| 1,006 | 7 | 148 |
| 下载次数 | 被引频次 | 阅读次数 |
当前地表水突发性污染事件频发，已造成严重的环境和社会影响，对环境监管部门应急处置能力建设提出了新要求和新挑战。地表水水质在线监测数据具有高频率和高时效等特点，系统论述了基于在线监测时间序列数据的水质预测模型的研究现状和进展，包括数据软测量、预处理方法和水质预测模型等，分析了不同水质预测模型在应用过程中存在的问题，并对未来研究方向进行了展望，以期为水质预测预警和环境监管提供技术支持和方法参考。
Abstract：Sudden pollution incidents in surface water have occurred frequently and caused serious environmental and social impacts, which raised new requirements and challenges towards to environmental supervision departments. Online monitoring data of surface water quality have features of high-frequency and high time-efficiency. The recent research status and progress of water-quality prediction models with online time-series monitoring data were summarized, including data soft measurement, preprocessing methods, and water-quality prediction models. The problems in the practical applications of the relevant water-quality prediction models were analyzed. Also, the future research directions with respect to water-quality prediction are proposed. The aim of this work is to provide reference and technology support for water-quality prediction and warning, and environmental supervision.
[1] YAO H,ZHANG T Z,LIU B,et al.Analysis of surface water pollution accidents in China:characteristics and lessons for risk management [J].Environmental Management,2016,57(4):868-878.
[2] ZHAO Y,PAN Y L,WANG W S,et al.A brain-inspired dynamic environmental emergency response framework for sudden water pollution accidents [J].Water,2021,13(21):3097.
[3] 张丽峰.国家重污染事故频发河流水体污染防治战略研究[D].合肥：合肥工业大学，2012.ZHANG L F.Water pollution prevention strategies for rivers of heavy pollution accident occurred frequently in China [D].Hefei:Hefei University of Technology,2012.
[4] SHI B,WANG P,JIANG J P,et al.Applying high-frequency surrogate measurements and a wavelet-ANN model to provide early warnings of rapid surface water quality anomalies [J].Science of the Total Environment,2018,610/611:1390-1399.
[5] 张迪，嵇晓燕，宫正宇，等.滇池流域水环境综合管理技术支撑平台构建研究[J].中国环境监测，2016,32(6):118-122.ZHANG D,JI X Y,GONG Z Y,et al.Construction of technical support platform for integrated management of water environment in Dianchi River Basin [J].Environmental Monitoring in China,2016,32(6):118-122.
[6] 杨宇锋，武暕，王璐，等.基于随机森林模型的辽河高时间分辨率氮、磷浓度模拟与预测[J].环境科学学报，2022,42(12):384-391.YANG Y F,WU J,WANG L,et al.Simulation and prediction of nitrogen and phosphorus concentrations with high time resolution in Liao River using random forest model [J].Acta Scientiae Circumstantiae,2022,42(12):384-391.
[7] 柳维，杨维.水质自动监测系统在水环境监测中的应用[J].中国资源综合利用，2022,40(10):46-48.LIU W,YANG W.Application of water quality automatic monitoring system in water environment monitoring [J].China Resources Comprehensive Utilization,2022,40(10):46-48.
[8] 张梦迪，徐庆，马春燕，等.基于在线监测数据的水质预测及异常识别方法研究进展 [C]//第十八届长三角科技论坛环境保护分论坛(上海市环境科学学会2021年学术年会)暨上海市环境科学学会第八届会员代表大会论文集.上海，2021:77-85.ZHANG M D,XU Q,MA C Y,et al.Research progress on water quality prediction and anomaly identification methods based on online monitoring data [C] // Proceedings of the 18th Yangtze River Delta Science and Technology Forum on Environmental Protection and the Eighth General Meeting of the Shanghai Society of Environmental Science.2021:77-85.
[9] 陈美璘，何清龙.基于熵权法混合模型的贵州省旅游人数预测研究[J].数学的实践与认识，2018,48(21):307-313.CHEN M L,HE Q L.The forecast of tourists in Guizhou province based on entropy-weighted mixed model [J].Mathematics in Practice and Theory,2018,48(21):307-313.
[10] WANG Q,WANG L L.The nonlinear effects of population aging,industrial structure,and urbanization on carbon emissions:a panel threshold regression analysis of 137 countries [J].Journal of Cleaner Production,2021,287:125381.
[11] SHYTI B,VALERA D.The regression model for the statistical analysis of Albanian economy [J].International Journal of Mathematics Trends and Technology,2018,62(2):90-96.
[12] 唐亦舜，徐庆，刘振鸿，等.基于优化非线性自回归神经网络模型的水质预测[J].东华大学学报(自然科学版),2022,48(3):93-100.TANG Y S,XU Q,LIU Z H,et al.Prediction of water quality based on the optimized nonlinear auto-regressive neural network model [J].Journal of Donghua University (Natural Science),2022,48(3):93-100.
[13] 周添一，徐庆，刘振鸿，等.优化NARX神经网络对时间序列溶解氧的预测[J].东华大学学报(自然科学版),2022,48(2):105-110.ZHOU T Y,XU Q,LIU Z H,et al.Time-series dissolved oxygen prediction based on optimized NARX neural network [J].Journal of Donghua University (Natural Science),2022,48(2):105-110.
[14] CHEN Y Y,SONG L H,LIU Y Q,et al.A review of the artificial neural network models for water quality prediction [J].Applied Sciences,2020,10(17):5776.
[15] 周添一.基于在线数据的水质时间序列预测及叶绿素a软测量的研究[D].上海：东华大学，2022.ZHOU T Y.Research of water quality time series prediction and the soft measurement of chlorophyll a based on online data [D].Shanghai:Donghua University,2022.
[16] 张梦秋.基于软测量的污水水质预测系统[D].兰州：西北师范大学，2016.ZHANG M Q.Wastewater quality prediction system based on soft sensor [D].Lanzhou:Northwest Normal University,2016.
[17] 李俊.城镇污水处理厂污水氨氮和运营能耗的软测量模型研究[D].广州：广东工业大学，2018.LI J.Study on soft-measurement model of ammonia-nitrogen and operational energy consumption in urban sewage treatment plant [D].Guangzhou:Guangdong University of Technology,2018.
[18] 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.SHI B.The study on dynamic warning and monitoring modeling for water pollution and risk analysis for emergency disposal project [D].Harbin:Harbin Institute of Technology,2018.
[19] 琚振闯，王晓，弓艳霞.基于BP神经网络的黄河水质预测研究[J].青海大学学报，2017,35(3):88-92.JU Z C,WANG X,GONG Y X.Prediction of water quality in Yellow River based on BP neural network model [J].Journal of Qinghai University,2017,35(3):88-92.
[20] 袁梅雪，魏守科，孙铭，等.基于小波去噪和LSTM的Seq2Seq水质预测模型[J].计算机系统应用，2022,31(6):38-47.YUAN M X,WEI S K,SUN M,et al.Seq2Seq water quality prediction model based on wavelet denoising and LSTM [J].Computer Systems & Applications,2022,31(6):38-47.
[21] 秦文虎，付亚涛.基于向量自回归模型的水质异常检测研究[J].安全与环境学报，2018,18(4):1560-1563.QIN W H,FU Y T.Water quality abnormity inspection and detection via the vector auto-regressive model [J].Journal of Safety and Environment,2018,18(4):1560-1563.
[22] LIU C L,PAN C Z,CHANG Y W,et al.An integrated autoregressive model for predicting water quality dynamics and its application in Yongding River [J].Ecological Indicators,2021,133:108354.
[23] 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.ZHU W Y,SHI B,JIANG J P,et al.Dynamic early warning method based on abnormal detection of water quality time series [J].Environmental Science & Technology,2018,41(12):131-137.
[24] 王丙参，夏鸿鸣，何万生.基于AR(p)模型的渭河水质预测[J].宜宾学院学报，2011,11(12):13-15.WANG B C,XIA H M,HE W S.The prediction of water quality based on AR(p) model in Weihe,Tianshui Reach [J].Journal of Yibin University,2011,11(12):13-15.
[25] 黄玥，黄志霖，肖文发，等.三峡水库蓄水运行后入出库断面水质评价与预测[J].环境污染与防治，2019,41(2):211-215.HUANG Y,HUANG Z L,XIAO W F,et al.Water quality evaluation and prediction of the reservoir inflow and outflow after the Three Gorges Project operation [J].Environmental Pollution & Control,2019,41(2):211-215.
[26] 陈青松.青衣江水质分析方法研究[D].成都：西南交通大学，2018.CHEN Q.Study on water quality analysis method of Qingyi River [D].Chengdu:Southwest Jiaotong University,2018.
[27] 董国庆，孙伯寅，李峥，等.时间序列模型在水源水化学耗氧量预测中的应用[J].环境与健康杂志，2018,35(3):234-237.DONG G Q,SUN B Y,LI Z,et al.Application of time series model in prediction of chemical oxygen demand of source water [J].Journal of Environment and Health,2018,35(3):234-237.
[28] 吕昌涛，赖华.基于ARMA模型的自来水厂原水水质短期预报[J].工业仪表与自动化装置，2016(2):98-101.LYU C T,LAI H.Short-term forecast for source water quality of water plant based on ARMA model [J].Industrial Instrumentation & Automation,2016(2):98-101.
[29] 王晓鹏.河流水质模拟预测的统计建模研究：以湟水河小峡桥断面为例[J].青海师范大学学报(自然科学版),2015,31(4):1-5.WANG X P.Study on simulation and prediction statistical modeling of river water quality—taking Xiaoxia Bridge section of the Huangshui River Basin as example [J].Journal of Qinghai Normal University (Natural Science),2015,31(4):1-5.
[30] 陈能汪，余镒琦，陈纪新，等.人工神经网络模型在水质预警中的应用研究进展[J].环境科学学报，2021,41(12):4771-4782.CHEN N W,YU Y Q,CHEN J X,et al.Artificial neural network models for water quality early warning:a review [J].Acta Scientiae Circumstantiae,2021,41(12):4771-4782.
[31] 王佳楠.基于BP神经网络的高锰酸盐指数预测研究：以渭南潼关吊桥段为例[D].西安：长安大学，2017.WANG J N.Prediction of permanganate index based on BP neural network:a case study of Tongguan drawbridge area in Weinan City[D].Xi’an:Chang’an University,2017.
[32] 刘品.BP神经网络结构优化研究及应用[D].北京：中国地质大学(北京),2016.LIU P.The BP neural network structure optimization research and application [D].Beijing:China University of Geosciences (Beijing),2016.
[33] YAN J Z,XU Z B,YU Y C,et al.Application of a hybrid optimized BP network model to estimate water quality parameters of Beihai Lake in Beijing [J].Applied Sciences,2019,9(9):1863.
[34] 刘洁，祝榕婕，姜德迅，等.基于遗传-神经网络的实时水质预测模型[J].南水北调与水利科技(中英文),2020,18(6):93-100.LIU J,ZHU R J,JIANG D X,et al.Real-time water quality prediction model based on IGA-BPNN method [J].South-to-North Water Transfers and Water Science & Technology,2020,18(6):93-100.
[35] 张梦迪，徐庆，刘振鸿，等.基于动态滑动窗口BP神经网络的水质时间序列预测[J].环境工程技术学报，2022,12(3):809-815.ZHANG M D,XU Q,LIU Z H,et al.Prediction of water quality time series based on the dynamic sliding window BP neural network model [J].Journal of Environmental Engineering Technology,2022,12(3):809-815.
[36] 雷腾.基于神经网络水质预测模型[D].海口：海南大学，2015.LEI T.Based on the neural network model to predict water quality [D].Haikou:Hainan University,2015.
[37] HOCHREITER S,SCHMIDHUBER J.Long short-term memory [J].Neural Computation,1997,9(8):1735-1780.
[38] 杜爽，徐展琦，马涛，等.基于神经网络模型的网络流量预测综述[J].无线电通信技术，2020,46(2):216-222.DU S,XU Z Q,MA T,et al.A survey of network traffic prediction based on neural network models [J].Radio Communications Technology,2020,46(2):216-222.
[39] 秦文虎，陈溪莹.基于长短时记忆网络的水质预测模型研究[J].安全与环境学报，2020,20(1):328-334.QIN W H,CHEN X Y.Water quality forecast and prediction model based on long-and short-term memory network [J].Journal of Safety and Environment,2020,20(1):328-334.
[40] 孙开争，刘杨，姜腾龙，等.城市河流水质预测的LSTM方法适用性研究[J].河北环境工程学院学报，2022,32(6):78-82.SUN K Z,LIU Y,JIANG T L,et al.Study on applicability of LSTM prediction methods on urban river water quality [J].Journal of Hebei University of Environmental Engineering,2022,32(6):78-82.
[41] 王嫄嫄.基于LSTM的水质预测方法研究[D].南京：南京邮电大学，2019.WANG Y Y.Research of water quality prediction methods based on LSTM [D].Nanjing:Nanjing University of Posts and Telecommunications,2019.
基本信息:
DOI：10.19886/j.cnki.dhdz.2022.0483
中图分类号:X52
引用信息:
[1]秦艳,徐庆,陈晓倩,等.基于在线监测时间序列数据的水质预测模型研究进展[J].东华大学学报(自然科学版),2024,50(03):116-122.DOI:10.19886/j.cnki.dhdz.2022.0483.
基金信息:
上海市生态环境局科研项目(沪环科[2020]第51号)