Prediction of spring discharge by neural networks using orthogonal wavelet decomposition - IMT Mines Alès Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Prediction of spring discharge by neural networks using orthogonal wavelet decomposition

Résumé

Neural networks are increasingly used in the field of hydrology due to their properties of parsimony and universal approximation with regard to nonlinear systems. Nevertheless, as a result of the non stationarity of natural variables (rainfalls and consequently discharges) it appeared as difficult to capture both dynamics (roughly slow and fast) in a same neural network while their respective behaviors cannot be fully dissociated. For this reason the identification of the behavior of a complex aquifer, such as the aquifer of the Lez spring addressed in this study, is not yet fully achieved. Taking profit of such an analysis this paper presents an original way to decompose the behavior of the aquifer in several independent components using the powerful tool of multiresolution analysis. The method allows thus to perform discharge prediction without rainfalls prediction up to three days ahead increasing considerably the performance of the predictive methods.

Domaines

Risques
Fichier non déposé

Dates et versions

hal-04662914 , version 1 (26-07-2024)

Identifiants

Citer

Anne Johannet, Line Kong a Siou, Alain Mangin, Valérie Borrell Estupina, Séverin Pistre, et al.. Prediction of spring discharge by neural networks using orthogonal wavelet decomposition. 2012 International Joint Conference on Neural Networks (IJCNN 2012 - Brisbane), Jun 2012, Brisbane, Australia. pp.1-8, ⟨10.1109/IJCNN.2012.6252620⟩. ⟨hal-04662914⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More