一种新的雾霾天气下PM2.5浓度短时预测模型

A New Short-term Prediction Model of PM2.5 in Haze Weather

大气污染一直是影响人们生活质量的主要因素之一,针对山东省临沂市2018—2019年空气质量情况,采用小波变换DB5(Daubechies 5)的尺度系数A4对临沂市的细颗粒物(Fine Particulate Matter,PM2.5)浓度、天顶总延迟量(Zenith Total Delay,ZTD)、大气可降水量(Precipitable Water Vapar,PWV)和NO 2浓度进行分解与重构,然后利用多元线性回归方法建立适合临沂地区的雾霾天气下短时预报模型,重构后的PM2.5浓度与NO 2浓度相关系数、PM2.5与PWV相关系数较原始序列分别提高了20.46%,25.48%,重构后的模型决定系数R 2、F检验、F检验对应的P值,剩余平方和S 2较原始模型分别提高了29.86%,18.89%,0,72.72%。因此建立临沂地区雾霾天气下短时PM2.5预报模型可以有效地进行PM2.5监测,对雾霾治理提供一定的技术支持。

Air pollution has been one of the main factors influencing the quality of people's life.In terms of air quality condition of Shandong province in 2018—2019,fine particulate matter(fine particulate matter,PM2.5)concentration,amount of Zenith Total Delay(Zenith Total Delay,ZTD),atmospheric precipitation(Precipitable Water Vapar,PWV)and NO 2 concentration of Linyiwere decomposed and reconstructed using the wavelet transform coefficient of the scale of the DB5 A4.Then,multiple linear regression method was appliedto establish a short-time forecast model that was suitable for Linyi region in haze weather.The reconstructed correlation coefficient of PM2.5 and NO 2 and the correlation coefficient of PM2.5 and PWV increased by 20.46%and 25.48%respectively compared with the original sequence.The reconstructed model R 2,F and P and S 2 increased by 29.86%,18.89%and 0,72.72%respectively compared with the original model.Therefore,the establishment of short-term PM2.5 forecast model under haze weather in Linyi area couldeffectively monitor PM2.5 and provide some technical support for haze control.