Neural network stochastic simulation applied for quantifying uncertainties

N Foudil-Bey, J Royer, L Cheng, F Erchiqui, J Mareschal

Abstract


Generally the geostatistical simulation methods are used to generate several realizations of physical properties in the sub-surface, these methods are based on the variogram analysis and limited to measures correlation between variables at two locations only. In this paper, we propose a simulation of properties based on supervised Neural network training at the existing drilling data set. The major advantage is that this method does not require a preliminary geostatistical study and takes into account several points. As a result, the geological information and the diverse geophysical data can be combined easily. To do this, we used a neural network with multi-layer perceptron architecture like feed-forward, then we used the back-propagation algorithm with conjugate gradient technique to minimize the error of the network output. The learning process can create links between different variables, this relationship can be used for interpolation of the properties on the one hand, or to generate several possible distribution of physical properties on the other hand, changing at each time and a random value of the input neurons, which was kept constant until the period of learning. This method was tested on real data to simulate multiple realizations of the density and the magnetic susceptibility in three-dimensions at the mining camp of Val d'Or, Québec (Canada).

Full Text:

PDF

References


A. Tarantola, "Popper, Bayes and the inverse problem," Nature Physics, vol. 2, no. 8, pp. 492-494, 2006. CrossRef

A. Tarantola and B. Valette, "Generalized Nonlinear Inverse Problems Solved Using the Least Squares Criterion," Reviews of Geophysics and Space Physics, vol. 20, pp. 219-232, May 1982. CrossRef

W. Menke, Geophysical Data Analysis: Discrete Inverse Theory. Academic Press, Inc. New York, 1984.

M. Poulton, K. Sternberg, and C. Glass, "Neural network pattern recording of the subsurface EM images," Journal of Applied Geophysics, vol. 29, pp. 21-36, 1992. CrossRef

E.-Q. Gad and K. Ushijima, "Inversion of DC resistivity data using neural networks," Geophysical Prospecting, vol. 49, no. 4, pp. 417-430, 2001. CrossRef

C. Calderón-Macías, M. K. Sen, and P. L. Stoffa, "Artificial neural networks for parameter estimation in geophysics," Geophysical Prospecting, vol. 48, no. 1, pp. 21-47, 2000. CrossRef

A. Neyamadpour, W. A. T. W. Abdullah, and S. Taib, "Use of Artificial Neural Networks to Invert 3D Electrical Resistivity Imaging Data," AIP Conference Proceedings, vol. 1150, no. 1, pp. 210-213, 2009.

G. Röth and A. Tarantola, "Neural networks and inversion of seismic data.," Journal of Geophysical Research, vol. 99, pp. 811-822, 1994. CrossRef

N. Metropolis and S. Ulam, "The Monte Carlo method," Journal of the American Statistical Association, vol. 44, pp. 335-341, 1949. CrossRef

J. H. Holland, Adaptation in Natural and Artificial Systems. University of Michigan Press, 1975.

S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, "Optimization by Simulated Annealing," Science, vol. 220, pp. 671-680, May 1983. 10.1126/science.220.4598.671. CrossRef

C. V. Deutsch and A. G. Journel, GSLIB: Geostatistical Software Library and User's Guide, vol. 2nd Edition. Oxford University Press, New York, 1998.

A. Journel and E. Isaaks, "Conditional Indicator Simulation: Application to a Saskatchewan uranium deposit," Mathematical Geology, vol. 16, pp. 685-718, 1984. 10.1007/BF01033030.

T. M. Hansen, A. G. Journel, A. Tarantola, and K. Mosegaard, "Linear inverse Gaussian theory and geostatistics," Geophysics, vol. 71, no. 6, pp. R101-R111, 2006.

M. C. Looms, T. M. Hansen, K. S. Cordua, L. Nielsen, K. H. Jensen, and A. Binley, "Geostatistical inference using crosshole ground-penetrating radar," Geophysics, vol. 75, no. 6, pp. J29-J41, 2010.

E. Gloaguen, D. Marcotte, M. Chouteau, and H. Perroud, "Borehole radar velocity inversion using cokriging and cosimulation," Journal of Applied Geophysics, vol. 57, no. 4, pp. 242-259, 2005. CrossRef

P. Shamsipour, D. Marcotte, M. Chouteau, and P. Keating, "3D stochastic inversion of gravity data using cokriging and cosimulation," Geophysics, vol. 75, no. 1, pp. I1-I10, 2010.

S. Strebelle, "Conditional Simulation of Complex Geological Structures Using Multiple-Point Statistics," Mathematical Geology, vol. 34, pp. 1-21, 2002. 10.1023/A:1014009426274. CrossRef

J. Caers and A. G. Journel, "Stochastic Reservoir Simulation using Neural Networks Trained on Outcrop data," Society of Petroleum Engineers, pp. 27-30 September, 1998. Annual Technical Conference and Exhibition.

J. Caers, "Geostatistical reservoir modelling using statistical pattern recognition," Journal of Petroleum Science and Engineering, vol. 29, pp. 177-188, 2001. CrossRef

T. T. Tran, "Improving variogram reproduction on dense simulation grids," Computers and Geosciences, vol. 20, pp. 1161-1168, August 1994. CrossRef

P. Wong and S. Shibli, "Modelling a fluvial reservoir with multipoint statistics and principal components," Journal of Petroleum Science and Engineering, vol. 31, pp. 157-163, 2001. CrossRef

S. Haykin, Neural Networks A Comprehensive Foundation. Prentice Hall, New Jersey, 1999.

A. Nigrin, Neural Networks for Pattern Recognition. Cambridge, MA: The MIT Press, 1993.

J. Zurada, Introduction To Artificial Neural Systems. Boston: PWS Publishing Company, 1992.

D. E. Rummelhart, G. E. Hinton, and R. Williams, "Learning internal representation by back-propagating errors," Nature, vol. 332, pp. 533-536, 1986.

D. Singer and R. Kouda, "Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan," Mathematical Geology, vol. 28, pp. 1017-1023, 1996. 10.1007/BF02068587. CrossRef

W. M. Brown, T. D. Gedeon, D. I. Groves, and R. G. Barnes, "Artificial neural networks: a new method for mineral prospectivity mapping," Australian Journal of Earth Sciences, vol. 47, no. 4, pp. 757-770, 2000. CrossRef

A. Porwal, E. J. M. Carranza, and M. Hale, "Artificial Neural Networks for Mineral-Potential Mapping: A Case Study from Aravalli Province, Western India," Natural Resources Research, vol. 12, pp. 155-171, 2003. 10.1023/A:1025171803637. CrossRef

E. Werbos, The Roots of Back-Propagation. John Wiley Sons, Inc, 1994.

J. R. Taylor, An Introduction to Error Analysis: The Study of Uncertainties in Physical Measurements 2nd Edition, University Science Books, 1997.

J. Y. F. Yam and T. W. S. Chow, "A weight initialization method for iproving training speed in feedforward neural network," Neurocomputing, vol. 30, pp. 219-232, 2000. CrossRef

E. Johansson, F. Dowla, and D. Goodman, "Backpropagation Learning for Multilayer Feed-Forward Neural Networks Using the Conjugate Gradient Method," International Journal of Neural Systems, vol. 2, no. 4, pp. 291-301, 1991. CrossRef

L. Wong, D. Davis, T. Krogh, and F. Robert, "U-Pb zircon and rutile chronology of Archean greenstone formation and gold mineralization in the Val d'Or region, Québec," Earth and Planetary Science Letters, vol. 104, pp. 325-336, 1991. CrossRef

C. R. Scott, W. U. Mueller, and P. Pilote, "Physical volcanology, stratigraphy, and lithogeochemistry of an Archean volcanic arc: evolution from plume-related volcanism to arc rifting of SE Abitibi Greenstone Belt, Val d'Or, Canada," Precambrian Research, vol. 115, pp. 223-260, 2002. CrossRef

J. K. Mortensen, "U-Pb geochronology of the eastern Abitibi Subprovince. Part 1: Chibougamau-Matagami-Joutel region," Canadian Journal of Earth Sciences, vol. 30, no. 1, pp. 11-28, 1993. CrossRef

W. Mueller and J. Mortensen, "Age constraints and characteristics of subaqueous volcanic construction, the Archean Hunter Mine Group, Abitibi greenstone belt," Precambrian Research, vol. 115, pp. 119-152, 2002. CrossRef




DOI: http://dx.doi.org/10.1260/1750-9548.7.1.31

Copyright (c) 2016 The International Journal of Multiphysics