Seismic noise filtering based on generalized regression neural networks

Nouredine Djarfour, Jalal Ferahtia, Foudel Babaia, Kamel Baddari, El adj Said, Mohammed Farfour

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper deals with the application of Generalized Regression Neural Networks to the seismic data filtering. The proposed system is a class of neural networks widely used for the continuous function mapping. They are based on the well known nonparametric kernel statistical estimators. The main advantages of this neural network include adaptability, simplicity and rapid training. Several synthetic tests are performed in order to highlight the merit of the proposed topology of neural network. In this work, the filtering strategy has been applied to remove random noises as well as source-related noises from real seismic data extracted from a field in the South of Algeria. The obtained results are very promising and indicate the high performance of the proposed filter in comparison to the well known frequency-wavenumber filter.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalComputers and Geosciences
Volume69
DOIs
Publication statusPublished - 2014

Fingerprint

seismic noise
seismic data
filter
Neural networks
topology
Topology
test
comparison

Keywords

  • Filtering
  • Generalized regression neural networks
  • Random noise
  • Seismic data

ASJC Scopus subject areas

  • Information Systems
  • Computers in Earth Sciences

Cite this

Seismic noise filtering based on generalized regression neural networks. / Djarfour, Nouredine; Ferahtia, Jalal; Babaia, Foudel; Baddari, Kamel; Said, El adj; Farfour, Mohammed.

In: Computers and Geosciences, Vol. 69, 2014, p. 1-9.

Research output: Contribution to journalArticle

Djarfour, Nouredine ; Ferahtia, Jalal ; Babaia, Foudel ; Baddari, Kamel ; Said, El adj ; Farfour, Mohammed. / Seismic noise filtering based on generalized regression neural networks. In: Computers and Geosciences. 2014 ; Vol. 69. pp. 1-9.
@article{eee28338f8f94d01b2a671712aef5712,
title = "Seismic noise filtering based on generalized regression neural networks",
abstract = "This paper deals with the application of Generalized Regression Neural Networks to the seismic data filtering. The proposed system is a class of neural networks widely used for the continuous function mapping. They are based on the well known nonparametric kernel statistical estimators. The main advantages of this neural network include adaptability, simplicity and rapid training. Several synthetic tests are performed in order to highlight the merit of the proposed topology of neural network. In this work, the filtering strategy has been applied to remove random noises as well as source-related noises from real seismic data extracted from a field in the South of Algeria. The obtained results are very promising and indicate the high performance of the proposed filter in comparison to the well known frequency-wavenumber filter.",
keywords = "Filtering, Generalized regression neural networks, Random noise, Seismic data",
author = "Nouredine Djarfour and Jalal Ferahtia and Foudel Babaia and Kamel Baddari and Said, {El adj} and Mohammed Farfour",
year = "2014",
doi = "10.1016/j.cageo.2014.04.007",
language = "English",
volume = "69",
pages = "1--9",
journal = "Computers and Geosciences",
issn = "0098-3004",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Seismic noise filtering based on generalized regression neural networks

AU - Djarfour, Nouredine

AU - Ferahtia, Jalal

AU - Babaia, Foudel

AU - Baddari, Kamel

AU - Said, El adj

AU - Farfour, Mohammed

PY - 2014

Y1 - 2014

N2 - This paper deals with the application of Generalized Regression Neural Networks to the seismic data filtering. The proposed system is a class of neural networks widely used for the continuous function mapping. They are based on the well known nonparametric kernel statistical estimators. The main advantages of this neural network include adaptability, simplicity and rapid training. Several synthetic tests are performed in order to highlight the merit of the proposed topology of neural network. In this work, the filtering strategy has been applied to remove random noises as well as source-related noises from real seismic data extracted from a field in the South of Algeria. The obtained results are very promising and indicate the high performance of the proposed filter in comparison to the well known frequency-wavenumber filter.

AB - This paper deals with the application of Generalized Regression Neural Networks to the seismic data filtering. The proposed system is a class of neural networks widely used for the continuous function mapping. They are based on the well known nonparametric kernel statistical estimators. The main advantages of this neural network include adaptability, simplicity and rapid training. Several synthetic tests are performed in order to highlight the merit of the proposed topology of neural network. In this work, the filtering strategy has been applied to remove random noises as well as source-related noises from real seismic data extracted from a field in the South of Algeria. The obtained results are very promising and indicate the high performance of the proposed filter in comparison to the well known frequency-wavenumber filter.

KW - Filtering

KW - Generalized regression neural networks

KW - Random noise

KW - Seismic data

UR - http://www.scopus.com/inward/record.url?scp=84900403782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900403782&partnerID=8YFLogxK

U2 - 10.1016/j.cageo.2014.04.007

DO - 10.1016/j.cageo.2014.04.007

M3 - Article

VL - 69

SP - 1

EP - 9

JO - Computers and Geosciences

JF - Computers and Geosciences

SN - 0098-3004

ER -