郭骐嘉,姚宜斌,周永江

• 1:武汉大学测绘学院

摘要(Abstract)：

针对PM2.5浓度的预报问题,该文结合国家GNSS服务(IGS)分析中心获取的北京房山站的气象数据及同期的PM2.5实测数据,分析了气象因子和环境污染物因子对PM2.5浓度的影响,并提出了基于随机森林算法的PM2.5浓度预测方法,建立了融合GNSS气象参数的PM2.5随机森林预测模型。实验结果表明:该算法的时效性达6 h,在一定精度范围内能够取得较好的预测效果,同时能够有效地抑制过拟合的现象。

关键词(KeyWords)： GNSS气象参数;PM2.5;随机森林;浓度预测;拟合优度

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41721003,41874033)

作者(Author): 郭骐嘉,姚宜斌,周永江

DOI: 10.16251/j.cnki.1009-2307.2021.04.006

参考文献(References)：

• [1]ZHAO R,GU X X,XUE B,et al.Short period PM2.5prediction based on multivariate linear regression model[J].PloS One,2018,13(7):e0201011．
• [2]KHANIABADI Y O,GOUDARZI G,DARYANOOSH SM,et al.Exposure to PM10,NO2,and O3and impacts on human health[J].Environmental Science and Pollution Research,2017,24:2781-2789．
• [3]TSAI F C,SMITH K R,VICHIT V N,et al.Indoor/outdoor PM10and PM2.5in Bangkok,Thailand[J].Journal of Exposure Analysis and Environmental Epidemiology,2000,10(1):15-26．
• [4]CHEN Yegang.Prediction algorithm of PM2.5 mass concentration based on adaptive BP neural network[J].Computing,2018,100(8):825-838．
• [5]PATERAKI S T,ASIMAKOPOULOS D N,MAGGOS TH.Chemical characterization,sources and potential health risk of PM2.5and PM1pollution across the Greater Athens Area[J].Chemosphere,2020,241:12506．
• [6]CHAK K C,YAO X H.Air pollution in mega cities in China[J].Atmospheric Environment,2008,42(1):1-42．
• [7]ZHOU G,XU J,XIE Y,et al.Numerical air quality forecasting over eastern China:an operational application of WRF-Chem[J].Atmospheric Environment,2017,153:94-108．
• [8]LI R,ZHANG M,CHEN L,et al.CMAQ simulation of atmospheric CO2,concentration in East Asia:comparison with GOSAT observations and ground measurements[J].Atmospheric Environment,2017,160:176-185．
• [9]QIAO T,ZHAO M,XIU G,et al.Simultaneous monitoring and compositions analysis of PM1,and PM2.5in Shanghai:implications for characterization of haze pollution and source apportionment[J].The Science of the Total Environment,2016,557/558:386-394．
• [10]LIU S K,CAI S,CHEN Y,et al.The effect of pollutional haze on pulmonary function[J].Journal of Thoracic Disease,2016,8(1):41-56．
• [11]XIA X,ZHAO W,RUI X,et al.A comprehensive evaluation of air pollution prediction improvement by a machine learning method[C]∥IEEE International Conference on Service Operations and Logistics and Informatics.[S.l.]:IEEE,2016:176-181．
• [12]朱亚杰，李琦，侯俊雄，等．基于支持向量回归的PM2.5浓度实时预报[J]．测绘科学，2016,41(1):12-17.(ZHU Yajie,LI Qi,HOU Junxiong,et al.Real time prediction of PM2.5concentration based on support vector regression algorithms[J].Science of Surveying and Mapping,2016,41(1):12-17．）
• [13]ELBAYOUMI M,RAMLI N A,YUSOF N F F M.Development and comparison of regression models and feedforward backpropagation neural network models to predict seasonal indoor PM2.5-10 and PM2.5concentrations in naturally ventilated schools[J].Atmospheric Pollution Research,2015,6(6):1013-1023．
• [14]MING D,DONG Y,YAN K,et al.PM2.5concentration prediction using hidden semi-Markov model-based times series data mining[J].Expert Systems with Applications,2008,36(5):9046-9055．
• [15]潘文超，郝金明，徐海鑫，等．利用IGS对流层产品预报空气质量指数研究[J]．测绘通报，2016(1):76-79.(PAN Wenchao,HAO Jinming,XU Haixin,et al.Study on forecasting air quality index of tropospheric products using IGS[J].Bulletin of Surveying and Mapping,2016(1):76-79．）
• [16]陈锦超，董雪玲，张婉，等．北京市霾天PM2.5污染特征及其与气象因素的关系[J]．环境科学与技术，2018,41(8):87-94.(CHEN Jinchao,DONG Xueling,ZHANG Wan,et al.PM2.5pollution characteristics and its relationship with meteorological factors in Beijing in haze days[J].Environmental Science and Technology,2018,41(8):87-94．）
• [17]ZHAO Chen,WANG Qing,BAN Jie,et al.Estimating the daily PM2.5concentration in the Beijing-TianjinHebei region using a random forest model with a0.01°×0.01°spatial resolution[J].Environment International,2019,134:105297．
• [18]SINGH K P,GUPTA S,RAI P.Identifying pollution sources and predicting urban air quality using ensemble learning methods[J].Atmospheric Environment,2013,80:426-437．
• [19]GOCHEVA-ILIEVA S G,VOYNIKOVA D S,STOIMENOVAM P,et al.Regression trees modeling of time series for air pollution analysis and forecasting[J].Neural Computing and Applications,2019,31(12):9023-9039．
• [20]KULKARNI G E,MULEY A A,DESHMUKH N K,et al.Autoregressive integrated moving average time series model for forecasting air pollution in Nanded city,Maharashtra,India[J].Modeling Earth Systems and Environment,2018,4(4):1435-1444.