基于BP人工神经网络的大气颗粒物PM_(10)质量浓度预测  

Prediction of PM_(10) mass concentrations based on BP artificial neural network

作　　者：石灵芝[1] 邓启红[1] 路婵[1] 刘蔚巍[1] 

机构地区：[1]中南大学能源科学与工程学院,湖南长沙410083

出　　处：《中南大学学报（自然科学版）》2012年第5期1969-1974,共6页Journal of Central South University:Science and Technology

基　　金：高等学校全国优秀博士学位论文作者专项资金资助项目(200545);国家自然科学基金资助项目(51178466);国家"十一五"科技支撑计划项目(2008BAJ12B03)

摘　　要：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。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.

关 键 词：BP人工神经网络 PM10 预测 多元线性回归 高污染 

分 类 号：X831[环境科学与工程—环境工程]