基于气象因素的PM10浓度预测

为建立准确高效的空气质量预报系统,建立以污染物、气象因素、污染物混合气象因素的三种预测因子模式,并将该三种预测因子模式作为支持向量机回归 (Support vector machine regression, SVR)的输入变量进行PM10浓度的每日预测,寻找最优预测因子模式。并使用灰狼优化算法 (Grey wolf optimization, GWO)对支持向量机回归模型进行优化,形成GWO-SVR模型。实验结果表明,污染物混合气象因素作为输入变量为最优预测因子模式, SVR和GWO-SVR模型测试集确定系数分别达到$R^2$=0.79和$R^2$=0.81,预测精度较高,经比较发现GWO-SVR模型预测性能较好。之后,依据风向条件对数据进行分类,使用较优的GWO-SVR进行PM10浓度预测,预测结果显示盛行西南风时, 预测集评测指标为$R$=0.91、$M_{\rm SE}$=47.15,优于盛行东北风时的$R$=0.87、$M_{\rm SE}$=125.80和所有数据下的$R$=0.90、$M_{\rm SE}$=107.94。

Prediction of PM10 Concentration Based on Meteorological Factors

In order to establish an accurate and efficient air quality forecasting system, three forecasting models based on pollutants, meteorological factors and pollutant mixed meteorological factors were established and used as input variables for support vector machine regression (SVR) for the daily forecast to look for the best predictor mode. The support vector machine regression model was optimized by using grey wolf optimization (GWO) to form the GWO-SVR model. The experimental results show that the meteorological factors of pollutants mixing acted as input variables is the optimal predictor model, and the determination coefficients of the test set of SVR and GWO-SVR model are $R^2$=0.79 and $R^2$=0.81, respectively, which indicates both of the models have high prediction accuracy. By comparision, GWO-SVR model prediction performance is better. After that, the data is classified according to the wind direction conditions and the better GWO-SVR is used to predict the PM10 concentration. The prediction results show that when the prevailing southwest wind prevails, the evaluation index of prediction set is $R$=0.91 and $M_{\rm SE}$=47.15, which is better than the status with prevailing northeasterly wind where $R$=0.87 and $M_{\rm SE}$=125.80 and the whole data with $R$=0.90 and $M_{\rm SE}$=107.94.