Smooth regression to estimate effective porosity using seismic attributes

Abstract Data mining is very important to characterize complex geological structures, where a large variety of geophysical and petrophysical variables are typically involved and interrelated. In this paper we apply smooth regression for data analysis, by means of the Gamma test (a revolutionary estimator of the noise in a data set) to aid in the construction of Artificial Neural Network (ANN) models to predict effective porosity (φe) using seismic attributes. As a result, we obtain the best combination of seismic attributes to estimate φe. We briefly describe the Gamma test, its benefits in model identification and model building. The first validation of the Neural Network based on leave-one-out was poor. Therefore, we generate a complementary set of synthetic data (from the original well-log data), varying the effective porosity and applying the Gassmann's equation for fluid substitution to obtain resulting velocities and densities. The complete procedure is repeated including the new synthetic well-logs and the best suited selection of seismic attributes is used to train a new ANN producing a better validation and more accurate results. The advantage of smooth regression over other techniques is that it tells us how well we can predict φe using any model. This information saves time during training of the ANN and also sets a lower bound for the mean squared error to prevent over-training.

[1]  C. Kalkomey,et al.  Potential risks when using seismic attributes as predictors of reservoir properties , 1997 .

[2]  John P. Castagna,et al.  Offset-dependent reflectivity : theory and practice of AVO analysis , 1993 .

[3]  F. Gaßmann.  Uber die Elastizitat poroser Medien. , 1961 .

[4]  Mohammad Karamouz,et al.  Input data selection for solar radiation estimation , 2009 .

[5]  Antonia J. Jones,et al.  New tools in non-linear modelling and prediction , 2004, Comput. Manag. Sci..

[6]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[7]  E. Baysal,et al.  Seismic attributes revisited , 1994 .

[8]  Kevin P. Dorrington,et al.  Genetic‐algorithm/neural‐network approach to seismic attribute selection for well‐log prediction , 2004 .

[9]  Michael Batzle,et al.  Gassmann's equation and fluid‐saturation effects on seismic velocities , 2004 .

[10]  C. G. Broyden.  The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations , 1970 .

[11]  G. Backus.  Long-Wave Elastic Anisotropy Produced by Horizontal Layering , 1962 .

[12]  Nenad Koncar,et al.  A note on the Gamma test , 1997, Neural Computing & Applications.

[13]  M. Taner,et al.  Complex seismic trace analysis , 1979 .

[14]  Dafydd Evans.  Data-derived estimates of noise for unknown smooth models using near-neighbour asymptotics , 2002 .

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

[16]  Bjørn Ursin,et al.  Porosity and permeability prediction from wireline logs using artificial neural networks: a North Sea case study , 2001 .

[17]  John P. Castagna,et al.  Comparison of AVO indicators: A modeling study , 1994 .

[18]  Amit Kumar Srivastava,et al.  Estimation of effective porosity using geostatistics and multiattribute transforms: A case study , 2004 .

[19]  Antonia J. Jones,et al.  Asymptotic moments of near–neighbour distance distributions , 2002, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[20]  Antonia J. Jones,et al.  Non-parametric estimation of residual moments and covariance , 2008, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[21]  C. G. Broyden.  The Convergence of a Class of Double-rank Minimization Algorithms 2. The New Algorithm , 1970 .

[22]  John Quirein,et al.  Use of multiattribute transforms to predict log properties from seismic data , 2001 .

[23]  Roderick W. Van Koughnet,et al.  Sequential backus averaging; upscaling well logs to seismic wavelengths , 2001 .

[24]  Antonia J. Jones,et al.  The Gamma Test , 2002 .

[25]  A. J. Jones,et al.  A proof of the Gamma test , 2002, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[26]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[27]  D. Goldfarb.  A family of variable-metric methods derived by variational means , 1970 .

[28]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[29]  J. White,et al.  Underground Sound: Application of Seismic Waves , 1983 .

[30]  Antonia J. Jones,et al.  Feature selection for genetic sequence classification , 1998, Bioinform..

[31]  A. B. Wood.  A Text Book Of Sound , 1941 .

[32]  Quincy Chen,et al.  Seismic attribute technology for reservoir forecasting and monitoring , 1997 .

[33]  T. Mukerji,et al.  The Rock Physics Handbook: Contents , 2009 .

[34]  A. Bhatt,et al.  Committee neural networks for porosity and permeability prediction from well logs , 2002 .

[35]  Arthur E. Barnes,et al.  Short Note The calculation of instantaneous frequency and instantaneous bandwidth , 1992 .

[36]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[37]  John Quirein,et al.  Multiattribute seismic analysis , 1997 .

[38]  Christian Gastaldi,et al.  Reservoir characterization from seismic attributes: An example from the Peciko Field (Indonesia) , 1997 .

[39]  K. Marfurt,et al.  Seismic attributes — A historical perspective , 2005 .