Abstract
We present a framework that enables estimation of low-dimensional sub-resolution reservoir properties directly from seismic data, without requiring the solution of a high dimensional seismic inverse problem. Our workflow is based on the Bayesian evidential learning approach and exploits learning the direct relation between seismic data and reservoir properties to efficiently estimate reservoir properties. The theoretical framework we develop allows incorporation of non-linear statistical models for seismic estimation problems. Uncertainty quantification is performed with approximate Bayesian computation. With the help of a synthetic example of estimation of reservoir net-to-gross and average fluid saturations in sub-resolution thin sand reservoir, several nuances are foregrounded regarding the applicability of unsupervised and supervised learning methods for seismic estimation problems. Finally, we demonstrate the efficacy of our approach by estimating posterior uncertainty of reservoir net-to-gross in sub-resolution thin sand reservoir from an offshore delta dataset using 3D pre-stack seismic data.
Similar content being viewed by others
References
Aleardi, M., Ciabarri, F.: Assessment of different approaches to rock-physics modeling: a case study from offshore Nile Delta. Geophysics. 82(1), MR15–MR25 (2017). https://doi.org/10.1190/geo2016-0194.1
Aleardi, M., Ciabarri, F., Calabrò, R.: Two-stage and single-stage seismic-petrophysical inversions applied in the Nile Delta. Lead. Edge. 37(7), 510–518 (2018). https://doi.org/10.1190/tle37070510.1
Aleardi, M.: Applying a probabilistic seismic-petrophysical inversion and two different rock-physics models for reservoir characterization in offshore Nile Delta. J. Appl. Geochem. 148, 272–286 (2018). https://doi.org/10.1016/j.jappgeo.2017.12.006
Aki, K., Richards, P.G.: Quantitative seismology. W. H. Freeman & Co, Washington, D.C. (1980)
Avseth, P., Mukerji, T., Mavko, G.: Quantitative Seismic Interpretation. Cambridge University Press, Cambridge (2005)
Beaumont, M.A., Zhang, W., Balding, D.J.: Approximate Bayesian computation in population genetics. Genetics. 162, 2025–2035 (2002)
Beaumont, M.A.: Approximate Bayesian computation in evolution and ecology. Annu. Rev. Ecol. Evol. Syst. 41, 379–406 (2010)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798–1828 (2013)
Blum, M.G.B.: Approximate Bayesian computation: a nonparametric perspective. J. Am. Stat. Assoc. 105, 1178–1187 (2010a) MR2752613
Blum, M.G.B.: Choosing the summary statistics and the acceptance rate in approximate Bayesian computation. In: Saporta, G., Lechevallier, Y. (eds.) COMPSTAT 2010: Proceedings in Computational Statistics, pp. 47–56. Springer, New York (2010b)
Blum, M.G.B., Nunes, M.A., Prangle, D., Sisson, S.A.: A comparative review of dimension reduction methods in approximate Bayesian computation. Stat. Sci. 28(2), 189–208 (2013)
Borg, I., Groenen, P.: Modern Multidimensional Scaling: Theory and Applications. Springer (1997)
Bosch, M., Mukerji, T., Gonzalez, E.F.: Seismic inversion for reservoir properties combining statistical rock physics and geostatistics: a review. Geophysics. 75(5), A165–A176 (2010). https://doi.org/10.1190/1.3478209
Cunningham, P.: In: Cord, M., Cunningham, P. (eds.) Dimension reduction: Machine learning techniques for multimedia: case studies on organization and retrieval. Springer (2008)
Daubechies, I.: Ten lectures on wavelets, CBMS-NSF conference series in applied mathematics, SIAM Ed (1992)
Dejtrakulwong, P.: Rock physics and seismic signatures of sub-resolution sand-shale systems: Ph.D. Thesis, Stanford University, California (2012)
Dejtrakulwong, P., Mukerji, T., Mavko, G.: Using kernel principal component analysis to interpret seismic signatures of thin shaly-sand reservoirs. SEG Exp. Abstr. (2012). https://doi.org/10.1190/segam2012-1013.1
Deutsch, C., Journel, A.G.: GSLIB: geostatistical software library and user’s guide. Oxford University Press, London (1992)
Donoho, D.L., Johnstone, I.M.: Ideal spatial adaptation by wavelet shrinkage. Biometrika. 81, 425–455 (1994) MR1311089
Donoho, D., Johnstone, I., Kerkyacharia, G., Picard, D.: Wavelet shrinkage: asymptopia? (with discussion). J. Roy. Statist. Soc. Ser.B. 57, 301–337 (1995) MR1323344
Eidsvik, J., Mukerji, T., Switzer, P.: Estimation of geological attributes from a well log: an application of hidden Markov chains. Math. Geol. 36(3), 379–397 (2004)
Fearnhead, P., Prangle, D.: Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. J. R. Stat. Soc. Ser. B Stat Methodol. 74(3), 419–474 (2012)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. The MIT Press, Cambridge (2016)
Goovaerts, P.: Geostatistics for natural resources evaluation. Oxford University Press, London (1997)
Grana, D., Mukerji, T., Dvorkin, J., Mavko, G.: Stochastic inversion of facies from seismic data based on sequential simulations and probability perturbation method. Geophysics. 77(4), M53–M72 (2012). https://doi.org/10.1190/geo2011-0417.1
Hermans, T., Oware, E., Caers, J.: Direct prediction of spatially and temporally varying physical properties from time-lapse electrical resistance data. Water Resour. Res. 52(9), 7262–7283. ISSN 19447973 (2016). https://doi.org/10.1002/2016WR019126
Hinton, G. E., Zemel, R. S.: Autoencoders, minimum description length, and helmholtz free energy. In: NIPS, 1993 (1994)
Hinton, G.E., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science. 313(5786), 504–507 (2006)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37(ICML’15), vol. 37, pp. 448–456 (2015) JMLR.org
Jiang, B., T.-y. Wu, C. Zheng, and W. H. Wong, 2015, Learning summary statistic for approximate Bayesian computation via deep neural network. arXiv preprint arXiv:1510.02175
Kingma, D., and J. Ba, 2014, Adam: a method for stochastic optimization: arXiv preprint arXiv:1412.6980
Lee, H., Ekanadham, C., Ng, A.: Sparse deep belief net model for visual area V2. In: Platt, J., Koller, D., Singer, Y., Roweis, S.P. (eds.) Advances in Neural Information Processing Systems 20 (NIPS’07). MIT Press, Cambridge, MA (2008)
Li, L., A Bayesian approach to causal and evidential analysis for uncertainty quantification throughout the reservoir forecasting process: Ph.D. Thesis, Stanford University, California (2017)
Mallat, S.: A wavelet tour of signal processing, 2nd edn. Academic Press, San Diego (1999)
Marion, D., Nur, A., Yin, H., Han, D.: Compressional velocity and porosity in sand-clay mixtures. Geophysics. 60(1), 241–251 (1992)
Mavko, G., Mukerji, T., Dvorkin, J.: The rock physics handbook, 2nd edn. Cambridge University Press, Cambridge (2009)
Moore, B.: Principal component analysis in linear systems: controllability, observability, and model reduction. IEEE Trans. Autom. Control. 26(1), 17–32 (1981)
Rousseeuw, P.J., Van Zomeren, B.C.: Unmasking multivariate outliers and leverage points. J. Am. Stat. Assoc. 85(411), 633–651 (1990)
Rousseeuw, P.J., Van Driessen, K.: A fast algorithm for the minimum covariance determinant estimator. Technometrics. 41, 212–223 (1999)
Satija, A., Caers, J.: Direct forecasting of subsurface flow response from non-linear dynamic data by linear least-squares in canonical functional principal component space. Adv. Water Resour. 77, 69–81, ISSN 03091708 (2015). https://doi.org/10.1016/j.advwatres.2015.01.002
Satija, A., Scheidt, C., Li, L., Caers, J.: Direct forecasting of reservoir performance using production data without history matching. Comput. Geosci. 21(2), 315–333 (2017)
Scheidt, C., Renard, P., Caers, J.: Prediction-focused subsurface modeling: investigating the need for accuracy in flow-based inverse modeling. Math. Geosci. 47(2), 173–191, ISSN 18748953 (2014). https://doi.org/10.1007/s11004-014-9521-6
Scheidt, C., Li, L., Caers, J.: Quantifying uncertainty in subsurface systems. Wiley-Blackwell, New Jerseys (2017)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Scott, D.W., Tapia, R.A., Thompson, R.A.: Kernel density estimation revisited: nonlinear analysis. Theory Methods Appl. 1, 339–372 (1977)
Silverman, B.W.: Density estimation for statistics and data analysis. Chapman & Hall, London (1986)
Sisson, S. and Y. Fan, 2010, Likelihood-free Markov chain Monte Carlo: arXiv preprint arXiv:1001.2058
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Tarantola, A.: Inverse problem theory and methods for model parameter estimation: SIAM (2005)
Vidakovic, B.: Statistical modeling by wavelets, p. MR1681904. John Wiley & Sons, New York (1999)
Wegmann, D., Leuenberger, C., Excoffier, L.: Efficient approximate Bayesian computation coupled with Markov chain Monte Carlo without likelihood. Genetics. 182(4), 1207–1218 (2009)
Walden, A.T., White, R.E.: Seismic wavelet estimation: a frequency domain solution to a geophysical noisy input-output problem. IEEE Trans. Geosci. Remote Sens. 36, 287–297 (1998)
Acknowledgements
This work is supported by the sponsors of the Stanford Center for Earth Resources Forecasting (SCERF), and support from the Dean of the Stanford School of Earth, Energy, and Environmental Sciences, Professor Steve Graham. We thank Edison E&P for providing the dataset for the real case application. We offer special thanks to Dr. Fabio Ciabarri for his advice and assistance regarding various aspects of the real dataset. We would also like to thank Professor Jef Caers for insightful discussions regarding the methodology.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Pradhan, A., Mukerji, T. Seismic Bayesian evidential learning: estimation and uncertainty quantification of sub-resolution reservoir properties. Comput Geosci 24, 1121–1140 (2020). https://doi.org/10.1007/s10596-019-09929-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-019-09929-1