Reservoir property prediction using abductive networks
Authors:
- 1 January 2010
- journal article
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 75 (1) , P1-P9
Abstract
Statistical methods, such as linear regression and neural networks, are commonly used to predict reservoir properties from seismic attributes. However, a huge number of attributes can be extracted from seismic data and an efficient method for selecting an attribute subset with the highest correlation to the property being predicted is essential. Most statistical methods, however, lack an optimized approach for this attribute selection. We propose to predict reservoir properties from seismic attributes using abductive networks, which use iterated polynomial regression to derive high-degree polynomial predictors. The abductive networks simultaneously select the most relevant attributes and construct an optimal nonlinear predictor. We applied the approach to predict porosity from seismic data of an area within the 'Uthmaniyah portion of the Ghawar oil field, Saudi Arabia. The data consisted of normal seismic amplitude, acoustic impedance, 16 other seismic attributes, and porosity logs from seven wells located in the study area. Out of 27 attributes, the abductive network selected only the best two to six attributes and produced a more accurate and robust porosity prediction than using the more common neural-network predictors. In addition, the proposed method requires no effort in choosing the attribute subset or tweaking their parameters.Keywords
This publication has 14 references indexed in Scilit:
- Genetic-algorithm/neural-network approach to seismic attribute selection for well-log predictionGeophysics, 2004
- Estimation of effective porosity using geostatistics and multiattribute transforms: A case studyGeophysics, 2004
- Seismic facies classification and identification by competitive neural networksGeophysics, 2003
- Estimation of reservoir properties from seismic data by smooth neural networksGeophysics, 2003
- Case History: Comparison of linear regression and a probabilistic neural network to predict porosity from 3-D seismic attributes in Lower Brushy Canyon channeled sandstones, southeast New MexicoGeophysics, 2001
- Reservoir characterization using seismic waveform and feedforword neural networksGeophysics, 2001
- Use of multiattribute transforms to predict log properties from seismic dataGeophysics, 2001
- Seismic-controlled nonlinear extrapolation of well parameters using neural networksGeophysics, 1998
- Potential risks when using seismic attributes as predictors of reservoir propertiesThe Leading Edge, 1997
- Polynomial Theory of Complex SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1971