Borehole electrical resistivity modeling using neural networks

A neural network approach has been applied to model downhole resistivity tools, i.e., to generate a synthetic tool response for a given earth resistivity model. The microlaterolog (MLL), shallow dual laterolog (DLLs), and deep dual laterolog (DLLd) tools are modeled using neural networks to demonstrate this approach. Efforts have been made to select various neural network parameters, including the type of neural network, the length of input data for training, the number of hidden nodes, and the number of training samples.A modular neural network (MNN) has been selected because it can facilitate the training and prediction of tool responses in formations with large resistivity variations. The input data for training are taken to be the model formation resistivity values sampled over a depth window. The window length is chosen based on the tool lengths. Three different window lengths are used for experiments: 6.1, 9.1, and 30.5 m. We found the longer window lengths generally have higher modeling accuracy fo...

[1]  H. A. Vallas,et al.  Resistivity-log Inversion Using a Heterogeneous Artificial Neural Network , 1993 .

[2]  D. W. Vasco,et al.  Inversion of gravity gradiometry data using a neural network , 1990 .

[3]  G. Wadge,et al.  Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: an example from the Ocean Drilling Program , 1999 .

[4]  Ralf Birken,et al.  Neural Network Interpretation of High Frequency Electromagnetic Ellipticity Data Part II: Analyzing 3D Responses , 1999 .

[5]  Tsili Wang,et al.  3-D dc resistivity modeling using the sweeping-seed, conjugate-gradient method , 2001 .

[6]  Andrew K. Chan,et al.  Solution of the fundamental problem in resistivity logging with a hybrid method , 1984 .

[7]  Roland Chemali,et al.  The Dual Laterolog In Common Complex Situations , 1988 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  K. V. Paulson,et al.  Magnetotelluric inversion using regularized Hopfield neural networks , 1997 .

[10]  Ralf Andreas Birken.  Neural network interpretation of electromagnetic ellipticity data in a frequency range from 1 kHz to 32 MHz , 1997 .

[11]  Jeffrey L. Baldwin,et al.  Application Of A Neural Network To The Problem Of Mineral Identification From Well Logs , 1990 .

[12]  Weng Cho Chew,et al.  Electromagnetic borehole fields in a layered, dipping‐bed environment with invasion , 1992 .

[13]  NEURAL NETWORK INTERPRETATION OF HIGH-FREQUENCY ELECTROMAGNETIC ELLIPTICITY DATA , 1997 .

[14]  A. Roy.  THE CONCEPT OF APPARENT RESISTIVITY IN LATEROLOG 7 , 1977 .

[15]  Liang C. Shen,et al.  Dual Laterolog Response In 3-D Environments , 1998 .

[16]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[17]  Mirko van der Baan,et al.  Neural networks in geophysical applications , 2000 .

[18]  Lin Zhang,et al.  Fast forward modeling simulation of resistivity well logs using neural networks , 1999 .

[19]  Vladimir Druskin,et al.  Fast Modeling Of Induction And Resistivity Logging In The Model With Mixed Boundaries , 1993 .

[20]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[21]  J. Suau,et al.  The Dual Laterolog-Rxo Tool , 1972 .