Air quality prediction using optimal neural networks with stochastic variables

We apply recent methods in stochastic data analysis for discovering a set of few stochastic variables that represent the relevant information on a multivariate stochastic system, used as input for artificial neural network models for air quality forecast. We show that using these derived variables as input variables for training the neural networks it is possible to significantly reduce the amount of input variables necessary for the neural network model, without considerably changing the predictive power of the model. The reduced set of variables including these derived variables is therefore proposed as an optimal variable set for training neural network models in forecasting geophysical and weather properties. Finally, we briefly discuss other possible applications of such optimized neural network models.

[1]  Joseph Rynkiewicz,et al.  A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions , 2007, Environ. Model. Softw..

[2]  R. Trigo,et al.  Simulation of daily temperatures for climate change scenarios over Portugal: a neural network model approach , 1999 .

[3]  F. Nejadkoorki,et al.  Forecasting Extreme PM 10 Concentrations Using Artificial Neural Networks , 2012 .

[4]  David Kleinhans,et al.  Searching for optimal variables in real multivariate stochastic data , 2011, 1111.2008.

[5]  D. R. Middleton.  A New Box Model to Forecast Urban Air Quality: Boxurb , 1998 .

[6]  Roy M. Harrison,et al.  Regression modelling of hourly NOx and NO2 concentrations in urban air in London , 1997 .

[7]  C. Gardiner.  Handbook of Stochastic Methods , 1983 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Friedrich,et al.  How to quantify deterministic and random influences on the statistics of the foreign exchange market , 1999, Physical review letters.

[10]  M Haase,et al.  Extracting strong measurement noise from stochastic time series: applications to empirical data. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  W. Briggs.  Statistical Methods in the Atmospheric Sciences , 2007 .

[12]  D. Kleinhansa,et al.  An iterative procedure for the estimation of drift and diffusion coefficients of Langevin processes , 2005 .

[13]  M. Haase,et al.  Reducing stochasticity in the North Atlantic Oscillation index with coupled Langevin equations. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  J. Peinke,et al.  Description of a Turbulent Cascade by a Fokker-Planck Equation , 1997 .

[15]  Patricio Perez.  Prediction of sulfur dioxide concentrations at a site near downtown Santiago, Chile , 2001 .

[16]  William H. Press,et al.  Numerical recipes , 1990 .

[17]  C. Borrego,et al.  Particulate Matter and Health Risk under a Changing Climate: Assessment for Portugal , 2012, TheScientificWorldJournal.

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

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

[20]  Dimitrios Melas,et al.  Development and Assessment of Neural Network and Multiple Regression Models in Order to Predict PM10 Levels in a Medium-sized Mediterranean City , 2007 .

[21]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[22]  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 .

[23]  Andreas Daffertshofer,et al.  Deterministic and stochastic features of rhythmic human movement , 2006, Biological Cybernetics.

[24]  Malik Beshir Malik,et al.  Applied Linear Regression , 2005, Technometrics.

[25]  L. Dawidowski,et al.  Artificial neural network for the identification of unknown air pollution sources , 1999 .

[26]  H. Risken.  Fokker-Planck Equation , 1984 .

[27]  M. C. Hubbard,et al.  A Comparison of Nonlinear Regression and Neural Network Models for Ground-Level Ozone Forecasting , 2000, Journal of the Air & Waste Management Association.

[28]  Deborah J. Luecken,et al.  Development and analysis of air quality modeling simulations for hazardous air pollutants , 2006 .

[29]  Matthias Demuzere,et al.  The impact of weather and atmospheric circulation on O 3 and PM 10 levels at a rural mid-latitude site , 2008 .

[30]  Stephen Dorling,et al.  Statistical surface ozone models: an improved methodology to account for non-linear behaviour , 2000 .

[31]  Muhammad Sahimi,et al.  Approaching complexity by stochastic methods: From biological systems to turbulence , 2011 .

[32]  J. Peinke,et al.  Principal axes for stochastic dynamics. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[33]  V. V. Lopes,et al.  Uncovering wind turbine properties through two-dimensional stochastic modeling of wind dynamics. , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.

[34]  R. Trigo,et al.  Circulation weather types and their influence on the precipitation regime in Portugal. , 2000 .

[35]  Bindhu Lal,et al.  Prediction of dust concentration in open cast coal mine using artificial neural network , 2012 .

[36]  Gabriel Ibarra-Berastegi,et al.  Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area , 2006, Environ. Model. Softw..

[37]  Muhammad Sahimi,et al.  Markov analysis and Kramers-Moyal expansion of nonstationary stochastic processes with application to the fluctuations in the oil price. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[38]  Joachim Peinke,et al.  Reconstruction of complex dynamical systems affected by strong measurement noise. , 2006, Physical review letters.

[39]  I. Grabec,et al.  Examples of Analysis of Stochastic Processes Based on Time Series Data , 2003 .

[40]  Saeid Baroutian,et al.  Forecasting Extreme PM10 Concentrations Using Artificial Neural Networks , 2012 .

[41]  V. Prybutok,et al.  A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area. , 1996, Environmental pollution.

[42]  M. Kolehmainen,et al.  Neural networks and periodic components used in air quality forecasting , 2001 .

[43]  Jason A. C. Gallas,et al.  Minimizing Stochasticity in the NAO Index , 2007, Int. J. Bifurc. Chaos.

[44]  Jorge Reyes,et al.  Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile , 2000 .

[45]  P. G. Lind,et al.  Evaluating strong measurement noise in data series with simulated annealing method , 2011, 1212.6356.

[46]  S. Lade.  Finite sampling interval effects in Kramers-Moyal analysis , 2009, 0905.4324.

[47]  Roberto San José García,et al.  Prediction of ozone levels in London using the MM5-CMAQ modelling system , 2006, Environ. Model. Softw..

[48]  T. Hassard,et al.  Applied Linear Regression , 2005 .