Influencing factors and prediction of ambient Peroxyacetyl nitrate concentration in Beijing,China
|
摘要
Peroxyacyl nitrates(PANs) are important secondary pollutants in ground-level atmosphere.Accurate prediction of atmospheric pollutant concentrations is crucial to guide effective precautions for before and during specific pollution events. In this study, four models based on the back-propagation(BP) artificial neural network(ANN) and multiple linear regression(MLR) methods were used to predict the hourly average PAN concentrations at Peking University, Beijing, in 2014. The model inputs were atmospheric pollutant data and meteorological parameters. Model 3 using a BP-ANN based on the original variables achieved the best prediction results among the four models, with a correlation coefficient(R) of 0.7089, mean bias error of -0.0043 ppb, mean absolute error of 0.4836?ppb, root mean squared error of 0.5320?ppb, and Willmott's index of agreement of 0.8214. Based on a comparison of the performance indices of the MLR and BP-ANN models, we concluded that the BP-ANN model was able to capture the highly non-linear relationships between PAN concentration and the conventional atmospheric pollutant and meteorological parameters,providing more accurate results than the traditional MLR models did, with a markedly higher goodness of R. The selected meteorological and atmospheric pollutant parameters described a sufficient amount of PAN variation, and thus provided satisfactory prediction results. More specifically, the BP-ANN model performed very well for capturing the variation pattern when PAN concentrations were low. The findings of this study address some of the existing knowledge gaps in this research field and provide a theoretical basis for future regional air pollution control.
Peroxyacyl nitrates(PANs) are important secondary pollutants in ground-level atmosphere.Accurate prediction of atmospheric pollutant concentrations is crucial to guide effective precautions for before and during specific pollution events. In this study, four models based on the back-propagation(BP) artificial neural network(ANN) and multiple linear regression(MLR) methods were used to predict the hourly average PAN concentrations at Peking University, Beijing, in 2014. The model inputs were atmospheric pollutant data and meteorological parameters. Model 3 using a BP-ANN based on the original variables achieved the best prediction results among the four models, with a correlation coefficient(R) of 0.7089, mean bias error of -0.0043 ppb, mean absolute error of 0.4836?ppb, root mean squared error of 0.5320?ppb, and Willmott's index of agreement of 0.8214. Based on a comparison of the performance indices of the MLR and BP-ANN models, we concluded that the BP-ANN model was able to capture the highly non-linear relationships between PAN concentration and the conventional atmospheric pollutant and meteorological parameters,providing more accurate results than the traditional MLR models did, with a markedly higher goodness of R. The selected meteorological and atmospheric pollutant parameters described a sufficient amount of PAN variation, and thus provided satisfactory prediction results. More specifically, the BP-ANN model performed very well for capturing the variation pattern when PAN concentrations were low. The findings of this study address some of the existing knowledge gaps in this research field and provide a theoretical basis for future regional air pollution control.
Peroxyacyl nitrates(PANs) are important secondary pollutants in ground-level atmosphere.Accurate prediction of atmospheric pollutant concentrations is crucial to guide effective precautions for before and during specific pollution events. In this study, four models based on the back-propagation(BP) artificial neural network(ANN) and multiple linear regression(MLR) methods were used to predict the hourly average PAN concentrations at Peking University, Beijing, in 2014. The model inputs were atmospheric pollutant data and meteorological parameters. Model 3 using a BP-ANN based on the original variables achieved the best prediction results among the four models, with a correlation coefficient(R) of 0.7089, mean bias error of -0.0043 ppb, mean absolute error of 0.4836?ppb, root mean squared error of 0.5320?ppb, and Willmott's index of agreement of 0.8214. Based on a comparison of the performance indices of the MLR and BP-ANN models, we concluded that the BP-ANN model was able to capture the highly non-linear relationships between PAN concentration and the conventional atmospheric pollutant and meteorological parameters,providing more accurate results than the traditional MLR models did, with a markedly higher goodness of R. The selected meteorological and atmospheric pollutant parameters described a sufficient amount of PAN variation, and thus provided satisfactory prediction results. More specifically, the BP-ANN model performed very well for capturing the variation pattern when PAN concentrations were low. The findings of this study address some of the existing knowledge gaps in this research field and provide a theoretical basis for future regional air pollution control.
引文
Akkoyunlu,A.,Yetilmezsoy,K.,Erturk,F.,Oztemel,E.,2010.Aneural network-based approach for the prediction of urban SO2concentrations in the Istanbul metropolitan area.Int.J.Environ.Pollut.40,301-321.
Baawain,M.S.,Al-Serihi,A.S.,2014.Systematic approach for the prediction of ground-level air pollution(around an industrial port)using an artificial neural network.Aerosol air Qual.Res.14(1),124-134.
Baawain,M.S.,El-Din,M.G.,Smith,D.W.,2007.Artificial neural networks modeling of ozone bubble columns:mass transfer coefficient,gas hold-up,and bubble size.Ozone Sci.Eng.29(5),343-352.
Bishop,C.M.,1995.Neural Networks for Pattern Recognition.Clarendon Press.
Cai,M.,Yin,Y.,Xie,M.,2009.Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach.Transp Res D Trans Environ.14(1),32-41.
Chaloulakou,A.,Saisana,M.,Spyrellis,N.,2003a.Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens.Sci.Total Environ.313(1),1-13.
Chaloulakou,A.,Grivas,G.,Spyrellis,N.,2003b.Neural network and multiple regression models for PM10prediction in Athens:a comparative assessment.Air Waste management Assoc.53(10),1183-1190.
Chattopadhyay,S.,Chattopadhyay,G.,2012.Modeling and prediction of monthly total oozone concentrations by use of an artificial neural network based on principal component analysis.Pure Appl.Geophys.169,1891-1908.
Faris,H.,Alkasassbeh,M.,Rodan,A.,2014.Artificial neural networks for surface ozone prediction:models and analysis.Pol.J.Environ.Stud.23,341-348.
Fischer,E.V.,Jacob,D.J.,Yantosca,R.M.,Sulprizio,M.P.,Millet,D.B.,Mao,J.,et al.,2014.Atmospheric peroxyacetyl nitrate(PAN):a global budget and source attribution.Atmos.Chem.Phys.14(5),2679-2698.
Gao,T.,Li,H.,Wang,B.,Yang,G.,Xu,Z.,Zeng,L.,et al.,2014.Peroxyacetyl nitrate observed in Beijing in august from 2005 to2009.J.Environ.Sci.26(10),2007-2017.
Gardner,M.W.,Dorling,S.R.,1998.Artificial neural networks(the multilayer perception)-a review of applications in the atmospheric sciences.Atmos.Environ.32,2627-2636.
de Gennaro,G.,Trizio,L.,Di Gilio,A.,Pey,J.,Perez,N.,Cusack,M.,et al.,2013.Neural network model for the prediction of PM10daily concentrations at two sites in the western Mediterranean.Sci.Total Environ.463,875-883.
Grivas,G.,Chaloulakou,A.,2006.Artificial neural network models for prediction of PM hourly concentrations,in the greater area of Athens.Greece.Atmos.Environ.40(7),1216-1229.
Huang,G.,1991.Application of the theory of multivariate statistical analysis to prediction of air pollution in the urban environment.Environ.Sci.6(4),69-85.
Huang,M.L.,Hung,Y.H.,Chen,W.Y.,2010.Neural network classifier with entropy based feature selection on breast cancer diagnosis.J.Med.Syst.34(5),865-873.
Karacan,O.C.,2007.Development and application of reservoir models and artificial neural networks for optimizing ventilation air requirements in development mining of coal seams.Int.J.Coal Geol.72,221-239.
Karacan,O.C.,2008.Modeling and prediction of ventilation methane emissions of U.S.longwall mines using supervised artificial neural networks,Int.J.Coal Geol.73,371-387.
Kleindienst,T.E.,1994.Recent developments in the chemistry and biology of peroxyacetyl nitrate.Res.Chem.Intermed.20(3-5),335-384.
Lei,X.N.,1998.Air Pollution Numerical Forecasting Foundations and Patterns.China Meteorological Press.
Lu,W.Z.,Wang,W.J.,Wang,X.K.,Yan,S.H.,Lam,J.C.,2004.Potential assessment of a neural network model with PCA/RBFapproach for forecasting pollutant trends in Mong Kok urban air.Hong Kong.Environ.Res.96(1),79-87.
Nelson,M.M.,Illingworth,W.T.,1991.A Practical Guide to Neural Nets(Addison-Wesely).
Ozkan,G.,Ucan,L.,Ozkan,G.,2010.The prediction of SO2removal using statistical methods and artificial neural network.Neural Comput.Appl.19,67-75.
Payne,V.,Alvarado,M.,Cadypereira,K.E.,Worden,J.,Kulawik,S.S.,Fischer,E.V.,2013.Global satellite retrievals of Peroxy acetyl nitrate(PAN)in the troposphere//proceedings of the AGU fall meeting.San Francisco 2013,0182.
Pires,J.C.M.,Goncalves,B.,Azevedo,F.G.,Carneiro,A.P.,Rego,N.,Assembleia,A.J.B.,et al.,2012.Optimization of artificial neural network models through genetic algorithms for surface ozone concentration forecasting.Environ.Sci.Pollut.Res.19,3228-3234.
Ripley,B.D.,1996.Pattern Recognition and Neural Nets.Cambridge University Press.
Russo,A.,Raischel,F.,Lind,P.G.,2013.Air quality prediction using optimal neural networks with stochastic variables.Atmos.Environ.79,822-830.
Sánchez,A.B.,Ordó?ez,C.,Lasheras,F.S.,Juez,F.J.D.C.,RocaPardi?as,J.,2013.Forecasting SO2pollution incidents by means of Elman artificial neural networks and ARIMA models.Abstr.Appl.Anal.2013(3),1728-1749.
Seinfeld,J.H.,Pandis,S.N.,2012.Atmospheric Chemistry and Physics:From Air Pollution to Climate Change.John Wiley.
Singh,H.B.,Salas,L.J.,Viezee,W.,1986.Global distribution of peroxyacetyl nitrate.Nature 321(6070),588-591.
Sousa,S.I.V.,Martins,F.G.,Pereira,M.C.,Alvim-Ferraz,M.C.M.,2006.Prediction of ozone concentrations in oporto city with statistical approaches.Chemosphere 64(7),1141-1149.
Sousa,S.I.V.,Martins,F.G.,Alvim-Ferraz,M.C.M.,Pereira,M.C.,2007.Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations.Environ.Modelling and Software 22(1),97-103.
Stephens,E.R.,Hanst,P.L.,Doerr,R.C.,Scott,W.E.,1956.Reactions of nitrogen dioxide and organic compounds in air.Ind.Eng.Chem.48(9),1498-1504.
Vyskocil,A.,Viau,C.,Lamy,S.,1998.Peroxyacetyl nitrate:review of toxicity.Hum.Exp.Toxicol.17(4),212-220.
Zhang,J.M.,Wang,T.,Ding,A.J.,Zhou,X.H.,Xue,L.K.,Poon,C.N.,et al.,2009.Continuous measurement of peroxyacetyl nitrate(pan)in suburban and remote areas of western China.Atmos.Environ.43(2),228-237.
Zhang,H.,Liu,Y.,Shi,R.,Yao,Q.C.,2013.Evaluation of PM10forecasting based on an artificial neural network model and intake fraction in an urban area:a case study in Taiyuan City.China.J.Air Waste Manage.Assoc.63,755-763.
Zhang,H.,Xu,X.,Lin,W.,Wang,Y.,2014.Wintertime peroxyacetyl nitrate(pan)in the megacity Beijing:role of photochemical and meteorological processes.J.Environ.Sci.26(1),83-96.
Zhang,G.,Mu,Y.,Zhou,L.,Zhang,C.,Zhang,Y.,Liu,J.,et al.,2015.Summertime distributions of peroxyacetyl nitrate(pan)and peroxypropionyl nitrate(ppn)in Beijing:understanding the sources and major sink of pan.Atmos.Environ.103(1),289-296.
Zhang,B.,Zhao,B.,Zuo,P.,Huang,Z.,Zhang,J.,2017.Ambient peroxyacyl nitrate concentration and regional transportation in Beijing.Atmos.Environ.166,543-550.
Baawain,M.S.,Al-Serihi,A.S.,2014.Systematic approach for the prediction of ground-level air pollution(around an industrial port)using an artificial neural network.Aerosol air Qual.Res.14(1),124-134.
Baawain,M.S.,El-Din,M.G.,Smith,D.W.,2007.Artificial neural networks modeling of ozone bubble columns:mass transfer coefficient,gas hold-up,and bubble size.Ozone Sci.Eng.29(5),343-352.
Bishop,C.M.,1995.Neural Networks for Pattern Recognition.Clarendon Press.
Cai,M.,Yin,Y.,Xie,M.,2009.Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach.Transp Res D Trans Environ.14(1),32-41.
Chaloulakou,A.,Saisana,M.,Spyrellis,N.,2003a.Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens.Sci.Total Environ.313(1),1-13.
Chaloulakou,A.,Grivas,G.,Spyrellis,N.,2003b.Neural network and multiple regression models for PM10prediction in Athens:a comparative assessment.Air Waste management Assoc.53(10),1183-1190.
Chattopadhyay,S.,Chattopadhyay,G.,2012.Modeling and prediction of monthly total oozone concentrations by use of an artificial neural network based on principal component analysis.Pure Appl.Geophys.169,1891-1908.
Faris,H.,Alkasassbeh,M.,Rodan,A.,2014.Artificial neural networks for surface ozone prediction:models and analysis.Pol.J.Environ.Stud.23,341-348.
Fischer,E.V.,Jacob,D.J.,Yantosca,R.M.,Sulprizio,M.P.,Millet,D.B.,Mao,J.,et al.,2014.Atmospheric peroxyacetyl nitrate(PAN):a global budget and source attribution.Atmos.Chem.Phys.14(5),2679-2698.
Gao,T.,Li,H.,Wang,B.,Yang,G.,Xu,Z.,Zeng,L.,et al.,2014.Peroxyacetyl nitrate observed in Beijing in august from 2005 to2009.J.Environ.Sci.26(10),2007-2017.
Gardner,M.W.,Dorling,S.R.,1998.Artificial neural networks(the multilayer perception)-a review of applications in the atmospheric sciences.Atmos.Environ.32,2627-2636.
de Gennaro,G.,Trizio,L.,Di Gilio,A.,Pey,J.,Perez,N.,Cusack,M.,et al.,2013.Neural network model for the prediction of PM10daily concentrations at two sites in the western Mediterranean.Sci.Total Environ.463,875-883.
Grivas,G.,Chaloulakou,A.,2006.Artificial neural network models for prediction of PM hourly concentrations,in the greater area of Athens.Greece.Atmos.Environ.40(7),1216-1229.
Huang,G.,1991.Application of the theory of multivariate statistical analysis to prediction of air pollution in the urban environment.Environ.Sci.6(4),69-85.
Huang,M.L.,Hung,Y.H.,Chen,W.Y.,2010.Neural network classifier with entropy based feature selection on breast cancer diagnosis.J.Med.Syst.34(5),865-873.
Karacan,O.C.,2007.Development and application of reservoir models and artificial neural networks for optimizing ventilation air requirements in development mining of coal seams.Int.J.Coal Geol.72,221-239.
Karacan,O.C.,2008.Modeling and prediction of ventilation methane emissions of U.S.longwall mines using supervised artificial neural networks,Int.J.Coal Geol.73,371-387.
Kleindienst,T.E.,1994.Recent developments in the chemistry and biology of peroxyacetyl nitrate.Res.Chem.Intermed.20(3-5),335-384.
Lei,X.N.,1998.Air Pollution Numerical Forecasting Foundations and Patterns.China Meteorological Press.
Lu,W.Z.,Wang,W.J.,Wang,X.K.,Yan,S.H.,Lam,J.C.,2004.Potential assessment of a neural network model with PCA/RBFapproach for forecasting pollutant trends in Mong Kok urban air.Hong Kong.Environ.Res.96(1),79-87.
Nelson,M.M.,Illingworth,W.T.,1991.A Practical Guide to Neural Nets(Addison-Wesely).
Ozkan,G.,Ucan,L.,Ozkan,G.,2010.The prediction of SO2removal using statistical methods and artificial neural network.Neural Comput.Appl.19,67-75.
Payne,V.,Alvarado,M.,Cadypereira,K.E.,Worden,J.,Kulawik,S.S.,Fischer,E.V.,2013.Global satellite retrievals of Peroxy acetyl nitrate(PAN)in the troposphere//proceedings of the AGU fall meeting.San Francisco 2013,0182.
Pires,J.C.M.,Goncalves,B.,Azevedo,F.G.,Carneiro,A.P.,Rego,N.,Assembleia,A.J.B.,et al.,2012.Optimization of artificial neural network models through genetic algorithms for surface ozone concentration forecasting.Environ.Sci.Pollut.Res.19,3228-3234.
Ripley,B.D.,1996.Pattern Recognition and Neural Nets.Cambridge University Press.
Russo,A.,Raischel,F.,Lind,P.G.,2013.Air quality prediction using optimal neural networks with stochastic variables.Atmos.Environ.79,822-830.
Sánchez,A.B.,Ordó?ez,C.,Lasheras,F.S.,Juez,F.J.D.C.,RocaPardi?as,J.,2013.Forecasting SO2pollution incidents by means of Elman artificial neural networks and ARIMA models.Abstr.Appl.Anal.2013(3),1728-1749.
Seinfeld,J.H.,Pandis,S.N.,2012.Atmospheric Chemistry and Physics:From Air Pollution to Climate Change.John Wiley.
Singh,H.B.,Salas,L.J.,Viezee,W.,1986.Global distribution of peroxyacetyl nitrate.Nature 321(6070),588-591.
Sousa,S.I.V.,Martins,F.G.,Pereira,M.C.,Alvim-Ferraz,M.C.M.,2006.Prediction of ozone concentrations in oporto city with statistical approaches.Chemosphere 64(7),1141-1149.
Sousa,S.I.V.,Martins,F.G.,Alvim-Ferraz,M.C.M.,Pereira,M.C.,2007.Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations.Environ.Modelling and Software 22(1),97-103.
Stephens,E.R.,Hanst,P.L.,Doerr,R.C.,Scott,W.E.,1956.Reactions of nitrogen dioxide and organic compounds in air.Ind.Eng.Chem.48(9),1498-1504.
Vyskocil,A.,Viau,C.,Lamy,S.,1998.Peroxyacetyl nitrate:review of toxicity.Hum.Exp.Toxicol.17(4),212-220.
Zhang,J.M.,Wang,T.,Ding,A.J.,Zhou,X.H.,Xue,L.K.,Poon,C.N.,et al.,2009.Continuous measurement of peroxyacetyl nitrate(pan)in suburban and remote areas of western China.Atmos.Environ.43(2),228-237.
Zhang,H.,Liu,Y.,Shi,R.,Yao,Q.C.,2013.Evaluation of PM10forecasting based on an artificial neural network model and intake fraction in an urban area:a case study in Taiyuan City.China.J.Air Waste Manage.Assoc.63,755-763.
Zhang,H.,Xu,X.,Lin,W.,Wang,Y.,2014.Wintertime peroxyacetyl nitrate(pan)in the megacity Beijing:role of photochemical and meteorological processes.J.Environ.Sci.26(1),83-96.
Zhang,G.,Mu,Y.,Zhou,L.,Zhang,C.,Zhang,Y.,Liu,J.,et al.,2015.Summertime distributions of peroxyacetyl nitrate(pan)and peroxypropionyl nitrate(ppn)in Beijing:understanding the sources and major sink of pan.Atmos.Environ.103(1),289-296.
Zhang,B.,Zhao,B.,Zuo,P.,Huang,Z.,Zhang,J.,2017.Ambient peroxyacyl nitrate concentration and regional transportation in Beijing.Atmos.Environ.166,543-550.