郑州市PM_(2.5)浓度时空分布特征及预测模型研究

科研成果详情

题名	郑州市PM_(2.5)浓度时空分布特征及预测模型研究
其他题名	Study on Spatiotemporal Variability of PM_(2.5) Concentrations and Prediction Model over Zhengzhou City
作者	陈强; 梅琨; 朱慧敏; 蔡贤雷; 张明华
发表日期	2015
发表期刊	中国环境监测影响因子和分区
语种	中文
原始文献类型	期刊论文
关键词	PM_(2.5) 预测模拟 BP-ANN模型多元线性回归模型 GIS 郑州地区
摘要	利用统计学原理和GIS技术,对郑州市2013年8月17—12月31日期间PM_(2.5)浓度时空分布特征进行分析,同时结合气象资料与前一日污染数据,建立人工神经网络反向传播算法模型(BP-ANN)和多元线性回归模型用于该市细颗粒物污染的短期预测。结果表明,郑州市PM_(2.5)浓度日变化呈单峰模式,随逆温现象的发生和交通的密集于上午11: 00达到峰值,午后逐步下降。在工作日、周末与国庆节的对比中,国庆节期间颗粒物污染浓度高出平日32.8%,表明人为活动的加剧影响PM_(2.5)的排放; 周末与工作日期间无显著差异。在空间分布上,金水区、管城回族区污染最为严重,工业燃煤、地铁施工等源排放是造成污染的主要原因; 位于远郊的岗里水库,受秸秆焚烧和市区污染输送等影响,PM_(2.5)浓度亦维持较高水平。最后,研究将所构建的BP-ANN预测模型和多元线性回归模型对比,结果发现两模型在建模阶段预测值与真实值的拟合一致性指标分别为0.944、0.918,均方根误差分别为59.788、70.611; 验证阶段拟合一致性指标分别为0.854、0.794,平均绝对误差分别为25.298、32.775,表明BP-ANN模型在预测郑州市PM_(2.5)污染过程中更具优势。
其他摘要	This paper is to identify the spatial and temporal patterns of PM_(2.5) concentrations and then attempt to model its distributions using Zhengzhou as an example. The spatial and temporal distributions of PM_(2.5) concentrations were analyzed using statistics theory and Geographic Information System (GIS)technology,from 17 August 2013 to 31 December 2013. Significant diurnal variations of PM_(2.5) concentrations were observed and showed a unimodal pattern with one marked peak at 11: 00,due to the temperature inversion and dense traffic,and a declined trend in the afternoon. On National Day,particulate matter concentrations were found 32. 8% higher than usual,suggesting the influence of intensification of anthropogenic activities on PM_(2.5) emissions; there was no significant difference between weekends and weekdays. The spatial distribution of PM_(2.5) concentration presented a severe pollution level both in Guancheng Hui District and Jinshui District,mainly due to the pollution source-emission such as fire coal and subway construction; High concentration of PM_(2.5) was also observed in Gangli Reservoir station which located in suburban area,due to external sources transport and the effect of straw burning. Finally,a back-propagation artificial neural network model (BP-ANN)and a multiple linear regression model were established and compared combined with meteorological data for a shortterm estimation of fine particle pollution. The index of agreement of the two models’predicted and observed value in the modeling phase were 0. 944,0. 918,root mean square error were 59. 788,70. 611,respectively; in the validation phase the index of agreement were 0. 854,0. 794,mean absolute error were 25. 298,32. 775,respectively,which indicating that BP-ANN model has more advantages in predicting the process of PM_(2.5) pollution in Zhengzhou City.
ISSN	1002-6002
卷号	31 期号:3 页码:105-112
收录类别	CSCD ; 维普
学科领域	环境质量评价与环境监测
URL	查看原文
CSCD记录号	CSCD:5473060
引用统计
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/98700
专题	公共卫生学院_水环境应用技术研究所
作者单位	温州医科大学水环境应用技术研究所, 浙江, 温州, 325035
第一作者单位	温州医科大学
第一作者的第一单位	温州医科大学
推荐引用方式 GB/T 7714	陈强,梅琨,朱慧敏,等. 郑州市PM_(2.5)浓度时空分布特征及预测模型研究[J]. 中国环境监测,2015,31(3):105-112.
APA	陈强, 梅琨, 朱慧敏, 蔡贤雷, & 张明华. (2015). 郑州市PM_(2.5)浓度时空分布特征及预测模型研究. 中国环境监测, 31(3), 105-112.
MLA	陈强,et al."郑州市PM_(2.5)浓度时空分布特征及预测模型研究".中国环境监测 31.3(2015):105-112.