The inclusion of exogenous variables in functional autoregressive ozone forecasting

In this article, we propose a new technique for ozone forecasting. The approach is functional, that is we consider stochastic processes with values in function spaces. We make use of the essential characteristic of this type of phenomenon by taking into account theoretically and practically the continuous time evolution of pollution. One main methodological enhancement of this article is the incorporation of exogenous variables (wind speed and temperature) in those models. The application is carried out on a six-year data set of hourly ozone concentrations and meteorological measurements from Bethune (France). The study examines the summer periods because of the higher values observed. We explain the non-parametric estimation procedure for autoregressive Hilbertian models with or without exogenous variables (considering two alternative versions in this case) as well as for the functional kernel model. The comparison of all the latter models is based on up-to-24 hour-ahead predictions of hourly ozone concentrations. We analyzed daily forecast curves upon several criteria of two kinds: functional ones, and aggregated ones where attention is put on the daily maximum. It appears that autoregressive Hilbertian models with exogenous variables show the best predictive power. Copyright (C) 2002 John Wiley Sons, Ltd.

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

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

[3]  Y. Slamani.  Etude comparative de differents modeles mathematiques pour la prediction des niveaux de pollution atmospherique , 1988 .

[4]  B. Ghattas,et al.  Prévisions des pics d'ozone par arbres de régression, simples et agrégés par Bootstrap , 1999 .

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

[6]  J. Viel,et al.  A model selection tool in multi-pollutant time series : The Granger-Causality diagnosis , 1999 .

[7]  Marija Zlata Boznar,et al.  A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain , 1993 .

[8]  Philippe C. Besse,et al.  Approximation spline de la prvision d'un processus fonctionnel autorgressif d'ordre 1 , 1996 .

[9]  R. Tibshirani,et al.  Generalized Additive Models , 1991 .

[10]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[11]  D. Bosq.  Linear Processes in Function Spaces: Theory And Applications , 2000 .

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

[13]  Ross Ihaka,et al.  Gentleman R: R: A language for data analysis and graphics , 1996 .

[14]  Non-causalité et discrétisation fonctionnelle, théorèmes limites pour un processus ARHX(1) , 2000 .

[15]  Andrew C. Comrie,et al.  Climatology and forecast modeling of ambient carbon monoxide in Phoenix, Arizona , 1999 .

[16]  T. Mourid.  Contribution à la statistique des processus autorégressifs à temps continus , 1995 .

[17]  M. Deistler,et al.  Time series models for short term forecasting of ozone in the eastern part of Austria , 2001 .

[18]  Kasım Koçak,et al.  Nonlinear time series prediction of O3 concentration in Istanbul , 2000 .

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

[20]  Paul L. Speckman,et al.  A model for predicting maximum and 8 h average ozone in Houston , 1999 .

[21]  Jose Torres-Jimenez,et al.  Short-term ozone forecasting by artificial neural networks , 1995 .

[22]  Wenceslao González-Manteiga,et al.  Time-series analysis for ambient concentrations , 1993 .

[23]  Wenceslao González-Manteiga,et al.  Prediction of SO2 pollution incidents near a power station using partially linear models and an historical matrix of predictor‐response vectors , 2000 .

[24]  Colin O. Wu,et al.  Nonparametric Mixed Effects Models for Unequally Sampled Noisy Curves , 2001, Biometrics.

[25]  P. Perez,et al.  Statistical modelling and prediction of atmospheric pollution by particulate material : two nonparametric approaches , 2001 .

[26]  B. Silverman,et al.  Functional Data Analysis , 1997 .

[27]  Philippe C. Besse,et al.  Autoregressive Forecasting of Some Functional Climatic Variations , 2000 .

[28]  Monique Graf-Jaccottet,et al.  Predictive models for ground ozone and nitrogen dioxide time series , 1998 .

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