基于多元线性回归方程安顺市四季AQI预报模型的建立与效果评估

Establishment and effect evaluation of AQI prediction model for Anshun based on multiple linear regression equation

对安顺市2015—2019年包括日平均气温、平均相对湿度、平均本站气压、日照时数等18个地面气象观测要素和污染累积基础(前一日AQI值)与当日AQI作相关性分析,选用强相关因子建立四季多元线性逐步回归模型,运用等级评分、准确率、标准化平均误差(NME)等6种参数对4个模型预报效果进行评估。得出以下主要结论:四季AQI与气象要素值均表现出明显相关关系,春、夏季预报效果优于秋、冬季,四季AQI预报模型均可以满足实际运用需求。

Correlation analysis was conducted for 18 meteorological observation elements,including daily average temperature,average relative humidity,average atmospheric pressure,sunshine duration,and pollution accumulation basis(AQI of the previous day)and AQI of the current day in Anshun from 2015 to 2019,and a multiple linear regression model was established with strong correlation factors.Six parameters,such as grade score,accuracy and normalization mean error(NME),were used to evaluate the prediction effects of the four models.The main conclusions are as follows:AQI in four seasons shows obvious correlation with meteorological element values,the forecast effect of spring and summer is better than that of autumn and winter,and the forecast model of AQI in four seasons can meet the practical application requirements.