A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions

Alain-Louis Dutot (1) , Joseph Rynkiewicz (2, 3) , Frédy E. Steiner (1) , Julien Rude (1)

1 LISA (UMR_7583) - Laboratoire Interuniversitaire des Systèmes Atmosphériques
2 CES - Centre d'économie de la Sorbonne
3 SAMOS - Statistique Appliquée et MOdélisation Stochastique

A neural network combined to a neural classifier is used in a real time forecasting of hourly maximum ozone in the centre of France, in an urban atmosphere. This neural model is based on the MultiLayer Perceptron (MLP) structure. The inputs of the statistical network are model output statistics of the weather predictions from the French National Weather Service. With this neural classifier, the Success Index of forecasting is 78% whereas it is from 65% to 72% with the classical MLPs. During the validation phase, in the Summer of 2003, six ozone peaks above the threshold were detected. They actually were seven.

Domaines: Applications [stat.AP]; Statistiques [math.ST]; Théorie [stat.TH]; Autre; Milieux et Changements globaux

Alain-Louis Dutot, Joseph Rynkiewicz, Frédy E. Steiner, Julien Rude. A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions. Environmental Modelling and Software, 2007, 22 (9), pp.1261-1269. ⟨10.1016/j.envsoft.2006.08.002⟩. ⟨hal-00259126⟩