Integration of Ensemble Data Assimilation and Deep Learning for History Matching Facies Models
- Smith Arauco Canchumuni (PUC-RIO) | Alexandre A. Emerick (PETROBRAS) | Marco Aurelio Pacheco (PUC-RIO)
- Document ID
- Offshore Technology Conference
- OTC Brasil, 24-26 October, Rio de Janeiro, Brazil
- Publication Date
- Document Type
- Conference Paper
- 2017. Offshore Technology Conference
- Ensemble Smoother With Multiple Data Assimilation, Facies, Reservoir History Matching, Deep Learning
- 8 in the last 30 days
- 391 since 2007
- Show more detail
- View rights & permissions
Ensemble data assimilation methods have been applied with remarkable success in several real-life history-matching problems. However, because these methods rely on Gaussian assumptions, their performance is severely degraded when the prior geology is described in terms of complex facies distributions. This fact motivated an intense investigation reported in the literature to develop efficient and robust parameterizations. Despite the large number of publications, preserving plausible geological features when updating facies models is still one of the main challenges with ensemble-based history matching.
This work reports our initial results towards the development of a robust parameterization based on Deep Learning (DL) for proper history matching of facies models with ensemble methods. The process begins with a set of prior facies realizations, which are used for training a DL network. DL identifies the main features of the facies images, allowing the construction of a reduced parameterization of the models. This parameterization is transformed to follow a Gaussian distribution, which is updated to account for the dynamic observed data using the method known as ensemble smoother with multiple data assimilation (ES-MDA). After each data assimilation, DL is used to reconstruct the facies models based on the initial learning. The proposed method is tested in a synthetic history-matching problem based on the well-known PUNQ-S3 case. We compare the results of the proposed method against the standard ES-MDA (with no parameterization) and another parameterization based on principal component analysis.
|File Size||3 MB||Number of Pages||13|
C. C. Agbalaka and D. S. Oliver. Application of the EnKF and localization to automatic history matching of facies distribution and production data. Mathematical Geosciences, 40(4):353–374, 2008. doi: 10.1007/s11004-008-9155-7.
M. Armstrong, A. Galli, H. Beucher, G. L. Loc'h, D. Renard, B. Doligez, R. Eschard, and F. Geffroy. Plurigaussian Simulations in Geosciences. Springer-Verlag Berlin Heidelberg, 2nd edition, 2011. doi: 10.1007/978-3-642-19607-2.
H. Chang, D. Zhang, and Z. Lu. History matching of facies distributions with the EnKF and level set parameterization. Journal of Computational Physics, 229:8011–8030, 2010. doi: 10.1016/j.jcp.2010.07.005.
C. Chen, G. Gao, P. Gelderblom, and E. Jimenez. Integration of cumulative-distribution-function mapping with principal- component analysis for the history matching of channelized reservoirs. SPE Reservoir Evaluation & Engineering, 19(2): 278–293, 2016. doi: 10.2118/170636-PA.
Y. Chen and D. S. Oliver. History matching of the Norne full-field model with an iterative ensemble smoother. SPE Reservoir Evaluation & Engineering, 17(2), 2014. doi: 10.2118/164902-PA.
A. Cominelli, L. Dovera, S. Vimercati, and G. Nsvdal. Benchmark study of ensemble Kalman filter methodology: History matching and uncertainty quantification for a deep-water oil reservoir. In Proceedings of the International Petroleum Technology Conference, Doha, Qatar, 7-9 December, number IPTC 13748, 2009. doi: 10.2523/13748-MS.
X. Deng, X. Tian, S. Chen, and C. J. Harris. Deep learning based nonlinear principal component analysis for industrial process fault detection. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), 2017. doi: 10.1109/IJCNN.2017.7965994.
A. A. Emerick. Analysis of the performance of ensemble-based assimilation of production and seismic data. Journal of Petroleum Science and Engineering, 139:219–239, 2016. doi: 10.1016/j.petrol.2016.01.029.
A. A. Emerick. Investigation on principal component analysis parameterizations for history matching channelized facies models with ensemble-based data assimilation. Mathematical Geosciences, 49(1):85–120, 2017. doi: 10.1007/s11004-016-9659-5.
A. A. Emerick and A. C. Reynolds. History matching a field case using the ensemble Kalman filter with covariance localization. SPE Reservoir Evaluation & Engineering, 14(4):423–432, 2011. doi: 10.2118/141216-PA.
A. A. Emerick and A. C. Reynolds. Ensemble smoother with multiple data assimilation. Computers & Geosciences, 55: 3–15, 2013a. doi: 10.1016/j.cageo.2012.03.011.
A. A. Emerick and A. C. Reynolds. History matching of production and seismic data for a real field case using the ensemble smoother with multiple data assimilation. In Proceedings of the SPE Reservoir Simulation Symposium, The Woodlands, Texas, USA, 18-20 February, number SPE 163675, 2013b. doi: 10.2118/163675-MS.
F. Evensen, J. Hove, H. C. Meisingset, E. Reiso, K. S. Seim, and Ø. Espelid. Using the EnKF for assisted history matching of a North Sea reservoir model. In Proceedings of the SPE Reservoir Simulation Symposium, Houston, Texas, 26-28 February, number SPE 106184, 2007. doi: 10.2118/106184-MS.
V. Haugen, G. Nsvdal, L.-J. Natvik, G. Evensen, A. M. Berg, and K. M. Flornes. History matching using the ensemble Kalman filter on a North Sea field case. SPE Journal, 13(4):382–391, 2008. doi: 10.2118/102430-PA.
Y. LeCun, Y. Bengio, and G. Hinton. Deep learning. Nature, 521:436–444, 2015. doi: 10.1038/nature14539.
N. Liu and D. S. Oliver. Ensemble Kalman filter for automatic history matching of geologic facies. Journal of Petroleum Science and Engineering, 47(3-4):147–161, 2005. doi: 10.1016/j.petrol.2005.03.006.
P. K. Muthukumar and A. W. Black. A deep learning approach to data-driven parameterizations for statistical parametric speech synthesis. arXiv:1409.8558 [cs.CL], 2014. URL http://arxiv.org/abs/1409.8558.
J. Ping and D. Zhang. History matching of channelized reservoirs with vector-based level-set parameterization. SPE Journal, 19(3):514–529, 2014. doi: 10.2118/169898-PA.
P. Sarma, L. J. Durlofsky, and K. Aziz. Kernel principal component analysis for efficient differentiable parameterization of multipoint geostatistics. Mathematical Geosciences, 40(1):3–32, 2008. doi: 10.1007/s11004-007-9131-7.
B. M. Sebacher, R. Hanea, and A. Heemink. A probabilistic parametrization for geological uncertainty estimation using the ensemble Kalman filter (EnKF). Computational Geosciences, 17(5):813–832, 2013. doi: 10.1007/s10596-013-9357-z.
S. Strebelle. Conditional simulation of complex geological structures using multiple-point statistics. Mathematical Geology, 34(1):1–21, 2002. doi: 10.1023/A:1014009426274.
G. X. Vo and L. J. Durlofsky. A new differentiable parameterization based on principal component analysis for the lowdimensional representation of complex geological models. Mathematical Geosciences, 46(7):775–813, 2014. doi: 10.1007/s11004-014-9541-2.
Y. Zhang and D. S. Oliver. History matching using the ensemble Kalman filter with multiscale parameterization: A field case study. SPE Journal, 16(2):307–317, 2011. doi: 10.2118/118879-PA.
Y. Zhao, A. C. Reynolds, and G. Li. Generating facies maps by assimilating production data and seismic data with the ensemble Kalman filter. In Proceedings of the SPE Improved Oil Recovery Symposium, Tulsa, Oklahoma, 20-23 April, number SPE 113990, 2008. doi: 10.2118/113990-MS.