Hourly ozone prediction for a 24-h horizon using neural networks

  title={Hourly ozone prediction for a 24-h horizon using neural networks},
  author={Adriana Coman and Anda Ionescu and Yves Candau},
  journal={Environmental Modelling and Software},
This study is an attempt to verify the presence of non-linear dynamics in the ozone time series by testing a ‘‘dynamic’’ model, evaluated versus a ‘‘static’’ one, in the context of predicting hourly ozone concentrations, one-day ahead. The ‘‘dynamic’’ model uses a recursive structure involving a cascade of 24 multilayer perceptrons (MLP) arranged so that each MLP feeds the next one. The ‘‘static’’ model is a classical single MLP with 24 outputs. For both models, the inputs consist of ozone and… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 13 extracted citations


Publications referenced by this paper.
Showing 1-10 of 28 references

A rigorous inter-comparison of ground-level ozone predictions

U. Schlink, S. Dorling, +13 authors M. Doyle
Atmospheric Environment • 2003
View 6 Excerpts
Highly Influenced

Fundamentals of Neural Networks. Architectures, Algorithms and Applications

L. Fausett
View 4 Excerpts
Highly Influenced

Non-parametric short-term prediction of ozone concentration in Berlin

P. Haase, U. Schlink
Proceedings Air Pollution Modelling and Simulation Conference, • 2001
View 4 Excerpts
Highly Influenced

Neural Networks for Pattern Recognition

C. M. Bishop
View 5 Excerpts
Highly Influenced

Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo, Italy

U. Brunelli, V. Piazza, L. Pignato, F. Sorbello, S. Vitabile
Atmospheric Environment • 2007
View 2 Excerpts

Similar Papers

Loading similar papers…