Identification of potential PBT/POP-like chemicals by a deep learning approach based on 2D structural features [J]. Environmental Science & Technology, 2020, 54(13): 8221‒8231. |
| [47] |
Middya A I, Roy S. Pollutant specific optimal deep learning and statistical model building for air quality forecasting [J]. Environmental Pollution, 2022, 301: 118972. |
| [48] |
Tong X N, Mohapatra S, Zhang J J, et al. Source, fate, transport and modelling of selected emerging contaminants in the aquatic environment: Current status and future perspectives [J]. Water Research, 2022, 217: 118418. |
| [49] |
陈晓红. 以新一代信息技术为引擎加快形成新质生产力 [N]. 人民政协报, 2023-11-30(07). |
| [50] |
Chen X H. Accelerate the formation of new quality productive forces with new generation information technology as the engine [N]. People’s Political Consultative Conference Daily, 2023-11-30(07). |
| [51] |
Bhattacharya D, Cassady H J, Hickner M A, et al. Large language models as molecular design engines [J]. Journal of Chemical Information and Modeling, 2024, 64(18): 7086‒7096. |
| [52] |
Kim S, Jung Y, Schrier J. Large language models for inorganic synthesis predictions [J]. Journal of the American Chemical Society, 2024, 146(29): 19654‒19659. |
| [53] |
Tu Q S, Guo J, Li N, et al. Mitigating grand challenges in life cycle inventory modeling through the applications of large language models [J]. Environmental Science & Technology, 2024, 58(44): 19595‒19603. |
国家自然科学基金项目(72088101)
湘江实验室项目(24XJ01003)
/
| 〈 |
|
〉 |