-
在经济迅猛发展和社会不断进步过程中,突发性的环境事故也层出不穷。近年来,《中国统计年鉴》中有关全国性突发环境事件的数据,见表1[1-6]。
表1可知,自2014年起,突发环境事件的次数逐年下降,而在所有类型中,一般环境事件所占的比例超过95%。从数量上看,重大环境事件和较大环境事件的发生次数已经控制到很低的水平,但一般环境事件的发生次数依然处于较高的水平。实际上,在频发的环境污染事件中,水体污染事件在其中所占的比例不容小觑[7]。
目前,面对水体污染事件,尤其是突发性水体污染事件,对污染源的追溯最常用的方法有硝酸盐氮氧双稳定同位素溯源技术[8]、水化学特征分析技术[9]、水质模型与地理信息系统相结合技术[10]、多元统计分析技术[11]和三维荧光光谱特征分析技术[12]等。硝酸盐氮氧双稳定同位素溯源技术对污染源的定性和定量评估较为可靠,但是测试成本高,操作难度大[13]。水化学特征分析技术由于其分析结果的准确性较高,且该方法较为经济,被众多学者广泛使用,但此项技术依赖于分析水体的离子组成以定性分析污染源,不能进行污染源的定量评估[14]。水质模型与地理信息系统相结合技术虽能对水中污染物的迁移和转化过程进行较为精确的模拟,但实测数据需求量大、水质变量模拟具有一定局限性、复杂情况下模型的稳定性差,难以在无资料地区普遍应用和推广[15]。多元统计分析技术能够针对分析过程中产生的大量复杂的数据进行简化处理,从而挖掘分析出潜在的污染源特征,但该方法也存在无法定量评估污染源的问题[16]。
一种新型水污染分析检测和溯源技术,三维荧光光谱技术近年来逐渐发展成熟,与其他技术相比,其操作简单且检测过程快速无污染。另外,随着三维荧光光谱技术在水污染溯源案例中的使用以及三维荧光技术的不断更新与发展[17],以三维荧光光谱技术为基础的指纹图谱库逐步建立并完善[18],结合当今世界大数据与人工智能在环境管理中的广泛应用,一种流域指纹图谱和人工智能相结合的水污染在线监测-预警-溯源技术体系正在逐渐构建完善,见图1。
文章综合近年来国内外的相关研究和实际水污染溯源案例,综述了指纹图谱与人工智能结合形成的水污染在线监测-预警-溯源技术体系的构建过程与其在水污染分析检测和溯源领域的研究应用进展。
指纹图谱技术与人工智能在污染物溯源解析中的应用研究
Research and application of fingerprint technology and artificial intelligence in pollutant tracing and analysis
-
摘要: 水污染在线监测-预警-溯源体系在水环境污染事件的溯源中起到了至关重要的作用,而指纹图谱技术与人工智能的有机结合是污染物解析中重要的一环。文章通过水质在线监测-预警体系的建设、指纹图谱库的构建、大数据分析与AI相结合的污染溯源体系的完善以完成对污染物进行分析和溯源。对上述体系的构建以及该领域的研究应用进展进行全面综述,并对现有技术方法的优缺点进行比较和分析。
-
关键词:
- 水质指纹图谱 /
- 大数据 /
- 人工智能 /
- 在线监测-预警-溯源体系
Abstract: The online monitoring-early warning-traceability system for water pollutions plays an important role in the traceability of water pollution events. The combination of fingerprint technology and artificial intelligence (AI) is an important part in the traceability of pollutants. The analysis and traceability of pollutants could be achieved by the construction of the water quality online monitoring-early warning system, the establishment of the fingerprint database, and the improvement of the pollution traceability system with big data analysis and AI analysis. In this paper, the construction of the above systems and the research and application progress in this field are reviewed, the advantages and disadvantages of the existing methods are compared and analyzed. -
表 1 《中国统计年鉴》2014~2019年全国突发环境事件情况
t/a 突发环境
事件次数特别重大
环境事件重大
环境事件较大
环境事件一般
环境事件2014 471 0 3 16 452 2015 334 0 3 5 326 2016 304 0 3 5 296 2017 302 0 1 6 295 2018 286 0 2 6 278 2019 261 0 0 3 258 总计 1958 0 12 41 1905 -
[1] 中华人民共和国国家统计局.2015中国统计年鉴[M].北京: 中国统计出版社,2015. [2] 中华人民共和国国家统计局.2016中国统计年鉴[M].北京: 中国统计出版社,2016. [3] 中华人民共和国国家统计局.2017中国统计年鉴[M].北京: 中国统计出版社,2017. [4] 中华人民共和国国家统计局.2018中国统计年鉴[M].北京: 中国统计出版社,2018. [5] 中华人民共和国国家统计局.2019中国统计年鉴[M].北京: 中国统计出版社,2019. [6] 中华人民共和国国家统计局.2020中国统计年鉴[M].北京: 中国统计出版社,2020. [7] CAMP J S, ABKOWITZ M D, LEBOEUF E J. Inland waterway resource and spill management needs in Southeastern USA[J]. Disaster Prevention & Management, 2010, 19(4): 483 − 497. [8] ROGERS K M, NICOLINI E, GAUTHIER V. Identifying source and formation altitudes of nitrates in drinking water from Réunion Island, France, using a multi-isotopic approach[J]. Journal of Contaminant Hydrology, 2012, 138: 93 − 103. [9] ANSHUMALI, RAMANATHAN A L. Seasonal variation in the major ion chemistry of Pandoh Lake, Mandi District, Himachal Pradesh, India[J]. Applied Geochemistry, 2007, 22(8): 1736 − 1747. doi: 10.1016/j.apgeochem.2007.03.045 [10] NAS B, BERKTAY A. Groundwater contamination by nitrates in the city of Konya, (Turkey): A GIS perspective[J]. Journal of Environmental Management, 2006, 79(1): 30 − 37. doi: 10.1016/j.jenvman.2005.05.010 [11] SHRESTHA S, KAZAMA F. Assessment of surface water quality using multivariate statistical techniques: A case study of the Fuji river basin, Japan[J]. Environmental Modelling & Software, 2007, 22(4): 464 − 475. [12] INAMDAR S, SINGH S, DUTTA S, et al. Fluorescence characteristics and sources of dissolved organic matter for stream water during storm events in a forested mid-Atlantic watershed[J]. Journal of Geophysical Research-Biogeosciences, 2011, 116: G03043. [13] 徐志伟, 张心昱, 于贵瑞, 等. 中国水体硝酸盐氮氧双稳定同位素溯源研究进展[J]. 环境科学, 2014, 35(8): 3230 − 3238. doi: 10.13227/j.hjkx.2014.08.056 [14] VUAI S A, NAKAMURA K, TOKUYAMA A. Geochemical characteristics of runoff from acid sulfate soils in the northern area of Okinawa Island, Japan[J]. Geochemical Journal, 2003, 37(5): 579 − 592. doi: 10.2343/geochemj.37.579 [15] PRAHARAJ T, SWAIN S P, POWELL M A, et al. Delineation of groundwater contamination around an ash pond: geochemical and GIS approach[J]. Environment International, 2002, 27(8): 631 − 638. doi: 10.1016/S0160-4120(01)00121-0 [16] Bu H M, Tan X A, Li S Y, et al. Temporal and spatial variations of water quality in the Jinshui River of the South Qinling Mts. China[J]. Ecotoxicology and Environmental Safety, 2010, 73(5): 907 − 913. doi: 10.1016/j.ecoenv.2009.11.007 [17] 史斌. 水污染动态预警监测模型构建与应急处置工程风险分析[D]. 哈尔滨: 哈尔滨工业大学, 2018. [18] 吕清, 顾俊强, 徐诗琴, 等. 水纹预警溯源技术在地表水水质监测的应用[J]. 中国环境监测, 2015, 31(1): 152 − 156. doi: 10.3969/j.issn.1002-6002.2015.01.030 [19] 朱炜玉, 史斌, 姜继平, 等. 基于水质时间序列异常检测的动态预警方法[J]. 环境科学与技术, 2018, 41(12): 131 − 137. doi: 10.19672/j.cnki.1003-6504.2018.12.019 [20] DARIANE A B, AZIMI S. Streamflow forecasting by combining neural networks and fuzzy models using advanced methods of input variable selection[J]. Journal of Hydroinformatics, 2018, 20(2): 520 − 532. doi: 10.2166/hydro.2017.076 [21] 周俊临. 基于数据挖掘的分布式异常检测[D]. 成都: 电子科技大学, 2010. [22] BYER D. Real-time detection of intentional chemical contamination - In the distribution system[J]. Journal American Water Works Association, 2005, 97(7): 130 − 133. doi: 10.1002/j.1551-8833.2005.tb10938.x [23] BARZEGAR R, ADAMOWSKI J, MOGHADDAM A A. Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran[J]. Stochastic Environmental Research and Risk Assessment, 2016, 30(7): 1797 − 1819. doi: 10.1007/s00477-016-1213-y [24] HIMANSHU S K, PANDEY A, YADAV B. Ensemble wavelet-support vector machine approach for prediction of suspended sediment load using hydrometeorological data[J]. Journal of Hydrologic Engineering, 2017, 22(7): 05017006. doi: 10.1061/(ASCE)HE.1943-5584.0001516 [25] MOHAMMADPOUR R, SHAHARUDDIN S, CHANG C K, et al. Prediction of water quality index in constructed wetlands using support vector machine[J]. Environmental Science & Pollution Research, 2015, 22(8): 6208 − 6219. [26] 毛莺池, 齐海, 接青, 等. M-TAEDA: 多变量水质参数时序数据异常事件检测算法[J]. 计算机应用, 2017, 37(1): 138 − 144. doi: 10.11772/j.issn.1001-9081.2017.01.0138 [27] SINGH K P, MALIK A, MOHAN D, et al. Multivariate statistical techniques for the evaluation of spatial and temporal variations in water quality of Gomti River (India)—a case study - Science Direct[J]. Water Research, 2004, 38(18): 3980 − 3992. doi: 10.1016/j.watres.2004.06.011 [28] NAGHIBI S A, POURGHASEMI H R, ABBASPOUR K. A comparison between ten advanced and soft computing models for groundwater qanat potential assessment in Iran using R and GIS[J]. Theoretical and Applied Climatology, 2018, 131(3): 967-984. [29] PHUNG D, HUANG C, RUTHERFORD S, et al. Temporal and spatial assessment of river surface water quality using multivariate statistical techniques: a study in Can Tho City, a Mekong Delta area, Vietnam[J]. Environmental Monitoring and Assessment, 2015, 187(5):1-13. [30] RODE M, WADE A J, COHEN M J, et al. Sensors in the Stream: The High-Frequency Wave of the Present[J]. Environmental Science and Technology, 2016, 50(19): 10297 − 10307. doi: 10.1021/acs.est.6b02155 [31] 陈国庆, 顾正建, 朱拓, 等. 太湖水荧光光谱分析[J]. 中国环境监测, 2006(6): 16 − 18. doi: 10.3969/j.issn.1002-6002.2006.06.004 [32] MOSTOFA K, F WU, LIU C Q, et al. Characterization of Nanming River (southwestern China) sewerage-impacted pollution using an excitation-emission matrix and PARAFAC[J]. Limnology, 2010, 11(3): 217 − 231. doi: 10.1007/s10201-009-0306-4 [33] CARSTEA E M, BAKER A, BIEROZA M, et al. Continuous fluorescence excitation–emission matrix monitoring of river organic matter[J]. Water Research, 2010, 44(18): 5356 − 5366. doi: 10.1016/j.watres.2010.06.036 [34] HAMBLY A C, HENDERSON R K, STOREY M V, et al. Fluorescence monitoring at a recycled water treatment plant and associated dual distribution system – Implications for cross-connection detection[J]. Water Research, 2010, 44(18): 5323 − 5333. doi: 10.1016/j.watres.2010.06.003 [35] HENDERSON R K, BAKER A, MURPHY K R, et al. Fluorescence as a potential monitoring tool for recycled water systems: A review[J]. Water Research, 2009, 43(4): 863 − 881. doi: 10.1016/j.watres.2008.11.027 [36] GALINHA C F, CARVALHO G, PORTUGAL C, et al. Two-dimensional fluorescence as a fingerprinting tool for monitoring wastewater treatment systems[J]. Journal of Chemical Technology & Biotechnology, 2011, 86(7): 985 − 992. [37] WU J, PONS M N, POTIER O. Wastewater fingerprinting by UV-visible and synchronous fluorescence spectroscopy[J]. Water Science & Technology A Journal of the International Association on Water Pollution Research, 2006, 53(4-5): 449 − 456. [38] 王忠东, 武金玲, 李东明, 等. 基于荧光机制的光纤式农药残留测量系统[J]. 中国激光, 2006(7): 1003 − 1008. doi: 10.3321/j.issn:0258-7025.2006.07.029 [39] 陈茂福, 吴静, 律严励, 等. 城市污水的三维荧光指纹特征[J]. 光学学报, 2008(3): 578 − 582. doi: 10.3321/j.issn:0253-2239.2008.03.033 [40] 吴静, 曹知平, 谢超波, 等. 石化废水的三维荧光光谱特征[J]. 光谱学与光谱分析, 2011, 31(9): 2437 − 2441. [41] 李宏斌, 刘文清, 张玉钧, 等. 三维荧光光谱技术在水监测中的应用[J]. 光学技术, 2006(1): 27 − 30. doi: 10.3321/j.issn:1002-1582.2006.01.033 [42] 戴春燕, 吴静, 向熙, 等. 工业废水为主的城市污水的荧光指纹特征[J]. 光谱学与光谱分析, 2013, 33(2): 414 − 417. doi: 10.3964/j.issn.1000-0593(2013)02-0414-04 [43] 王宝玉. 基于谱分析与荧光响应的水污染预警溯源技术基础研究[D]. 哈尔滨: 哈尔滨工业大学, 2019. [44] 汤久凯, 吴静, 程澄, 等. 某半合成青霉素制药废水的水质指纹特性[J]. 光谱学与光谱分析, 2016, 36(11): 3602 − 3607. [45] 胡远, 柴一荻, 刘博, 等. 某兽药抗生素废水的荧光水质指纹特征[J]. 光谱学与光谱分析, 2018, 38(10): 3144 − 3147. [46] 吴静, 赵宇菲, 曹炯准, 等. 某头孢制药废水的水质指纹特征[J]. 光谱学与光谱分析, 2016, 36(4): 1075 − 1079. [47] 吴静, 崔硕, 苏伟, 等. 北京城市水体的三维荧光特征[J]. 光谱学与光谱分析, 2011, 31(6): 1562 − 1566. doi: 10.3964/j.issn.1000-0593(2011)06-1562-05 [48] 吴静, 谢超波, 曹知平, 等. 炼油废水的荧光指纹特征[J]. 光谱学与光谱分析, 2012, 32(2): 415 − 419. doi: 10.3964/j.issn.1000-0593(2012)02-0415-05 [49] 王士峰, 吴静, 程澄, 等. 某印染废水的水质指纹特征[J]. 光谱学与光谱分析, 2015, 35(12): 3440 − 3443. [50] 张梦怡, 付海娟, 池勇志. 指纹图谱法解析涂装废水中的有机污染物[J]. 山西建筑, 2021, 47(7): 166 − 169. doi: 10.13719/j.cnki.1009-6825.2021.07.059 [51] 谢超波, 吴静, 曹知平, 等. 大流量河道的水质荧光指纹变化[J]. 光谱学与光谱分析, 2014, 34(3): 695 − 697. doi: 10.3964/j.issn.1000-0593(2014)03-0695-03 [52] 刘传旸, 柴一荻, 徐宪根, 等. 南方某河水质荧光指纹特征及污染溯源[J]. 光谱学与光谱分析, 2021, 41(7): 2142 − 2147. [53] MOSTOFA K, YOSHIOKA T, KONOHIRA E, et al. Three-dimensional fluorescence as a tool for investigating the dynamics of dissolved organic matter in the Lake Biwa watershed[J]. Limnology, 2005, 6(2): 101 − 115. doi: 10.1007/s10201-005-0149-6 [54] BAKER A. Fluorescence excitation - emission matrix characterization of some sewage-impacted rivers[J]. Environmental Science & Technology, 2001, 35(5): 948 − 953. [55] 周慧平, 高燕, 尹爱经. 水污染源解析技术与应用研究进展[J]. 环境保护科学, 2014, 40(6): 19 − 24. doi: 10.3969/j.issn.1004-6216.2014.06.004 [56] BAKER A. Fluorescence excitation - Emission matrix characterization of river waters impacted by a tissue mill effluent[J]. Environmental Science & Technology, 2002, 36(7): 1377 − 1382. [57] BORISOVER M, LAOR Y, SAADI I, et al. Tracing organic footprints from industrial effluent discharge in recalcitrant riverine chromophoric dissolved organic matter[J]. Water Air and Soil Pollution, 2011, 222(1-4): 255 − 269. doi: 10.1007/s11270-011-0821-x [58] NADEN P S, OLD G H, ELIOT-LAIZE C, et al. Assessment of natural fluorescence as a tracer of diffuse agricultural pollution from slurry spreading on intensely-farmed grasslands[J]. Water Research, 2009, 44(6): 1701 − 1712. [59] CARSTEA E M, GHERVASE L, PAVELESCU G, et al. Real-time monitoring of an urban river contaminated with petroleum products[J]. Environmental Engineering and Management Journal, 2012, 11(2): 279 − 283. doi: 10.30638/eemj.2012.035 [60] 杨子臣. 基于三维荧光谱技术的矿物油种类鉴别[D]. 秦皇岛: 燕山大学, 2013. [61] 陈友明. 基于纹理分析的指纹图像预处理算法研究[J]. 电脑知识与技术, 2009, 5(30): 8499 − 8501. [62] 徐梅花. 指纹图像奇异点检测及特征提取算法研究[D]. 太原: 中北大学, 2010. [63] 汤海林. 指纹图像奇异点提取算法的研究与实现[J]. 电脑开发与应用, 2013, 26(7): 7 − 9. doi: 10.3969/j.issn.1003-5850.2013.07.003 [64] 程伟平, 廖锡健. 基于逆向概率密度函数的一维污染源排放重构[J]. 水动力学研究与进展A辑, 2011, 26(4): 460 − 469. doi: 10.3969/j.issn1000-4874.2011.04.010 [65] DATTA B, CHAKRABARTY D, DHAR A. Optimal dynamic monitoring network design and identification of unknown groundwater pollution sources[J]. Water Resources Management, 2009, 23(10): 2031 − 2049. doi: 10.1007/s11269-008-9368-z [66] 朱嵩, 刘国华, 王立忠, 等. 水动力-水质耦合模型污染源识别的贝叶斯方法[J]. 四川大学学报(工程科学版), 2009, 41(5): 30 − 35. doi: 10.15961/j.jsuese.2009.05.003 [67] 王家彪, 雷晓辉, 廖卫红, 等. 基于耦合概率密度方法的河渠突发水污染溯源[J]. 水利学报, 2015, 46(11): 1280 − 1289. doi: 10.13243/j.cnki.slxb.20150405