Modelling of Urban Near-Road Atmospheric PM Concentrations Using an Artificial Neural Network Approach with Acoustic Data Input

Air quality assessment is an important task for local authorities due to several adverse health effects that are associated with exposure to e.g., urban particle concentrations throughout the world. Based on the consumption of costs and time related to the experimental works required for standardized measurements of particle concentration in the atmosphere, other methods such as modelling arise as integrative options, on condition that model performance reaches certain quality standards. This study presents an Artificial Neural Network (ANN) approach to predict atmospheric concentrations of particle mass considering particles with an aerodynamic diameter of 0.25–1 μm (PM(0.25–1)), 0.25–2.5 μm (PM(0.25–2.5)), 0.25–10 μm (PM(0.25–10)) as well as particle number concentrations of particles with an aerodynamic diameter of 0.25–2.5 μm (PNC(0.25–2.5)). ANN model input variables were defined using data of local sound measurements, concentrations of background particle transport and standard meteorological data. A methodology including input variable selection, data splitting and an evaluation of their performance is proposed. The ANN models were developed and tested by the use of a data set that was collected in a street canyon. The ANN models were applied furthermore to a research site featuring an inner-city park to test the ability of the approach to gather spatial information of aerosol concentrations. It was observed that ANN model predictions of PM(0.25–10) and PNC(0.25–2.5) within the street canyon case as well as predictions of PM(0.25–2.5), PM(0.25–10) and PNC(0.25–2.5) within the case study of the park area show good agreement to observations and meet quality standards proposed by the European Commission regarding mean value prediction. Results indicate that the ANN models proposed can be a fairly accurate tool for assessment in predicting particle concentrations not only in time but also in space.

[1]  Multi-plume aerosol dynamics and transport model for urban scale particle pollution , 2005 .

[2]  Marc Guevara,et al.  The Potential impacts of electric vehicles on air quality in the urban areas of Barcelona and Madrid (Spain) , 2014 .

[3]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[4]  Luc Dekoninck,et al.  Spectral noise measurements supply instantaneous traffic information for multidisciplinary mobility and traffic related projects , 2016 .

[5]  Holger R. Maier,et al.  Selection of input variables for data driven models: An average shifted histogram partial mutual information estimator approach , 2009 .

[6]  K. Taylor.  Summarizing multiple aspects of model performance in a single diagram , 2001 .

[7]  Stephan Weber,et al.  Spatio-temporal covariation of urban particle number concentration and ambient noise , 2009 .

[8]  Joel D. Kaufman,et al.  The spatial relationship between traffic-generated air pollution and noise in 2 US cities. , 2009, Environmental research.

[9]  Yifang Zhu,et al.  Correlation of noise levels and particulate matter concentrations near two major freeways in Los Angeles, California. , 2014, Environmental pollution.

[10]  C. Schneider,et al.  A comparison of model performance between ENVI-met and Austal2000 for particulate matter , 2016 .

[11]  Gavin C. Cawley,et al.  Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki , 2003 .

[12]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[13]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 2. Case study: forecasting salinity in a river , 2005 .

[14]  Holger R. Maier,et al.  Data splitting for artificial neural networks using SOM-based stratified sampling , 2010, Neural Networks.

[15]  Yifang Zhu,et al.  Comparison of daytime and nighttime concentration profiles and size distributions of ultrafine particles near a major highway. , 2006, Environmental science & technology.

[16]  Matthias Ketzel,et al.  Estimation and validation of PM2.5/PM10 exhaust and non-exhaust emission factors for practical street pollution modelling , 2007 .

[17]  B. Brunekreef,et al.  Air pollution and lung cancer incidence in 17 European cohorts: prospective analyses from the European Study of Cohorts for Air Pollution Effects (ESCAPE). , 2013, The Lancet. Oncology.

[18]  P. Kassomenos,et al.  Identification of sources and processes affecting particulate pollution in Thessaloniki, Greece , 2011 .

[19]  M. Gardner,et al.  Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London , 1999 .

[20]  Martina S. Ragettli,et al.  Short-term associations between traffic-related noise, particle number and traffic flow in three European cities , 2015 .

[21]  Philip K. Hopke,et al.  Critical review and meta-analysis of ambient particulate matter source apportionment using receptor models in Europe , 2013 .

[22]  Ari Karppinen,et al.  Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki. , 2011, The Science of the total environment.

[23]  S. I. V. Sousa,et al.  Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations , 2007, Environ. Model. Softw..

[24]  B. De Baets,et al.  Correlation analysis of noise and ultrafine particle counts in a street canyon. , 2011, The Science of the total environment.

[25]  Christoph Schneider,et al.  Mobile measurements and regression modeling of the spatial particulate matter variability in an urban area. , 2012, The Science of the total environment.

[26]  Yafeng Yin,et al.  Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach , 2009 .

[27]  William M. Cox,et al.  A statistical procedure for determining the best performing air quality simulation model , 1990 .

[28]  C. Stow,et al.  Skill Assessment for Coupled Biological/Physical Models of Marine Systems. , 2009, Journal of marine systems : journal of the European Association of Marine Sciences and Techniques.

[29]  Gerard Hoek,et al.  Exposure to ultrafine and fine particles and noise during cycling and driving in 11 Dutch cities , 2009 .

[30]  Christoph Schneider,et al.  GIS-based identification of spatial variables enhancing heat and poor air quality in urban areas , 2012 .

[31]  K. P. Sudheer,et al.  Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions , 2010, Environ. Model. Softw..

[32]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[33]  Petr Hájek,et al.  Ozone prediction on the basis of neural networks, support vector regression and methods with uncertainty , 2012, Ecol. Informatics.

[34]  Germán Santos,et al.  A proposed methodology for the assessment of arsenic, nickel, cadmium and lead levels in ambient air. , 2016, The Science of the total environment.

[35]  D. Carruthers,et al.  FOR THE BENCHMARKING OF AIR QUALITY MODEL REGULATORY APPLICATIONS : THE “ TARGET ” APROACH , 2011 .

[36]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[37]  Mats Gustafsson,et al.  Urban air quality: the challenge of traffic non-exhaust emissions. , 2014, Journal of hazardous materials.

[38]  Wolfgang Römer,et al.  Klimamessstation Aachen-Hörn - Monatsberichte , 2017 .

[39]  J Aroba,et al.  Assessment of ultrafine particles and noise measurements using fuzzy logic and data mining techniques. , 2015, The Science of the total environment.

[40]  Davor Z. Antanasijević,et al.  Modeling of ammonia emission in the USA and EU countries using an artificial neural network approach , 2015, Environmental Science and Pollution Research.

[41]  P. Jurs,et al.  Prediction of the clearing temperatures of a series of liquid crystals from molecular structure , 1999 .

[42]  Stephan Weber,et al.  Variation of particle concentrations and environmental noise on the urban neighbourhood scale , 2008 .

[43]  Holger R. Maier,et al.  Non-linear variable selection for artificial neural networks using partial mutual information , 2008, Environ. Model. Softw..

[44]  Ulf Sandberg,et al.  Tyre/road noise reference book , 2002 .

[45]  A. Daly,et al.  Air Pollution Modeling - An Overview , 2007 .

[46]  S. Hanna,et al.  Air quality model performance evaluation , 2004 .

[47]  Hans Grimm,et al.  Aerosol Measurement: The Use of Optical Light Scattering for the Determination of Particulate Size Distribution, and Particulate Mass, Including the Semi-Volatile Fraction , 2009, Journal of the Air & Waste Management Association.

[48]  M. Ziefle,et al.  Small-scale variability of particulate matter and perception of air quality in an inner-city recreational area in Aachen, Germany , 2016 .

[49]  Markus Amann,et al.  Contributions to cities' ambient particulate matter (PM): a systematic review of local source contributions at global level , 2015 .

[50]  Bryan A. Tolson,et al.  A New Formulation for Feedforward Neural Networks , 2011, IEEE Transactions on Neural Networks.

[51]  Holger R. Maier,et al.  Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modelling , 2014, Environ. Model. Softw..

[52]  Stefan Fritsch,et al.  neuralnet: Training of Neural Networks , 2010, R J..

[53]  R N Meroney,et al.  On the use of numerical modelling for near-field pollutant dispersion in urban environments--A review. , 2016, Environmental pollution.

[54]  Philippe Thunis,et al.  A tool to evaluate air quality model performances in regulatory applications , 2012, Environ. Model. Softw..

[55]  M. Yassin,et al.  Numerical modeling on air quality in an urban environment with changes of the aspect ratio and wind direction , 2013, Environmental Science and Pollution Research.

[56]  J. Hooyberghs,et al.  A neural network forecast for daily average PM10 concentrations in Belgium , 2005 .

[57]  Laurent Francis,et al.  Assessment of air quality microsensors versus reference methods: The EuNetAir joint exercise , 2016 .

[58]  A. Karydas,et al.  Assessment of PM2.5 sources and their corresponding level of uncertainty in a coastal urban area using EPA PMF 5.0 enhanced diagnostics. , 2017, The Science of the total environment.

[59]  J. Seinfeld,et al.  Atmospheric Chemistry and Physics: From Air Pollution to Climate Change , 1997 .

[60]  Lidia Morawska,et al.  A STUDY OF THE HORIZONTAL AND VERTICAL PROFILE OF SUBMICROMETER PARTICLES IN RELATION TO A BUSY ROAD , 1999 .

[61]  Christer Johansson,et al.  Simulation of NOx and ultrafine particles in a street canyon in Stockholm, Sweden , 2004 .