摘要
为解决PM2.5浓度预测中存在的精度不高的问题,文章提出了一个基于相关分析、自回归分布滞后模型、果蝇优化算法、核极限学习机的在线PM2.5日浓度混合预测模型。并将模型应用于关中地区五个地市,用2016年1月至2017年5月监测数据对模型进行验证。结果表明:模型均方根误差<6μg,平均绝对百分比误差<8%,拟合优度R2>0.98,能够在日尺度下有效地预测PM2.5浓度,可以为当地开展空气污染预警和城市综合管理提供决策支持。
引文
[1]Sun W,Sun J.Daily PM2.5 Concentration Prediction Based on Principal Component Analysis and LSSVM Optimized by Cuckoo Search Algorithm[J].Journal of Environmental Management,2017,(188).
[2]Donkelaar A V,Martin R V,Brauer M,et al.Global Estimates of Ambient Fine Particulate Matter Concentrations From Satellite-based Aerosol Optical Depth:Development and Application[J].Environmental Health Perspectives,2010,118(6).
[3]Lu S,Yao Z,Chen X,et al.The Relationship Between Physicochemical Characterization and the Potential Toxicity of Fine Particulates(PM2.5)in Shanghai Atmosphere[J].Atmospheric Environment,2008,42(31).
[4]Bell M L,Francesca D,Keita E,et al.Spatial and Temporal Variation in PM2.5 Chemical Composition in the United States for Health Effects Studies[J].Environmental Health Perspectives,2007,115(7).
[5]Talbott E O,Rager J R,Benson S,et al.A Case-crossover Analysis of the Impact of PM2.5,on Cardiovascular Disease Hospitalizations for Selected CDC Tracking States[J].Environmental Research,2014,134(134C).
[6]Yan J,Lai C H,Lung S C,et al.Industrial PM2.5 Cause Pulmonary Adverse Effect Through RhoA/ROCK Pathway[J].Science of the Total Environment,2017.
[7]陈嘉雯,陈华超,徐强.全要素生产率与能源消费对碳排放影响的实证分析[J].统计与决策,2018,34(13).
[8]Huang G B,Zhu Q Y,Siew C K.Extreme Learning Machine:Theory and Applications[J].Neurocomputing,2006,(70).
[9]Huang G B,Zhou H,Ding X,et al.Extreme Learning Machine for Regression and Multiclass Classification[J].IEEE Transactions on Systems Man&Cybernetics Part B,2012,42(2).
[10]He W,Wang E,Xiong T.Intelligent Face Recognition based on Manifold Learning and Genetic-Chaos Algorithm Optimized Kernel Extreme Learning Machine[J].Journal of Communications,2013,8(10).
[11]Sun H,Yang J,Wang L.Resistance Spot Welding Quality Identification With Particle Swarm Optimization and A Kernel Extreme Learning Machine Model[J].International Journal of Advanced Manufacturing Technology,2016.
[12]Pan W C.A New Fruit Fly Optimization Algorithm:Taking the Financial Distress Model as an Example[J].Knowledge-Based Systems,2012,26(2)
[13]余辉,袁晶,于旭耀等.基于ARMAX的PM2.5小时浓度跟踪预测模型[J].天津大学学报(自然科学与工程技术版),2017,(1).