|
|
- 2017
基于ARMAX的PM2.5小时浓度跟踪预测模型
|
Abstract:
针对目前缺乏小时尺度上PM2.5浓度统计预测模型以及已有模型预测精度对训练数据的依赖问题, 利用天津市环保物联网监测到的污染物及气象数据, 建立了PM2.5小时浓度预测的多元时间序列模型(ARMAX), 并提出一种模型在线自适应改进方法：设定模型评价指标并实时监测, 当模型预测精度超标时对模型进行在线更新．将改进后的模型应用于天津市的9个监测站点, 用2013―2014年的监测数据对模型进行验证．结果表明：模型均方根误差RMSE＜20 μg, 平均绝对误差MAE＜20 μg, 拟合优度R2＞0.9, 能够在小时尺度下有效地预测PM2.5浓度, 可以为突发性PM2.5污染事件的应急处理提供决策支持．
To solve the lack of statistical prediction model in hourly scale for PM2.5 concentration and the training data dependence of the existing model，a multivariate time series model ARMAX was established. The pollutants and meteorological data monitored by Internet of Things for Environmental Protection in Tianjin were used to establish the model. An online adaptive improved method was proposed，in which three model evaluations were set and monitored online，the model was updated when prediction accuracy was reduced to an extent. The improved prediction model was applied to nine monitoring sites in Tianjin，and the data of 2013―2014 was used to validate the model. Results showed that with the model root mean square error RMSE＜20 μg，the mean absolute error MAE＜20 μg，and the goodness of fit R2＞0.9，the model can predict the next hourly scale PM2.5 concentration effectively，which can provide a decision support for the emergency treatment of PM2.5 pollution incidents
| [1] | Xiao S, Wang Q Y, Cao J J, et al. Long-term trends in visibility and impacts of aerosol composition on visibility impairment in Baoji, China[J]. <i>Atmospheric Research</i>, 2014, 149(6):88-95. |
| [2] | 陈义珍, 赵丹, 柴发合, 等. 广州市与北京市大气能见度与颗粒物质量浓度的关系[J]. 中国环境科学, 2010, 30(7):967-971. |
| [3] | Shorshani M F, Seigneur C, Rehn L P, et al. Atmospheric dispersion modeling near a roadway under calm meteorological conditions[J]. <i>Transportation Research Part D</i>:<i>Transport and Environment</i>, 2015, 34:137-154. |
| [4] | Cobourn W G. An enhanced PM<sub>2.5</sub> air quality forecast model based on nonlinear regression and back-trajectory concentrations[J]. <i>Atmospheric Environment</i>, 2010, 44(25):3015-3023. |
| [5] | Sun W, Zhang H, Palazoglu A, et al. Prediction of 24-hour-average PM<sub>2.5</sub> concentrations using a hidden Markov model with different emission distributions in Northern California[J]. <i>Science of the Total Environment</i>, 2013, 443:93-103. |
| [6] | Chen Y, Shi R, Shu S, et al. Ensemble and enhanced PM<sub>10</sub> concentration forecast model based on stepwise regression and wavelet analysis[J]. <i>Atmospheric Environment</i>, 2013, 74:346-359. |
| [7] | Zou B, Wang M, Wan N, et al. Spatial modeling of PM<sub>2.5</sub> concentrations with a multifactoral radial basis function neural network[J]. <i>Environmental Science and Pollution Research</i>, 2015, 22(14):10395-10404. |
| [8] | 王轩, 陈建华, 耿春梅, 等. 北京冬季气溶胶吸湿性的观测与分析[J]. 中国科学院研究生院学报, 2014, 31(3):322-328. |
| [9] | Wang Xuan, Chen Jianhua, Geng Chunmei, et al. Hygroscopic properties of the ambient aerosols observed in winter in Beijing[J]. <i>Journal of University of Chinese Academy of Sciences</i>, 2014, 31(3):322-328(in Chinese). |
| [10] | Chen Guanyi, Zhang Wen, Hou Li’an, et al. Pollution characteristics and influence factors of PM<sub>2.5</sub> in summer in Jixian County of Tianjin[J]. <i>Journal of Tianjin University</i>:<i>Science and Technology</i>, 2015, 48(2):95-102(in Chinese). |
| [11] | 王志娟, 韩力慧, 陈旭锋, 等. 北京典型污染过程PM<sub>2.5</sub>的特性和来源[J]. 安全与环境学报, 2012, 12(5):122-126. |
| [12] | Wang Zhijuan, Han Lihui, Chen Xufeng, et al. Characteristics and sources of PM<sub>2.5</sub> in typical atmospheric pollution episodes in Beijing[J]. <i>Journal of Safety and Environment</i>, 2012, 12(5):122-126(in Chinese). |
| [13] | 郑冬, 李丹, 纪德钰, 等. 大连市区近地面臭氧污染规律研究及与 PM<sub>2.5</sub> 等污染物的相关性分析[J]. 环境与可持续发展, 2014(6):177-180. |
| [14] | Zheng Dong, Li Dan, Ji Deyu, et al. Study on ozone in Dalian urban and correlation between ozone and PM<sub>2.5</sub>, other pollutants[J]. <i>Environment and Sustainable Development</i>, 2014(6):177-180(in Chinese). |
| [15] | Tao M, Chen L, Wang Z, et al. A study of urban pollution and haze clouds over northern China during the dusty season based on satellite and surface observations [J]. <i>Atmospheric Environment</i>, 2014, 82(5):183-192. |
| [16] | Chen Yizhen, Zhao Dan, Chai Fahe, et al. Correlation between the atmospheric visibility and aerosol fine particle concentrations in Guangzhou and Beijing[J]. <i>China Environmental Science</i>, 2010, 30(7):967-971(in Chinese). |
| [17] | Raaschou-Nielsen O, Andersen Z J, Beelen R, et al. Air pollution and lung cancer incidence in 17 European cohorts:Prospective analyses from the European study of cohorts for air pollution effects(ESCAPE)[J]. <i>The Lancet Oncology</i>, 2013, 14(9):813-822. |
| [18] | Cao J, Xu H, Xu Q, et al. Fine particulate matter constituents and cardiopulmonary mortality in a heavily polluted Chinese city[J]. <i>Environmental Health Perspectives</i>, 2012, 120(3):373-378. |
| [19] | Evans J, van Donkelaar A, Martin R V, et al. Estimates of global mortality attributable to particulate air pollution using satellite imagery[J]. <i>Environmental Research</i>, 2013, 120(1):33-42. |
| [20] | 薛文博, 王金南, 杨金田, 等. 国内外空气质量模型研究进展[J]. 环境与可持续发展, 2013(3):14-20. |
| [21] | 魏薇, 傅丽芳. 基于改进高斯模型的哈尔滨市PM<sub>2.5</sub>扩散问题实证分析[J]. 数学的实践与认识, 2014, 44(22):205-211. |
| [22] | Wei Wei, Fu Lifang. An empirical study on the problem of diffusion based on the improved Gauss model in Harbin city[J]. <i>Mathematics in Practice and Theory</i>, 2014, 44(22):205-211(in Chinese). |
| [23] | Riccio A, Chianese E, Agrillo G, et al. Source apportion of atmospheric particulate matter:A joint Eulerian/Lagrangian approach[J]. <i>Environmental Science and Pollution Research</i>, 2014, 21(23):13160-13168. |
| [24] | Fann N, Lamson A D, Anenberg S C, et al. Estimating the national public health burden associated with exposure to ambient PM<sub>2.5</sub> and ozone[J]. <i>Risk Analysis</i>, 2012, 32(1):81-95. |
| [25] | Djalalova I, Delle Monache L, Wilczak J. PM<sub>2. 5</sub> analog forecast and Kalman filter post-processing for the community multiscale air quality(CMAQ)model[J]. <i>Atmospheric Environment</i>, 2015, 108:76-87. |
| [26] | Solazzo E, Bianconi R, Pirovano G, et al. Operational model evaluation for particulate matter in Europe and North America in the context of AQMEII[J]. <i>Atmospheric Environment</i>, 2012, 53:75-92. |
| [27] | Voukantsis D, Karatzas K, Kukkonen J, et al. Intercomparison of air quality data using principal component analysis, and forecasting of PM<sub>10</sub> and PM<sub>2.5</sub> concentrations using artificial neural networks, in Thessaloniki and Helsinki[J]. <i>Science of the Total Environment</i>, 2011, 409(7):1266-1276. |
| [28] | Dimitriou K, Kassomenos P. A study on the reconstitution of daily PM<sub>10 </sub>and PM<sub>2.5</sub> levels in Paris with a multivariate linear regression model[J]. <i>Atmospheric Environment</i>, 2014, 98:648-654. |
| [29] | 陈冠益, 张雯, 侯立安, 等. 天津蓟县夏季PM<sub>2.5</sub>污染特征及影响因素[J]. 天津大学学报:自然科学与工程技术版, 2015, 48(2):95-102. |
| [30] | Xue Wenbo, Wang Jinnan, Yang Jintian, et al. Domestic and foreign research progress of air quality model [J]. <i>Environment and Sustainable Development</i>, 2013(3):14-20(in Chinese). |
