Modélisation spatio-temporelle de la pollution atmosphérique urbaine à partir d'un réseau de surveillance de la qualité de l'air

Cette etude est consacree a la modelisation spatio-temporelle de la pollution atmospherique urbaine en utilisant un ensemble de methodes statistiques exploitant les mesures de concentrations de polluants (NO2, O3) fournies par un reseau de surveillance de la qualite de l'air (AIRPARIF). Le principal objectif vise est l'amelioration de la cartographie des champs de concentration de polluants (le domaine d'interet etant la region d'Ile-de-France) en utilisant, d'une part, des methodes d'interpolation basees sur la structure spatiale ou spatio-temporelle des observations (krigeage spatial ou spatio-temporel), et d'autre part, des algorithmes, prenant en compte les mesures, pour corriger les sorties d'un modele deterministe (Filtre de Kalman d'Ensemble). Les resultats obtenus montrent que dans le cas du dioxyde d'azote la cartographie basee uniquement sur l'interpolation spatiale (le krigeage) conduit a des resultats satisfaisants, car la repartition spatiale des stations est bonne. En revanche, pour l'ozone, c'est l'assimilation sequentielle de donnees appliquee au modele (CHIMERE) qui permet une meilleure reconstitution de la forme et de la position du panache pendant les episodes de forte pollution analyses. En complement de la cartographie, un autre but de ce travail est d'effectuer localement la prevision des niveaux d'ozone sur un horizon de 24 heures. L'approche choisie est celle mettant en œuvre des methodes de type reseaux neuronaux. Les resultats obtenus en appliquant deux types d'architectures neuronales indiquent une precision correcte surtout pour les 8 premieres heures de l'horizon de prediction

[1]  Jacques Verron,et al.  A singular evolutive extended Kalman filter for data assimilation in oceanography , 1998 .

[2]  P. Goovaerts,et al.  Study of Spatial and Temporal Variations of Hydrogeochemical Variables Using Factorial Kriging Analysis , 1993 .

[3]  W. Dab,et al.  Air pollution and doctors' house calls: Results from the ERPURS system for monitoring the effects of air pollution on public health in Greater Paris, France, 1991-1995 , 1997 .

[4]  Yves Candau,et al.  Air pollutant emissions prediction by process modelling - Application in the iron and steel industry in the case of a re-heating furnace , 2007, Environ. Model. Softw..

[5]  F. L. Dimet,et al.  Variational algorithms for analysis and assimilation of meteorological observations: theoretical aspects , 1986 .

[6]  C. N. Hewitt,et al.  Biogenic emissions in Europe: 1. Estimates and uncertainties , 1995 .

[7]  P. Viotti,et al.  Atmospheric urban pollution: applications of an artificial neural network (ANN) to the city of Perugia , 2002 .

[8]  Shahrokh Rouhani,et al.  Multivariate geostatistical trend detection and network evaluation of space-time acid deposition data—I. Methodology , 1992 .

[9]  P. Houtekamer,et al.  A Sequential Ensemble Kalman Filter for Atmospheric Data Assimilation , 2001 .

[10]  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 .

[11]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[12]  Tomislav Hengl,et al.  Comparison of kriging with external drift and regression-kriging. Technical report , 2003 .

[13]  P. Kitanidis.  Generalized covariance functions in estimation , 1993 .

[14]  J. Seinfeld.  Atmospheric Chemistry and Physics of Air Pollution , 1986 .

[15]  Grace Wahba,et al.  Spline Models for Observational Data , 1990 .

[16]  S. Rouhani,et al.  Multivariate geostatistical trend detection and network evaluation of space-time acid deposition data—II. Application to NADP/NTN data , 1992 .

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

[18]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[19]  Stanislav Kolenikov,et al.  Spatiotemporal modeling of PM2.5 data with missing values , 2003 .

[20]  G. Matheron.  Principles of geostatistics , 1963 .

[21]  Arjo Segers,et al.  Data Assimilation in Atmospheric Chemistry Models Using Kalman Filtering , 2002 .

[22]  Jan G. Verwer,et al.  Gauss-Seidel Iteration for Stiff ODES from Chemical Kinetics , 1994, SIAM J. Sci. Comput..

[23]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[24]  G. Matheron.  Les variables régionalisées et leur estimation : une application de la théorie de fonctions aléatoires aux sciences de la nature , 1965 .

[25]  Robert Vautard,et al.  Validation of a hybrid forecasting system for the ozone concentrations over the Paris area , 2001 .

[26]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[27]  C. L. Ajaunie.  Geostatistical Approaches to Change of Support Problems – Theoretical Framework – , 2000 .

[28]  Gavin C. Cawley,et al.  A rigorous inter-comparison of ground-level ozone predictions , 2003 .

[29]  Peter K. Kitanidis,et al.  PARAMETRIC ESTIMATION OF COVARIANCES OF REGIONALIZED VARIABLES , 1987 .

[30]  R. M. Lark,et al.  The Matérn variogram model: Implications for uncertainty propagation and sampling in geostatistical surveys , 2007 .

[31]  I. Rodríguez‐Iturbe,et al.  On the synthesis of random field sampling from the spectrum: An application to the generation of hydrologic spatial processes , 1974 .

[32]  Robert Vautard,et al.  Sensitivity of photochemical pollution using the adjoint of a simplified chemistry‐transport model , 2000 .

[33]  Montserrat Fuentes,et al.  Recent advances in space‐time statistics with applications to environmental data: An overview , 2003 .

[34]  Anthony Hollingsworth,et al.  The statistical structure of short-range forecast errors as determined from radiosonde data , 1986 .

[35]  Robert N. Miller,et al.  Data assimilation into nonlinear stochastic models , 1999 .

[36]  Shahrokh Rouhani,et al.  Multivariate geostatistical approach to space‐time data analysis , 1990 .

[37]  Gavin C. Cawley,et al.  Modelling SO2 concentration at a point with statistical approaches , 2004, Environ. Model. Softw..

[38]  Gilbert Saporta,et al.  Probabilités, Analyse des données et statistique , 1991 .

[39]  S. A. Seguret.  Filtering Periodic Noise by Using Trigonometric Kriging , 1989 .

[40]  Milan Paluš,et al.  Nonlinearity and Prediction of Air Pollution , 2001 .

[41]  P. S. Maybeck,et al.  Stochastics Models, Estimation, and Control: Introduction , 1979 .

[42]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[43]  Gavin C. Cawley,et al.  Statistical models to assess the health effects and to forecast ground-level ozone , 2006, Environ. Model. Softw..

[44]  G. Matheron.  The intrinsic random functions and their applications , 1973, Advances in Applied Probability.

[45]  P. Houtekamer,et al.  Data Assimilation Using an Ensemble Kalman Filter Technique , 1998 .

[46]  Phaedon C. Kyriakidis,et al.  Geostatistical Space–Time Models: A Review , 1999 .