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

TL;DR

This paper presents a real-time neural network-based method for forecasting hourly maximum ozone levels in France, achieving higher success rates than traditional models by integrating weather prediction data.

Contribution

It introduces a neural classifier combining weather forecast outputs with MLPs for improved ozone peak prediction accuracy.

Findings

Success Index of 78% with neural classifier

Detected 7 ozone peaks in summer 2003

Outperformed classical MLP models

Abstract

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.