Neural networks as an intelligence amplification tool: A review of applications
Author:
- 1 January 2002
- journal article
- review article
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 67 (3) , 979-993
Abstract
The sophisticated algorithms we use to process, analyze, and interpret geophysical data automate tasks we used to do by hand, transform data into domains where patterns are more obvious, and allow us to calculate quantities where we used to rely on intuition or back-of-envelope estimates. But, the crux of the exploration problem is still interpretation—associating abstract patterns with geologic formations of economic value. Artificial neural networks are able to couple the speed and efficiency of the computer with the pattern recognition and association capabilities of the brain to aid the exploration process. The key concept to understand in the application of neural network technology is that they should not be used as an artificial intelligence tool to replace a human interpreter; rather, neural networks are an intelligence amplification toolkit that allows the interpreter to focus on the important information. More than 102 neural network papers have been published by SEG since 1988, and more than 550 neural network papers pertaining to any aspect of geophysics were published in that same time period. Neural network applications in exploration geophysics can generally be divided into two eras. The focus through 1994 was largely on learning what neural networks could do with different data sets, and how to prepare data for them and analyze the results. Networks were usually trained with synthetic data and then tested with field data. The second era, from 1995 to the present, has focused on some specific application areas such as reservoir characterization. The current emphasis is to integrate neural networks within a comprehensive interpretation scheme instead of as a stand-alone application. Neural network technology has helped us turn data into information by allowing us to find nontrivial correlations between geophysical data and petrophysical properties; relate detailed changes in wavelet morphology to small-scale changes in lithology; and find features in the wavelets that allow us to locate first breaks, track horizons, identify gas chimneys, or trace faults; and attenuate multiples. As the science and engineering of data acquisition progresses, neural networks will play an increasingly vital role in helping us find relevant information in the vast streams of data under the constraints of lower costs, less time, and fewer people.Keywords
This publication has 26 references indexed in Scilit:
- Neural networks in geophysical applicationsGeophysics, 2000
- Fracture‐frequency prediction from borehole wireline logs using artificial neural networksGeophysical Prospecting, 1999
- Multiple reflection attenuation in seismic data using backpropagationIEEE Transactions on Signal Processing, 1998
- Inversion of fracture density from field seismic velocities using artificial neural networksGeophysics, 1998
- The application of back‐propagation neural network to automatic picking seismic arrivals from single‐component recordingsJournal of Geophysical Research, 1997
- Permeability prediction with artificial neural network modeling in the Venture gas field, offshore eastern CanadaGeophysics, 1996
- Neural networks and inversion of seismic dataJournal of Geophysical Research, 1994
- AUTOMATED FIRST ARRIVAL PICKING: A NEURAL NETWORK APPROACH1Geophysical Prospecting, 1992
- A general regression neural networkIEEE Transactions on Neural Networks, 1991
- Outline of a theory of thought-processes and thinking machinesJournal of Theoretical Biology, 1961