Abstract
Various types of geophysical measurements have been made available to illuminate different characteristics of subsurface reservoir formations. It becomes crucial to both efficiently and effectively utilize the information contained in these measurements for enhanced reservoir characterization and more informative decision-making support. To address the problem, image-oriented history matching approaches were proposed, which have shown promising results in efficiently assimilating multiple types of geophysical measurements. Relying on the interpretability of geophysical measurements, image-oriented strategies seek to match the extracted features or patterns (e.g., water front positions from the inverted saturation field) instead of the original data in the model update step. Consequently, the quality of the extracted features directly impacts the performance of these methods. However, extracting reliable features from related geophysical data is not straightforward. It requires not only in-depth domain knowledge but also appropriate image processing techniques. This study explores the use of deep learning (DL) based image segmentation techniques as an alternative to assist the feature extraction for an image-oriented ensemble-based history matching workflow. Accounting for the special characteristics of the considered application, a fast unsupervised DL segmentation model based on the convolutional neural network (CNN) is used together with an image denoising algorithm. The developed workflow separates the history matching of geophysical data into two sequential steps. It starts with a (joint) geophysical inversion step for saturation mapping, followed by a featured-oriented assimilation step to match the inverted saturation field, in which water front positions are extracted using the DL-based segmentation model. We test the proposed workflow on a synthetic reservoir model to history match electromagnetic (EM) and seismic data, which illustrates its promising performance in extracting relevant information from the data for efficient history matching.
Similar content being viewed by others
Data availability
The data generated or analysed during this study are available from the corresponding authors on reasonable request.
Abbreviations
- CNN:
-
Convolutional neural network
- DL:
-
Deep learning
- EM:
-
Electromagnetic
- EnKF:
-
Ensemble Kalman filter
- HM:
-
History matching
- NLM:
-
Non-local means denoising
- SHM:
-
Seismic history matching
- \(\mathbf{c}\) :
-
Binary map
- \({\mathbf{d}}_{obs}\) :
-
Observed data
- \({\mathbf{d}}_{sim }\) :
-
Simulated data
- \({\mathbf{D}}_{obs}\) :
-
Ensemble of perturbed observations
- \(\varDelta \mathbf{D}\) :
-
Matrix of data misfit
- \(f\left(\cdot \right)\) :
-
Feature segmentation operator
- \(g\left(\cdot \right)\) :
-
Forward model mapping model parameters to predicted data
- \(h\left(\cdot \right)\) :
-
Dissimilarity measure
- \(\mathbf{K}\) :
-
Coefficient matrix similar to the Kalman gain
- \(l\) :
-
Loss function
- \(\mathbf{L}\) :
-
Localization matrix
- \(\mathbf{M}\) :
-
Ensemble of model realizations
- \({\text{N}}_{d}\) :
-
Number of data
- \({\text{N}}_{e}\) :
-
Ensemble size
- \({\text{N}}_{m}\) :
-
Number of model parameters
- \({\text{N}}_{s}\) :
-
Training dataset size
- \({\mathbf{r}}^{{\prime }}\) :
-
Normalized response map
- \({\text{s}}_{NLM}\) :
-
Denoised estimate by NLM
- \(std\) :
-
Standard deviation
- \({\mathbf{T}}_{*\to *}\) :
-
Directed distance maps
- \(w\left(\cdot \right)\) :
-
NLM weight
- \(\mathbf{x}\) :
-
Input image
- \({\lambda }_{\mathcal{l}}\) :
-
Tuning parameter for the iterative ensemble smoother
- \({\upsigma }\) :
-
Degree of smoothing for NLM
- \(\mu\) :
-
Weighting parameter in CNN loss function
References
Oliver, D.S., Reynolds, A.C., Liu, N.: Inverse theory for petroleum reservoir characterization and history matching. Cambridge University Press, Cambridge (2008). https://doi.org/10.1017/CBO9780511535642
Oliver, D.S., Chen, Y.: Recent progress on reservoir history matching: A review. Comput. Geosci. 15, 185–221 (2011). https://doi.org/10.1007/s10596-010-9194-2
Aanonsen, S.I., Nævdal, G., Oliver, D.S., Reynolds, A.C., Vallès, B.: The ensemble Kalman filter in reservoir engineering–a review. SPE J. 14, 393–412 (2009). https://doi.org/10.2118/117274-PA
Hoteit, I., Pham, D.T., Gharamti, M.E., Luo, X.: Mitigating observation perturbation sampling errors in the stochastic EnKF. Mon. Weather Rev. 143, 2918–2936 (2015). https://doi.org/10.1175/MWR-D-14-00088.1
Abadpour, A., Adejare, M., Chugunova, T., Mathieu, H., Haller, N.: Integrated geo-modeling and ensemble history matching of complex fractured carbonate and deep offshore turbidite fields, generation of several geologically coherent solutions using ensemble methods. In: Abu Dhabi International Petroleum Exhibition & Conference (2018). https://doi.org/10.2118/193028-MS
Chen, Y., Oliver, D.S.: History matching of the Norne full-field model with an iterative ensemble smoother. SPE Reserv. Eval. Eng. 17, 244–256 (2014). https://doi.org/10.2118/164902-PA
Haugen, V., Nœvdal, G., Natvik, L.J., Evensen, G., Berg, A.M., Flornes, K.M.: History matching using the ensemble Kalman filter on a North Sea field case. SPE J. 13, 382–391 (2008). https://doi.org/10.2118/102430-PA
Zhang, Y., Oliver, D.S.: History matching using the ensemble Kalman filter with multiscale parameterization: A field case study. SPE J. 16, 307–317 (2011). https://doi.org/10.2118/118879-PA
Emerick, A.A., Reynolds, A.C.: Ensemble smoother with multiple data assimilation. Comput. Geosci. 55, 3–15 (2013). https://doi.org/10.1016/j.cageo.2012.03.011
Luo, X., Stordal, A.S., Lorentzen, R.J., Nævdal, G.: Iterative ensemble smoother as an approximate solution to a regularized minimum-average-cost problem: Theory and applications. SPE J. 20, 962–982 (2015). https://doi.org/10.1086/309714
Chen, Y., Oliver, D.S.: Levenberg-Marquardt forms of the iterative ensemble smoother for efficient history matching and uncertainty quantification. Comput. Geosci. 17, 689–703 (2013). https://doi.org/10.1007/s10596-013-9351-5
Zhang, Y., Oliver, D.S., Chen, Y., Skaug, H.J.: Data assimilation by use of the iterative ensemble smoother for 2D facies models. SPE J. 20, 169–185 (2015). https://doi.org/10.2118/170248-pa
Hoteit, I., Luo, X., Pham, D.-T.: Particle Kalman filtering: A nonlinear bayesian framework for ensemble Kalman filters. Mon. Weather Rev. 140, 528–542 (2012). https://doi.org/10.1175/2011MWR3640.1
Astrakova, A., Oliver, D.S.: Conditioning truncated pluri-gaussian models to facies observations in ensemble-kalman-based data assimilation. Math. Geosci. 47, 345–367 (2015). https://doi.org/10.1007/s11004-014-9532-3
Lorentzen, R.J., Ncevdal, G., Shafieirad, A.: Estimating facies fields by use of the ensemble kalman filter and distance functions-applied to shallow-marine environments. SPE J. 18, 146–158 (2013). https://doi.org/10.2118/143031-pa
Liu, B., Ait-El-Fquih, B., Hoteit, I.: Efficient kernel-based ensemble gaussian mixture filtering. Mon. Weather Rev. 144, 781–800 (2016). https://doi.org/10.1175/MWR-D-14-00292.1
Katterbauer, K., Hoteit, I., Sun, S.: Synergizing crosswell seismic and electromagnetic techniques for enhancing reservoir characterization. SPE J. 21, 909–927 (2016). https://doi.org/10.2118/174559-pa
Lorentzen, R.J., Luo, X., Bhakta, T., Valestrand, R.: History matching the full norne field model using seismic and production data. SPE J. 1–16 (2019). https://doi.org/10.2118/194205-pa
Zhang, Y., Hoteit, I., Katterbauer, K., Maucec, M., Marsala, A.F.: Feature-based ensemble history matching in a fractured carbonate reservoir using time-lapse deep electromagnetic tomography. J. Pet. Sci. Eng. 208, 109259 (2022). https://doi.org/10.1016/j.petrol.2021.109259
Oliver, D.S., Fossum, K., Bhakta, T., Sandø, I., Nævdal, G., Lorentzen, R.J.: 4D seismic history matching. J. Pet. Sci. Eng. 207, 109119 (2021). https://doi.org/10.1016/j.petrol.2021.109119
Zhang, Y., Vossepoel, F.C., Hoteit, I.: Efficient assimilation of crosswell electromagnetic data using an ensemble-based history-matching framework. SPE J. 25, 119–138 (2020). https://doi.org/10.2118/193808-PA
Zhang, Y., Leeuwenburgh, O.: Image-oriented distance parameterization for ensemble-based seismic history matching. Comput. Geosci. 21, 713–731 (2017). https://doi.org/10.1007/s10596-017-9652-1
Trani, M., Arts, R., Leeuwenburgh, O.: Seismic history matching of fluid fronts using the ensemble Kalman filter. SPE J. 18, 159–171 (2013). https://doi.org/10.2118/163043-PA
Obidegwu, D., Chassagne, R., MacBeth, C.: Seismic assisted history matching using binary maps. J. Nat. Gas Sci. Eng. 42, 69–84 (2017). https://doi.org/10.1016/j.jngse.2017.03.001
Xiao, C., Leeuwenburgh, O., Lin, H.X., Heemink, A.: Conditioning of deep-learning surrogate models to image data with application to reservoir characterization. Knowl. Based Syst. 220, 106956 (2021). https://doi.org/10.1016/j.knosys.2021.106956
Tillier, E., Veiga, S., Da, Derfoul, R.: Appropriate formulation of the objective function for the history matching of seismic attributes. Comput. Geosci. 51, 64–73 (2013). https://doi.org/10.1016/j.cageo.2012.07.031
Derfoul, R., Da Veiga, S., Gout, C., Le Guyader, C., Tillier, E.: Image processing tools for better incorporation of 4D seismic data into reservoir models. J. Comput. Appl. Math. 240, 111–122 (2013). https://doi.org/10.1016/j.cam.2012.08.022
Zhang, Y., Hoteit, I.: Feature-oriented joint time-lapse seismic and electromagnetic history matching using ensemble methods. SPE J. 26, 1341–1365 (2021). https://doi.org/10.2118/203847-PA
Moorkamp, M.: Integrating electromagnetic data with other geophysical observations for enhanced imaging of the earth: A tutorial and review. Surv. Geophys. 38, 935–962 (2017). https://doi.org/10.1007/s10712-017-9413-7
Katterbauer, K., Arango, S., Sun, S., Hoteit, I.: Multi-data reservoir history matching for enhanced reservoir forecasting and uncertainty quantification. J. Pet. Sci. Eng. 128, 160–176 (2015). https://doi.org/10.1016/j.petrol.2015.02.016
Ghosh, S., Das, N., Das, I., Maulik, U.: Understanding deep learning techniques for image segmentation. ACM Comput. Surv. 52, 1–58 (2019). https://doi.org/10.1145/3329784
Sircar, A., Yadav, K., Rayavarapu, K., Bist, N., Oza, H.: Application of machine learning and artificial intelligence in oil and gas industry. Pet. Res. 6, 379–391 (2021). https://doi.org/10.1016/j.ptlrs.2021.05.009
Otchere, D.A., Arbi Ganat, T.O., Gholami, R., Ridha, S.: Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties: Comparative analysis of ANN and SVM models. J. Pet. Sci. Eng. 200, 108182 (2021). https://doi.org/10.1016/j.petrol.2020.108182
Ertekin, T., Sun, Q.: Artificial intelligence applications in reservoir engineering: A status check. Energies (Basel). 12 (2019). https://doi.org/10.3390/en12152897
Cheraghi, Y., Kord, S., Mashayekhizadeh, V.: Application of machine learning techniques for selecting the most suitable enhanced oil recovery method; challenges and opportunities. J. Pet. Sci. Eng 205, 108761 (2021). https://doi.org/10.1016/j.petrol.2021.108761
Wang, G., Ju, Y., Carr, T.R., Li, C., Cheng, G.: Application of Artificial Intelligence on Black Shale Lithofacies Prediction in Marcellus Shale, Appalachian Basin. Presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference (2014). https://doi.org/10.15530/URTEC-2014-1935021
Minaee, S., Boykov, Y.Y., Porikli, F., Plaza, A.J., Kehtarnavaz, N., Terzopoulos, D.: Image segmentation using deep learning: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 8828, 1–20 (2021). https://doi.org/10.1109/TPAMI.2021.3059968
Dell’Aversana, P., Bernasconi, G., Miotti, F., Rovetta, D.: Joint inversion of rock properties from sonic, resistivity and density well-log measurements. Geophys. Prospect. 59, 1144–1154 (2011). https://doi.org/10.1111/j.1365-2478.2011.00996.x
Zhang, Y., Oliver, D.S.: Improving the ensemble estimate of the Kalman gain by bootstrap sampling. Math. Geosci. 42, 327–345 (2010). https://doi.org/10.1007/s11004-010-9267-8
Gassmann, F.: Elastic waves through a packing of spheres. Geophysics 16, 673–685 (1951)
Archie, G.E.: The electrical resistivity log as an aid in determining some reservoir characteristics. Trans. AIME 146, 54–62 (1942). https://doi.org/10.2118/942054-G
Da Silva, C., Herrmann, F.: A unified 2D/3D large-scale software environment for nonlinear inverse problems. ACM Trans. Math. Softw. 45, 7 (2019). https://doi.org/10.1145/3291042
Mulder, W.A.: A multigrid solver for 3D electromagnetic diffusion. Geophys. Prospect. 54, 633–649 (2006)
Plessix, R.E., Mulder, W.A.: Resistivity imaging with controlled-source electromagnetic data: Depth and data weighting. Inverse Probl. 24, 034012 (2008). https://doi.org/10.1088/0266-5611/24/3/034012
Hassouna, M.S., Farag, A.A.: Multistencils fast marching methods: A highly accurate solution to the Eikonal equation on cartesian domains. IEEE Trans. Pattern Anal. Mach. Intell. 29, 1563–1574 (2007). https://doi.org/10.1109/TPAMI.2007.1154
Gillberg, T., Hjelle, Ã., Bruaset, A.M.: Accuracy and efficiency of stencils for the eikonal equation in earth modelling. Comput. Geosci. 16, 933–952 (2012). https://doi.org/10.1007/s10596-012-9296-0
Hao, S., Zhou, Y., Guo, Y.: A brief survey on semantic segmentation with deep learning. Neurocomputing 406, 302–321 (2020). https://doi.org/10.1016/j.neucom.2019.11.118
Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. Proceedings – 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. II, 60–65 (2005). https://doi.org/10.1109/CVPR.2005.38
Kim, W., Kanezaki, A., Tanaka, M.: Unsupervised learning of image segmentation based on differentiable feature clustering. IEEE Trans. Image Process. 29, 8055–8068 (2020). https://doi.org/10.1109/TIP.2020.3011269
Strebelle, S.: Conditional simulation of complex geological structures using multiple-point statistics. Math. Geol. 34, 1–21 (2002)
Sabottke, C.F., Spieler, B.M.: The effect of image resolution on deep learning in radiography. Radiol. Artif. Intell. 2 (2020). https://doi.org/10.1148/ryai.2019190015
Thambawita, V., Strümke, I., Hicks, S.A., Halvorsen, P., Parasa, S., Riegler, M.A.: Impact of image resolution on deep learning performance in endoscopy image classification: An experimental study using a large dataset of endoscopic images. Diagnostics. 11 (2021). https://doi.org/10.3390/diagnostics11122183
Acknowledgements
Support of this work was provided by the office of sponsored research at King Abdullah University of Science and Technology and by the research project titled as “AI aided probabilistic reservoir characterization using ensemble history matching and big data” (Grant No. RGC/3/4290-01-01) funded by Saudi Aramco.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare relevant to the work reported in this paper.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, Y., Katterbauer, K., Zhang, T. et al. Deep learning-aided image-oriented history matching of geophysical data. Comput Geosci 27, 591–604 (2023). https://doi.org/10.1007/s10596-023-10227-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-023-10227-0