Skip to Main content Skip to Navigation
Conference papers

Tomographic velocity images by Radial Basis Function Artificial Neural Network

Noureddine Djarfour 1 Jalal Ferahtia 1 Kamel Baddari 1 Tahar Aifa 2
1 LABOPHYT - Laboratoire de Physique de la Terre
2 Systèmes Tectoniques
GR - Géosciences Rennes
Abstract : The seismic tomography can be used to constrain estimates of the Earth's velocity structure. This kind of problem is usually known to be non-linear, high-dimensional, with a complex search space which may be riddled with many local minima, and results in irregular objective functions. We investigate here the performance and the application of a radial basis function artificial neural network (RBF-ANN) type, in the tomographic velocity reconstruction. The proposed structure has the advantage of being easily trained by means of a backpropagation algorithm without getting stuck in local minima. An adequate cross-validation test is run to ensure the performance of the network on new data sets. The application of such a network to synthetic data shows that the inverted seismic velocity section was efficient. A comparative reconstruction with tow classical methods was performed using Algebraic Reconstruction Technique (ART) Conjugate Gradient (CG). The results clearly show improvements of the quality of the reconstruction obtained by radial basis function artificial neural network.
Keywords : ART radial basis function neuron networks training traveltime velocity tomography CG ART.
Document type :
Conference papers
Complete list of metadata
https://hal-insu.archives-ouvertes.fr/insu-00612284
Contributor : Isabelle Dubigeon Connect in order to contact the contributor
Submitted on : Thursday, July 28, 2011 - 3:39:24 PM
Last modification on : Tuesday, October 19, 2021 - 7:01:30 PM

Identifiers

  • HAL Id : insu-00612284, version 1

Collections

INSU | CNRS | UNIV-RENNES1 | OSUR | GR | GR-3T | UNIV-RENNES | UR1-ENV

Citation

Noureddine Djarfour, Jalal Ferahtia, Kamel Baddari, Tahar Aifa. Tomographic velocity images by Radial Basis Function Artificial Neural Network. IEEE-2011 International Conference on Communications, Computing and Control Applications (CCCA'11), Mar 2011, Hammamet, Tunisia. PID1622973, p.65. ⟨insu-00612284⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

61