基于网络搜索信息的农村水环境质量灰色预测模型

doi:10.16381/j.cnki.issn1003-207x.2020.06.021

摘要/Abstract

摘要： 针对农村水环境直接监测数据相对缺乏、间接数据难以有效引入的问题，综合灰色关联分析和预测模型，提出一种基于网络搜索信息的农村水环境质量灰色预测模型。首先，综合考虑数据重要性和可获得性，确定农村水环境相关的搜索关键词清单；然后，采用主成分分析法提取搜索关键词的主要特征，构建初始网络搜索变量，并利用灰色绝对关联度衡量各初始网络搜索变量与水环境质量之间的关联程度。在此基础上，构建不同频率数据的多变量离散灰色模型，将强关联变量的降频数据作为多变量离散灰色模型的驱动因素，从而构建基于网络搜索信息的农村水环境质灰色预测模型。实例分析结果表明，相对于传统灰色模型，引入网络搜索信息可以提高农村水环境预测精度，为农村水环境治理提供决策支持。

关键词: 农村水环境, 网络搜索信息, 绝对关联度, 灰色模型, 多变量

Abstract: Water quality prediction is one of the key points in the prevention and control of rural water pollution. However, rural water environment lacks direct monitoring data, and non-direct data is difficult to introduce as variable effectively. A grey forecasting model of rural water environment quality based on online searching information is proposed by integrating grey incidence and prediction model. First, the relationship between rural water quality and online searching information is theorically analyzed, and demonstrated by the online searching data of Lanzhou water pollution event in 2014. Secondly, an initial list of searching keywords associated with rural water environment is collected according to Pressure-State-Response model. Then, by comprehensively contemplating importance and availability of the data, a final list of searching key words is determined. Furthermore, the main features of searching keywords are extracted to construct initial online searching variables by principal component analysis. Thirdly, utilizing grey absolute incidence to evaluate degree of association between each online searching variable and water environment quality. Fourthly, a new multivariable discrete grey forecasting model for different frequency data is proposed. Consequently, strongly associated variables are selected as driving factors of proposed model to construct rural water environment quality model. In case analysis, the data of the Chemical Oxygen Demand (COD) in Wuzhou, Guangxi Zhuang Autonomous Region is collected for 15 weeks. The proposed model is applied to forecast the COD with introducing the internet searching information. The performance of the model is compared with traditional grey forecasting model. The results show that introducing online searching information can significantly improve the accuracy of grey forecasting model of rural water environment quality. This study can provide decision support for rural water environment management. Meanwhile, a new approach for prediction of rural water environment is established.

Key words: rural water environment, online searching information, absolute degree of incidence, grey model, multi-variables

中图分类号:

X321

张可, 钟秋萍, 曲品品, 殷要, 左媛. 基于网络搜索信息的农村水环境质量灰色预测模型[J]. 中国管理科学, 2020, 28(6): 222-230.

ZHANG Ke, ZHONG Qiu-ping, QU Pin-pin, YIN Yao, ZUO Yuan. Grey Forecasting Model of Rural Water Environment Quality Based on Online Searching Information[J]. Chinese Journal of Management Science, 2020, 28(6): 222-230.

参考文献

[1] 张晓. 中国水污染趋势与治理制度[J]. 中国软科学, 2014,29(10):11-24.
[2] Sinshaw T A, Surbeck C Q, Yasarer H, et al. Artificial neural network for prediction of total nitrogen and phosphorus in US lakes[J]. Journal of Environmental Engineering, 2019, 145(6):112-125.
[3] Ruben G B, Zhang Ke, Bao Hongjun, et al. Application and sensitivity analysis of artificial neural network for prediction of chemical oxygen demand[J]. Water Resources Management, 2017, 32(1):1-11.
[4] 王小焕,邵景安,王金亮,等. 三峡库区长江干流入出库水质评价及其变化趋势[J]. 环境科学学报, 2017, 37(2):554-565.
[5] Thoe W, Lee J H. Daily forecasting of Hong Kong beach water quality by multiple linear regression models[J]. Journal of Environmental Engineering, 2014, 140(2):1-11.
[6] Patki V K, Shrihari S, Manu B, et al. Fuzzy system modeling for forecasting water quality index in municipal distribution system[J]. Urban Water Journal, 2015, 12(2):89-110.
[7] Nemtinov V A, Nemtinova Y V, Borisenko A B, et al. Construction of concentration fields of elements in 3D in groundwater of an industrial hub using GIS technologies[J]. Journal of Geochemical Exploration, 2014, 147(2):46-51.
[8] 樊敏,顾兆林. 非机理性水质模型研究综述[J]. 环境科学与管理, 2009, 36(9):63-67.
[9] 李娜,王腊春,谢刚,等. 山东省辖淮河流域河流水质趋势的灰色预测[J]. 环境科学与技术, 2012, 35(2):195-199.
[10] Ali G, Ashraf A, Bashir M K, et al. Exploring environmental Kuznets curve (EKC) in relation to green revolution:A case study of Pakistan[J]. Environmental Science & Policy, 2017, 77(11):166-171.
[11] Alamdarlo H N. The economic impact of agricultural pollutions in Iran, spatial distance function approach[J]. Science of the Total Environment, 2018, 616-617:1656-1663.
[12] Udeigwe T, Teboh J, Eze P, et al. Implications of leading crop production practices on environmental quality and human health[J]. Journal of Environmental Management, 2015, 151(3):267-279.
[13] 张可,马成文,丰景春,等. 基于离散灰色模型的农村水环境政策减排效应及其空间分异性研究[J]. 中国管理科学, 2017, 25(5):157-166.
[14] 徐玉妃,杨昆,罗毅,等. 滇池草海水质等级预测模型研究[J]. 水生态学杂志, 2018, 39(1):1-8.
[15] Lee J. Applying grey theory in predicting the arsenic contamination of groundwater in historical blackfoot disease territory[C]//2013 Ninth International Conference on Natural Computation (ICNC), Shenyang, China, 2013:1124-1128.
[16] Li Zhenbo, Jiang Yu, Yue Jun, et al. An improved gray model for aquaculture water quality prediction[J]. Intelligent Automation & Soft Computing, 2012, 18(5):11.
[17] 刘东君,邹志红. 灰色和神经网络组合模型在水质预测中的应用[J]. 系统工程, 2011, 29(9):105-109.
[18] Luo Yi, Yang Kun, Yu Zhenyu, et al. Dynamic monitoring and prediction of Dianchi Lake cyanobacteria outbreaks in the context of rapid urbanization[J]. Environmental Science & Pollution Research, 2017, 24(6):5335-5348.
[19] 刘秀丽,涂卓卓. 水环境安全评价方法及其在京津冀地区的应用[J]. 中国管理科学, 2018, 26(3):160-168.
[20] 钟文武,李光华,罗永新,等. Markov灰色残差GM(1,1)模型在滇池观音山断面水质预测中的应用研究[J]. 环境科学与管理, 2016, 41(11):80-84.
[21] 于慧,孙宝盛,李亚楠,等. 应用灰色模糊马尔科夫链预测海河水质变化趋势[J]. 中国环境科学, 2014, 34(3):810-816.
[22] 徐梅,晏福,刘振忠,等. 灰色GM(1,1)-小波变换-GARCH组合模型预测松花江流域水质[J]. 农业工程学报, 2016, 32(10):137-142.
[23] 刘东君,邹志红. 最优加权组合预测法在水质预测中的应用研究[J]. 环境科学学报, 2012, 32(12):3128-3132.
[24] Polgreen P M, Chen Y, Pennock D M, et al. Using internet searches for influenza surveillance[J]. Clinical Infectious Diseases, 2008, 47(11):1443-1448.
[25] Ginsberg J, Mohebbi M H, Patel R S, et al. Detecting influenza epidemics using search engine query data[J]. Nature, 2009, 457:1012-1014.
[26] Fantazzini D, Toktamysova Z. Forecasting volatility with empirical similarity and Google Trends[J]. International Journal of Production Economics, 2015, 170:97-135.
[27] Clark M, Wilkins E J, Dagan D T, et al. Bringing forecasting into the future:Using Google to predict visitation in US national parks[J]. Journal of Environmental Management, 2019, 243:88-94.
[28] Papanagnou C I, Matthews-Amune O. Coping with demand volatility in retail pharmacies with the aid of big data exploration[J]. Computers & Operations Research, 2018, 98(10):343-354.
[29] 蒋翠清,王睿雅,丁勇. 融入软信息的P2P网络借贷违约预测方法[J]. 中国管理科学, 2017, 25(11):12-21.
[30] 王娜. 基于大数据的碳价预测[J]. 统计研究, 2016, 34(11):56-62.
[31] 俞庆进,张兵. 投资者有限关注与股票收益——以百度指数作为关注度的一项实证研究[J]. 金融研究, 2012, 24(8):152-165.
[32] 董倩,孙娜娜,李伟. 基于网络搜索数据的房地产价格预测[J]. 统计研究,2014,32(10):81-88.
[33] 徐映梅,高一铭. 基于互联网大数据的CPI舆情指数构建与应用——以百度指数为例[J]. 数量经济技术经济研究, 2017, 34(1):94-112.
[34] 宋国君,朱璇. 基于问卷调查的淮河水环境状况评估[J]. 环境污染与防治, 2013,35(2):93-98.
[35] 甘利人,李恒. 科技用户信息搜寻过程中的问题解决机制解释[J]. 情报学报, 2006, 25(4):441-450.
[36] Liu Sifeng, Lin Yi. Grey information theory and practical applications[M]. London:Springer, 2011.
[37] 张可. 基于驱动控制的多变量离散灰色模型[J]. 系统工程理论与实践, 2014, 34(8):2084-2091.