Petrophysical parameters estimation from well-logs data using multilayer perceptron and radial basis function neural networks

  • Authors:

  • Leila Aliouane;Sid-Ali Ouadfeul;Noureddine Djarfour;Amar Boudella

  • Affiliations:

  • LABOPHYT, Faculté des Hydrocarbures et de la Chimie, Université M'hamad Bougara de Boumerdes, Boumerdes, Algeria,Algerian Petroleum Institute, IAP., Boumerdes, Algeria,Geophysics Departm ...;LABOPHYT, Faculté des Hydrocarbures et de la Chimie, Université M'hamad Bougara de Boumerdes, Boumerdes, Algeria,Algerian Petroleum Institute, IAP., Boumerdes, Algeria,Geophysics Departm ...;LABOPHYT, Faculté des Hydrocarbures et de la Chimie, Université M'hamad Bougara de Boumerdes, Boumerdes, Algeria,Algerian Petroleum Institute, IAP., Boumerdes, Algeria,Geophysics Departm ...;LABOPHYT, Faculté des Hydrocarbures et de la Chimie, Université M'hamad Bougara de Boumerdes, Boumerdes, Algeria,Algerian Petroleum Institute, IAP., Boumerdes, Algeria,Geophysics Departm ...

  • Venue:
  • ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The main objective of this work consists to use the two neural network models to estimate petrophysical parameters from well-logs data. Parameters to be estimated are: Porosity, Permeability and Water saturation. The neural network machines used consist of the Multilayer perceptron (MLP) and the Radial Basis Function (RBF). The main input used to train these neural models is the raw well-logs data recorded in a borehole located in the Algerian Sahara. Comparison between the two neural machines and conventional method shows that the RBF is the most suitable for petrophysical parameters prediction.