基于时间加权回归的郑州市空气质量分析研究  

Analysis of Air Quality in Zhengzhou City Based on Time-weighted Regression

作　　者：王照良[1] 庞飞 WANG Zhaoliang;PANG Fei(School of Mathematics and Information Science,Henan Polytechnic University,Jiaozuo 454000,Henan China)

机构地区：[1]河南理工大学数学与信息科学学院,河南焦作454000

出　　处：《河南科学》2025年第4期567-575,共9页Henan Science

基　　金：教育部人文社会科学研究项目(20YJC910010);河南省测绘科学与技术“双一流”学科创建项目(GCCYJ202428);河南理工大学博士基金(B2020-37)资助。

摘　　要：随着生态文明建设的发展,人们越来越关注生态环境问题,空气质量问题是其中之一。空气质量指数是衡量空气清洁度或污染程度的指标,其综合了多种污染物浓度,如PM_(2.5)、PM_(10)、二氧化硫、二氧化氮等。本研究聚焦于郑州市2021—2023年空气质量指数的变化趋势,采用时间加权回归方法进行了深入分析研究。结果显示,时间加权回归模型比普通多元线性模型效果好,R^(2)为97.78%,MSE为52.54,相对于多元线性回归R^(2)=88.31%有明显提升。郑州市空气质量存在显著的季节性差异,冬季污染较为严重。进一步揭示了空气质量指数与主要污染物浓度、气象因素之间的动态关系,为准确判断空气质量恶化时段及制定针对性的防控措施提供了有力的科学依据。With the development of ecological civilization construction,people pay more and more attention to ecological environment problems,air quality is one of them.The Air Quality Index(AQI)is a measure of air cleanliness or pollution,combining concentrations of pollutants such as PM_(2.5),PM_(10),sulfur dioxide and nitrogen dioxide.This paper focuses on the change trend of air quality index(AQI)in Zhengzhou from 2021 to 2023,and uses time-weighted regression method to conduct in-depth analysis and research.The results show that the time weighted regression model is better than the common multiple linear model,R^(2) is 97.78%,MSE is 52.54,which is higher than the R^(2) of multiple linear regression.There are significant seasonal differences in air quality in Zhengzhou,and the pollution is more serious in winter.The dynamic relationship between air quality index(AQI),concentration of major pollutants and meteorological factors was further revealed,which provided a strong scientific basis for accurately judging the deterioration period of air quality and formulating targeted prevention and control measures.

关 键 词：空气质量指数 时间加权回归 相关系数 多重共线性 污染物 季节性差异 

分 类 号：X51[环境科学与工程—环境工程]