Prediction of vertical PM2.5 concentrations alongside an elevated expressway by using the neural network hybrid model and generalized additive model

Ya GAO , Zhanyong WANG , Qing-Chang LU , Chao LIU , Zhong-Ren PENG , Yue YU

Front. Earth Sci. ›› 2017, Vol. 11 ›› Issue (2) : 347 -360.

PDF (1873KB)
Front. Earth Sci. ›› 2017, Vol. 11 ›› Issue (2) : 347 -360. DOI: 10.1007/s11707-016-0593-0
RESEARCH ARTICLE
RESEARCH ARTICLE

Prediction of vertical PM2.5 concentrations alongside an elevated expressway by using the neural network hybrid model and generalized additive model

Author information +
History +
PDF (1873KB)

Abstract

A study on vertical variation of PM2.5 concentrations was carried out in this paper. Field measurements were conducted at eight different floor heights outside a building alongside a typical elevated expressway in downtown Shanghai, China. Results show that PM2.5 concentration decreases significantly with the increase of height from the 3rd to 7th floor or the 8th to 15th floor, and increases suddenly from the 7th to 8th floor which is the same height as the elevated expressway. A non-parametric test indicates that the data of PM2.5 concentration is statistically different under the 7th floor and above the 8th floor at the 5% significance level. To investigate the relationships between PM2.5 concentration and influencing factors, the Pearson correlation analysis was performed and the results indicate that both traffic and meteorological factors have crucial impacts on the variation of PM2.5 concentration, but there is a rather large variation in correlation coefficients under the 7th floor and above the 8th floor. Furthermore, the back propagation neural network based on principal component analysis (PCA-BPNN), as well as generalized additive model (GAM), was applied to predict the vertical PM2.5 concentration and examined with the field measurement dataset. Experimental results indicated that both models can obtain accurate predictions, while PCA-BPNN model provides more reliable and accurate predictions as it can reduce the complexity and eliminate data co-linearity. These findings reveal the vertical distribution of PM2.5 concentration and the potential of the proposed model to be applicable to predict the vertical trends of air pollution in similar situations.

Keywords

vertical variations / principal component analysis / back propagation neural network / generalized additive model / urban elevated expressway

Cite this article

Download citation ▾
Ya GAO, Zhanyong WANG, Qing-Chang LU, Chao LIU, Zhong-Ren PENG, Yue YU. Prediction of vertical PM2.5 concentrations alongside an elevated expressway by using the neural network hybrid model and generalized additive model. Front. Earth Sci., 2017, 11(2): 347-360 DOI:10.1007/s11707-016-0593-0

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Abdul-Wahab S ABakheit C SAl-Alawi S M (2005). Principal component and multiple regression analysis in modelling of ground-level ozone and factors affecting its concentrations. Environ Model Softw20(10): 1263–1271

[2]

Aldrin MHaff I H (2005). Generalised additive modelling of air pollution, traffic volume and meteorology. Atmos Environ39(11): 2145–2155

[3]

Cai MYin YXie M (2009). Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach. Transp Res Part D Transp Environ14(1): 32–41

[4]

Carslaw D CBeevers S DTate J E (2007). Modelling and assessing trends in traffic-related emissions using a generalised additive modelling approach. Atmos Environ41(26): 5289–5299

[5]

Chan L YKwok W S (2000). Vertical dispersion of suspended particulates in urban area of Hong Kong. Atmos Environ34(26): 4403–4412

[6]

Colls J JMicallef A (1999). Measured and modelled concentrations and vertical profiles of airborne particulate matter within the boundary layer of a street canyon. Sci Total Environ235(1‒3): 221–233

[7]

Chaloulakou  ASaisana  MSpyrellis  N (2003). Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens. Science of the Total Environment313(1): 1–13

[8]

Gardner  M WDorling  S R (2000). Statistical surface ozone models: an improved methodology to account for non-linear behaviour. Atmospheric Environment34(1): 21–34

[9]

Hastie T JTibshirani R J (1990). Generalized additive models. London: Chapman and Hall 

[10]

He H DLu W Z (2012). Urban aerosol particulates on Hong Kong roadsides: size distribution and concentration levels with time. Stochastic Environ Res Risk Assess26(2): 177–187

[11]

He H DLu W ZXue Y (2014). Prediction of particulate matters at urban intersection by using multilayer perceptron model based on principal components. Stochastic Environ Res Risk Assess29(8): 2107–2114

[12]

He JQi ZZhao CBao X (2009). Simulations of pollutant dispersion at toll plazas using three-dimensional CFD models. Transp Res Part D Transp Environ14(8): 557–566160;

[13]

Kumar PFennell PLangley DBritter R (2008). Pseudo-simultaneous measurements for the vertical variation of coarse fine and ultrafine particles in an urban street canyon. Atmos Environ42(18): 4304–4319

[14]

Kumar PGarmory AKetzel MBerkowicz RBritter R (2009). Comparative study of measured and modelled number concentrations of nanoparticles in an urban street canyon. Atmos Environ43(4): 949–958

[15]

Li XWang JTu X DLiu WHuang Z (2007). Vertical variations of particle number concentration and size distribution in a street canyon in Shanghai, China. Sci Total Environ378(3): 306–316

[16]

Longley I DGallagher M WDorsey J RFlynn M (2004). A case-study of fine particle concentrations and fluxes measured in a busy street canyon in Manchester, UK. Atmos Environ38(22): 3595–3603

[17]

Mazzoleni CMoosmüller HKuhns H DKeislar R EBarber P WNikolic DNussbaum N JWatson J G (2004). Correlation between automotive CO, HC, NO, and PM emission factors from on-road remote sensing: implications for inspection and maintenance programs. Transp Res Part D Transp Environ9(6): 477–496

[18]

McNabola ABroderick B MGill L W (2009). The impacts of inter-vehicle spacing on in-vehicle air pollution concentrations in idling urban traffic conditions. Transp Res Part D Transp Environ14(8): 567–575

[19]

Milionis  A EDavies  T D (1994). Box-Jenkins univariate modelling for climatological time series analysis: an application to the monthly activity of temperature inversions. International Journal of Climatology14(5): 569–579.

[20]

Moseholm LSilva JLarson T (1996). Forecasting carbon monoxide concentrations near a sheltered intersection using video traffic surveillance and neural networks. Transp Res Part D Transp Environ1(1): 15–28

[21]

Muñoz EMartin M LTurias I JJimenez-Come M JTrujillo F J (2014). Prediction of PM10 and SO2 exceedances to control air pollution in the Bay of Algeciras, Spain. Stochastic Environ Res Risk Assess28(6): 1409–1420

[22]

Nagendra S SKhare M (2006). Artificial neural network approach for modelling nitrogen dioxide dispersion from vehicular exhaust emissions. Ecol Modell190(1‒2): 99–115

[23]

Ng  H K TBalakrishnan  NPanchapakesan  S (2007). Selecting the best population using a test for equality based on minimal Wilcoxon rank-sum precedence statistic. Methodology and Computing in Applied Probability9(2): 263–305

[24]

Schleicher N JNorra SChai FChen YWang SCen KYu  YStüben D (2011). Temporal variability of trace metal mobility of urban particulate matter from Beijing–A contribution to health impact assessments of aerosols. Atmos Environ45(39): 7248–7265

[25]

Schlink UDorling SPelikan ENunnari GCawley GJunninen HGreig  AFoxall  REben  KChatterton  TVondracek  JRichter  MDostal  MBertucco  LKolehmainen  MDoyle M (2003). A rigorous inter-comparison of ground-level ozone predictions. Atmos Environ37(23): 3237–3253

[26]

Sousa S I VMartins F GAlvim-Ferraz M C MPereira M C (2007). Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations. Environ Model Softw22(1): 97–103

[27]

Tang T QHuang H JShang H Y (2015c). Influences of the driver’s bounded rationality on micro driving behavior, fuel consumption and emissions. Transp Res Part D Transp Environ41: 423–432

[28]

Tang T QYu QYang S CDing C (2015a). Impacts of the vehicle’s fuel consumption and exhaust emissions on the trip cost allowing late arrival under car-following model.  Physica A: Statistical Mechanics and its Applications,  431: 52–62

[29]

Tang  T QLi  J GYang  S CShang  H Y (2015b). Effects of on-ramp on the fuel consumption of the vehicles on the main road under car-following model.  Physica A: Statistical Mechanics and its Applications,  419: 293–300

[30]

Wang J SChan T LNing ZLeung C WCheung C SHung W T (2006). Roadside measurement and prediction of CO and PM2.5 dispersion from on-road vehicles in Hong Kong. Transp Res Part D Transp Environ11(4): 242–249

[31]

Wang J SHuang Z (2002). Numerical study on impact of urban viaduct on local-scale of atmospheric environment. Shanghai Environmental Sciences21(3): 132–135

[32]

Wang ZHe H DLu FLu Q CPeng Z R (2015a). Hybrid model for prediction of carbon monoxide and fine particulate matter concentrations near a road intersection. Transp Res Rec2503: 29–38

[33]

Wang ZLu FHe  H DLu Q CWang DPeng Z R (2015b). Fine-scale estimation of carbon monoxide and fine particulate matter concentrations in proximity to a road intersection by using wavelet neural network with genetic algorithm. Atmos Environ104: 264–272

[34]

Wang ZLu Q CHe  H DWang DGao YPeng Z R (2016). Investigation of the spatiotemporal variation and influencing factors on fine particulate matter and carbon monoxide concentrations near a road intersection. Front. Earth Sci., doi: 10.1007/s11707-016-0564-5

[35]

Weber SKuttler WWeber K (2006). Flow characteristics and particle mass and number concentration variability within a busy urban street canyon. Atmos Environ40(39): 7565–7578

[36]

Wood S NAugustin N H (2002). GAMs with integrated model selection using penalized regression splines and applications to environmental modelling. Ecol Modell157(2‒3): 157–177

[37]

Zhang  C JZeng  J RWen  MZhang  G LFang  H PLi  Y (2012). Influence of Viaducts on Dispersion of Air Particles in Street Canyons. Research of Environmental Sciences25(2): 159–164.

[38]

Zhang D ZPeng Z R (2014). Near-road fine particulate matter concentration estimation using artificial neural network approach. Int J Environ Sci Technol11(8): 2403–2412

[39]

Zhang KBatterman S (2010). Near-road air pollutant concentrations of CO and PM2.5: A comparison of MOBILE6. 2/CALINE4 and generalized additive models. Atmos Environ44(14): 1740–1748

[40]

Zhang L DZhu W X (2015). Delay-feedback control strategy for reducing emission of traffic flow system.  Physica A: Statistical Mechanics and its Applications,  428: 481–492

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg

AI Summary AI Mindmap
PDF (1873KB)

984

Accesses

0

Citation

Detail

Sections
Recommended

AI思维导图

/