基于BP人工神经网络的大气颗粒物PM10质量浓度预测

根据2008年长沙市火车站监测点全年大气PM10及气象参数的小时平均数据,建立BP人工神经网络预测模型,预测PM10小时平均浓度。为证明人工神经网络模型用于预测PM10质量浓度的准确性,研究中考虑2种预测模型:多元线性回归模型与人工神经网络模型。研究结果表明:与传统的多元线性回归模型相比,人工神经网络模型能够捕捉污染物浓度与气象因素间的非线性影响规律,能更好地预测PM10质量浓度,拟合优度R2有较大提高;所选取气象参数及污染源强变量能较准确地描述大气PM10质量浓度的实时变化,用于PM10质量浓度的预测准确度较高,整体R2可达0.62;人工神经网络预测模型不仅适用于一般污染浓度情况,对于高污染时期PM10质量浓度的预测也较为准确。

Prediction of PM10 mass concentrations based on BP artificial neural network

The back-propagation(BP) artificial neural network model for prediction of PM10 mass concentrations was developed using atmospheric PM10 mass concentration and meteorological data in 2008,which was monitored in Changsha railway-station.In order to show the accuracy of PM10 mass concentration prediction based on artificial neural network,two models were developed: multiple linear regression model and artificial neural network model.The results show that the BP artificial neural network model can be trained to model the highly non-linear relationships between PM10 mass concentration and meteorological parameters,and to provide better results than the traditional multiple linear regression models with much higher goodness of fit(R2).The meteorological parameters and emission source variation variables can accurately describe PM10 variation,and thus provide satisfactory prediction results,with R2 of 0.62.In addition,the developed BP artificial neural network model for prediction of PM10 mass concentrations also works well for PM10 modelling during episode.