Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions. - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Physics: Conference Series Année : 2015

Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions.

, , , , (1)
1
Cyril Voyant
Marie Laure Nivet
  • Fonction : Auteur
  • PersonId : 865253
Christophe Paoli
Marc Muselli
  • Fonction : Auteur
  • PersonId : 841625
Gilles Notton
  • Fonction : Auteur
  • PersonId : 1084516

Résumé

In this paper, we propose to study four meteorological and seasonal time series coupled with a multi-layer perceptron (MLP) modeling. We chose to combine two transfer functions for the nodes of the hidden layer, and to use a temporal indicator (time index as input) in order to take into account the seasonal aspect of the studied time series. The results of the prediction concern two years of measurements and the learning step, eight independent years. We show that this methodology can improve the accuracy of meteorological data estimation compared to a classical MLP modelling with a homogenous transfer function.

Dates et versions

hal-03041989 , version 1 (05-12-2020)

Identifiants

Citer

Cyril Voyant, Marie Laure Nivet, Christophe Paoli, Marc Muselli, Gilles Notton. Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions.. Journal of Physics: Conference Series, 2015, 3rd International Conference on Mathematical Modeling in Physical Sciences (IC-MSQUARE) Aug 2014 Madrid, 574 (1), pp.012064. ⟨10.1088/1742-6596/574/1/012064⟩. ⟨hal-03041989⟩
29 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More