基于非参数检验和ARIMA 模型的芜湖市空气质量指数研究

Study on Air Quality Index(AQI) of Wuhu City Based on Nonparametric Test and ARIMA Model

在近几年全国空气质量总体有所好转的大环境下,本文通过分析芜湖市空气质量指数数据,探究芜湖市空气质量现状,并构建AQI短期预测模型,为芜湖市政府控制环境污染和有效地治理提供科学的依据。2013年12月1日—2020年10月31日近8年芜湖市空气质量指数(AQI)数据作为研究对象,R语言为实现工具。首先,分析AQI数据曲线图,采用非参数检验Kruskal-Wallis检验比较这8年AQI数据是否具有显著性差异;其次,根据对AQI时间序列平稳性分析结果,选择合理的时间序列模型—ARIMA模型,估计模型参数,建立拟合模型,并评价模型有效性;最后,利用模型预测未来几个月AQI。

In recent years,air conditions nationwide has been improving,through analyzing the air quality index data of Wuhu city,to explore the current situation of air conditions of Wuhu City,and model for AQI prediction,which provides scientific basis for Wuhu city government to control environmental pollution effectively.From December 1,2013 to October 31,2020,air quality Index(AQI)data of Wuhu city in recent 8 years were taken as the research object,and R language was used as the implementation tool.Firstly,the AQI data graph was analyzed,and the kruskal-Wallis test was used to compare the significant differences of the AQI data over the past 8 years.Secondly,according to the stationary analysis of AQI time series,an reasonable time series model--ARIMA model is selected,to estimate fitting model parameters and evaluate the effectiveness of the model.Finally,the ARIMA model is used to predict AQI in the coming months.