Inversion of fracture density from field seismic velocities using artificial neural networks

Geophysics - Tập 63 Số 2 - Trang 534-545 - 1998
Fred Kofi Boadu1
1Department of Civil & Environmental Engineering, Duke University, 127B Hudson Hall, Box 90287, Durham, North Carolina 27708-0287.

Tóm tắt

The inversion of fracture density from field measured P- and S-wave seismic velocities is performed using a neural network trained with an output from the modified displacement discontinuity fracture model. The basic idea is to use input‐output pairs generated by the fracture model to train the neural network. Once the neural network is trained, inversion of fracture density from field‐measured seismic velocities is performed very quickly. The overall performance of the neural network in the inversion process is assessed by means of a loss function. The results indicate that both sources of field information (P- and S-wave velocities) predict the field fracture density with reasonable accuracy. The performance of the neural network was compared to the prediction from least‐squares fitting. It is shown that the neural network out performs the least‐squares fitting in predicting the field‐fracture density values.

Từ khóa


Tài liệu tham khảo

Aki, K., and Richards, P. G., 1980, Quantitative seismology, theory and methods: W. H. Freeman & Co.

10.1029/JB087iB02p00936

Anderson, E. M., 1985, Electric transmission line fundamentals: Reston Publication Co.

Bishop, C. M., 1995, Neural networks for pattern recognition: Clarendon Press.

Boadu, F. K., 1994, Fractal characterization of fractures: Effect of fractures on seismic wave velocity and attenuation: Ph.D. thesis, Georgia Inst. Tech.

1995, Artificial neural networks: Applications and solutions to geophysical problems: Presented at the Second Joint Conf. on Information Science.

1997a, Fracture rock mass characterization parameters and seismic properties: Analytical studies, J. Appl. Geophys.36, 1–19.

1997b, Rock properties and seismic attenuation: Neural network analysis: Pageoph (in press).

10.1111/j.1365-246X.1996.tb01537.x

10.1111/j.1365-246X.1996.tb01537.x

10.1111/j.1365-246X.1996.tb01537.x

Bury, K. V., 1975, Statistical models in applied science: John Wiley & Sons, Inc.

10.1190/1.1441086

Dowla, F. W., and Rogers, L. L., 1995, Solving problems in environmental engineering and geosciences with artificial neural networks: M.I.T. Press.

10.1190/1.1442365

Garrett, J. H., 1994, Where and why artificial neural networks are applicable in civil engineering, J. Geotechnical Eng.8, 129–130.

Hassoun, M. H., 1995, Fundamentals of artificial neural networks: M.I.T. Press.

10.1190/1.1443850

Idziak, A., 1988, Seismic wave velocity in fractured sedimentary carbonate rocks: Acta Geophysica Polonica,36, 101–114.

O’Donoghue, J. D., and O’Flaherty, R. M., 1977, The underground works at Turlough Hill: Water Power,26, 5–12.

10.1029/JB095iB06p08617

10.1111/j.1365-2478.1979.tb00977.x

10.1029/GL010i008p00686

Worthington, M. H., 1984, An introduction to geophysical tomography: First Break,2, 20–26.