The Estimation of Stoneley Wave Velocity from Conventional Well Log Data: Using an Integration of Artificial Neural Networks

Stoneley wave velocity (Vst) is capable of providing accurate data for reservoir characterization objectives, such as permeability estimation, fracture evaluation, formation anisotropy identification, etc. At the first stage of this study, different types of artificial neural networks, including generalized regression neural network, radial basis neural network, and feed-forward backpropagation neural network were utilized to predict Vst from conventional well log data. Consequently, a generalized regression neural network was employed to combine results of mentioned artificial neural networks for overall estimation of Vst. This novel hybrid method can enhance the accuracy of final prediction through reaping the benefits of individual artificial neural networks. The proposed methodology, hybrid neural network, was applied in Asmari formation, which is the major carbonate reservoir rock of Iranian southern oil field. A group of 1,640 data points was used to establish the intelligent model, and a group of 800 data points was employed to assess the reliability of the constructed model. Results showed that integration of different artificial neural networks using generalized regression neural network can significantly improve the accuracy of final prediction.

[1]  Muhammad M. Saggaf,et al.  A fuzzy logic approach for the estimation of facies from wire-line logs , 2003 .

[2]  Shahab D. Mohaghegh,et al.  Virtual-Intelligence Applications in Petroleum Engineering: Part 1—Artificial Neural Networks , 2000 .

[3]  Marit Kongslien,et al.  Advanced Mechanical Earth Modelling And Wellbore-Stability Calculation Using Advanced Sonic Measurements: A Case Study on an HP/HT Field in the Norwegian North Sea , 2007 .

[4]  Masoud Nikravesh,et al.  Soft computing and intelligent data analysis in oil exploration , 2003 .

[5]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[6]  T. Endo.  Evaluation of Formation Permeability from Borehole Stoneley Waves , 2006 .

[7]  Richard M. Golden,et al.  Mathematical Methods for Neural Network Analysis and Design , 1996 .

[8]  S. Cuddy,et al.  Litho-Facies and Permeability Prediction from Electrical Logs using Fuzzy Logic , 1998 .

[9]  X. M. Tang,et al.  Detecting Thin Gas Beds In Formations Using Stoneley Wave Reflection And High-Resolution Slowness Measurements , 2001 .

[10]  Bahman Bohloli,et al.  Intelligent approaches for prediction of compressional, shear and Stoneley wave velocities from conventional well log data: A case study from the Sarvak carbonate reservoir in the Abadan Plain (Southwestern Iran) , 2010, Comput. Geosci..

[11]  Xiaoming Tang,et al.  Permeability Determination from Stoneley Waves in the Ara Group Carbonates, Oman , 2001, GeoArabia.

[12]  Constantin Cranganu,et al.  Using Artificial Neural Networks to Predict the Presence of Overpressured Zones in the Anadarko Basin, Oklahoma , 2007 .

[13]  A. Brie,et al.  Using The Stoneley Normalized Differential Energies For Fractured Reservoir Evaluation , 1988 .

[14]  S. Cuddy,et al.  Litho-Facies and Permeability Prediction from Electrical Logs using Fuzzy Logic , 2000 .

[15]  Marit Kongslien,et al.  Enhanced Mechanical Earth Modelling and Wellbore Stability Calculations Using Advanced Sonic Measurements—A Case Study of the HP/HT Kvitebjorn Field in the Norwegian North Sea , 2007 .

[16]  X. M. Tang,et al.  Estimating Formation Permeability And Anistoropy From Borehole Stoneley Waves , 2004 .

[17]  Alejandro Sánchez,et al.  Reservoir characterization using intelligent seismic inversion , 2005 .

[18]  P. M. Wong,et al.  Modeling Porosity Distribution in the A'nan Oilfield: Use of Geological Quantification, Neural Networks, and Geostatistics , 1999 .