Forecasting human exposure to PM10 at the national level using an artificial neural network approach

A neural network model for predicting country‐level concentrations of the fraction of particulates in the air with sizes less than 10 µm (PM10) has been developed using widely available sustainability and economical/industrial parameters as inputs. The model was trained and validated with the data for 23 European Union (EU) countries plus the EU27 as a group for the period from 2000 to 2008. The inputs for the model were selected using correlation analyses. Country‐level PM10 concentration data that were used as a model output were obtained from the World Bank. The artificial neural network (ANN) model, created with inputs chosen by correlation analyses, has shown very good performance in the forecast of country‐level PM10 concentrations. The mean absolute error for the ANN model prediction, in the case of most of the EU countries, was less than 13%, indicating stable and accurate predictions. The predictions obtained from the principal component regression model, which was trained and tested using the same datasets and input variables, had mean absolute errors from 20% to 150% for most of the countries. The wide availability of input parameters used in this model can overcome the problem of lack and scarcity of data in many countries, which can in turn prevent the determination of human exposure to PM10 at the national level. Copyright © 2013 John Wiley & Sons, Ltd.

[1]  Davor Z Antanasijević,et al.  PM(10) emission forecasting using artificial neural networks and genetic algorithm input variable optimization. , 2013, The Science of the total environment.

[2]  J. Kukkonen,et al.  Intercomparison of air quality data using principal component analysis, and forecasting of PM₁₀ and PM₂.₅ concentrations using artificial neural networks, in Thessaloniki and Helsinki. , 2011, The Science of the total environment.

[3]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[4]  Kelley Lee.  World Health Organization , 1946 .

[5]  Mihkel Kaljurand,et al.  Qualitative detection of illegal drugs (cocaine, heroin and MDMA) in seized street samples based on SFS data and ANN: validation of method , 2012 .

[6]  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 .

[7]  Jorge Reyes,et al.  Prediction of maximum of 24-h average of PM10 concentrations 30 h in advance in Santiago, Chile , 2002 .

[8]  John Irwin,et al.  A framework for evaluating regional-scale numerical photochemical modeling systems , 2010, Environmental fluid mechanics.

[9]  Anastasia K Paschalidou,et al.  Forecasting hourly PM10 concentration in Cyprus through artificial neural networks and multiple regression models: implications to local environmental management , 2011, Environmental science and pollution research international.

[10]  E. Nadaraya.  On Non-Parametric Estimates of Density Functions and Regression Curves , 1965 .

[11]  Tong-Seng Quah,et al.  Application of neural networks for software quality prediction using object-oriented metrics , 2005, J. Syst. Softw..

[12]  Gilles Foret,et al.  Combining deterministic and statistical approaches for PM10 forecasting in Europe , 2009 .

[13]  Viktor Pocajt,et al.  The forecasting of municipal waste generation using artificial neural networks and sustainability indicators , 2012, Sustainability Science.

[14]  Viktor Pocajt,et al.  Forecasting of Greenhouse Gas Emissions in Serbia Using Artificial Neural Networks , 2013 .

[15]  Archibald Cox,et al.  AIRBORNE PARTICLES AND HEALTH : HEI EPIDEMIOLOGIC EVIDENCE , 2001 .

[16]  Tong-Seng Quah,et al.  Application of neural networks for software quality prediction using object-oriented metrics , 2003, International Conference on Software Maintenance, 2003. ICSM 2003. Proceedings..

[17]  T. Bolanča,et al.  Application of different training methodologies for the development of a back propagation artificial neural network retention model in ion chromatography , 2008 .

[18]  Babak Omidvar,et al.  Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic , 2010, Expert Syst. Appl..

[19]  Shie-Yui Liong,et al.  An ANN application for water quality forecasting. , 2008, Marine pollution bulletin.

[20]  Dirk Tomandl,et al.  A Modified General Regression Neural Network (MGRNN) with new, efficient training algorithms as a robust 'black box'-tool for data analysis , 2001, Neural Networks.

[21]  P Hyde,et al.  Forecasting PM10 in metropolitan areas: Efficacy of neural networks. , 2012, Environmental pollution.

[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]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

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

[25]  Hugh M Cartwright,et al.  Artificial Neural Networks in Biology and Chemistry - The Evolution of a New Analytical Tool , 2009, Artificial Neural Networks.

[26]  G. S. Watson,et al.  Smooth regression analysis , 1964 .

[27]  E. Nadaraya.  On Estimating Regression , 1964 .

[28]  Silvia Curteanu,et al.  Neural networks applied in chemistry. I. Determination of the optimal topology of multilayer perceptron neural networks , 2011 .

[29]  Nabil A. Zaghloul,et al.  Neural network solution of inverse parameters used in the sensitivity-calibration analysis of the SWMM model simulations , 2001 .