Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Surrogate Model for Geological CO2 Storage and Its Use in Hierarchical MCMC History Matching (2308.06341v2)

Published 11 Aug 2023 in cs.CV and physics.geo-ph

Abstract: Deep-learning-based surrogate models show great promise for use in geological carbon storage operations. In this work we target an important application - the history matching of storage systems characterized by a high degree of (prior) geological uncertainty. Toward this goal, we extend the recently introduced recurrent R-U-Net surrogate model to treat geomodel realizations drawn from a wide range of geological scenarios. These scenarios are defined by a set of metaparameters, which include the horizontal correlation length, mean and standard deviation of log-permeability, permeability anisotropy ratio, and constants in the porosity-permeability relationship. An infinite number of realizations can be generated for each set of metaparameters, so the range of prior uncertainty is large. The surrogate model is trained with flow simulation results, generated using the open-source simulator GEOS, for 2000 random realizations. The flow problems involve four wells, each injecting 1 Mt CO2/year, for 30 years. The trained surrogate model is shown to provide accurate predictions for new realizations over the full range of geological scenarios, with median relative error of 1.3% in pressure and 4.5% in saturation. The surrogate model is incorporated into a hierarchical Markov chain Monte Carlo history matching workflow, where the goal is to generate history matched geomodel realizations and posterior estimates of the metaparameters. We show that, using observed data from monitoring wells in synthetic `true' models, geological uncertainty is reduced substantially. This leads to posterior 3D pressure and saturation fields that display much closer agreement with the true-model responses than do prior predictions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. A tutorial on adaptive MCMC. Stat. Comput. 18, 343–373.
  2. Multigrid reduction preconditioning framework for coupled processes in porous and fractured media. Comput. Methods Appl. Mech. Eng. 387, 114111.
  3. Reducing uncertainty in geologic CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT sequestration risk assessment by assimilating monitoring data. Int. J. Greenh. Gas Control. 94, 102926.
  4. Dimension-robust MCMC in Bayesian inverse problems. arXiv preprint arXiv:1803.03344.
  5. Deep generator priors for Bayesian seismic inversion. Adv. Geophys. 61, 179–216.
  6. Markov chain Monte Carlo: stochastic simulation for Bayesian inference. CRC Press.
  7. Weak convergence and optimal scaling of random walk Metropolis algorithms. Ann. Appl. Probab. 7, 110–120.
  8. Efficient Metropolis jumping rules. Bayesian Stat. 5, 42.
  9. Detection of potential leakage pathways from geological carbon storage by fluid pressure data assimilation. Adv. Water Resour. 86, 366–384.
  10. Monte Carlo sampling methods using Markov chains and their applications. Biometrika. 57, 97–109.
  11. Inference of rock flow and mechanical properties from injection-induced microseismic events during geologic CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT storage. Int. J. Greenh. Gas Control. 105, 103206.
  12. History matching for geological carbon storage using data-space inversion with spatio-temporal data parameterization. arXiv preprint arXiv:2310.03228.
  13. Use of multifidelity training data and transfer learning for efficient construction of subsurface flow surrogate models. J. Comput. Phys. 474, 111800.
  14. On the detection of leakage pathways in geological CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT storage systems using pressure monitoring data: Impact of model parameter uncertainties. Adv. Water Resour. 84, 112–124.
  15. Relative permeability and trapping of CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT and water in sandstone rocks at reservoir conditions. Water Resour. Res. 48, W02532.
  16. Doing Bayesian data analysis: A tutorial with R, JAGS, and Stan. Academic Press.
  17. Coupled multiphase thermo-hydro-mechanical analysis of supercritical CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT injection: Benchmark for the In Salah surface uplift problem. Int. J. Greenh. Gas Control. 51, 394–408.
  18. Petrophysical characterization of deep saline aquifers for CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT storage using ensemble smoother and deep convolutional autoencoder. Adv. Water Resour. 142, 103634.
  19. 3D CNN-PCA: A deep-learning-based parameterization for complex geomodels. Comput. Geosci. 148, 104676.
  20. Expanded uncertainty quantification in inverse problems: Hierarchical Bayes and empirical Bayes. Geophysics. 69, 1005–1016.
  21. Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media. Water Resour. Res. 55, 703–728.
  22. Stochastic inversion of wellbore stability models calibrated with hard and soft data, in: U.S. Rock Mechanics/Geomechanics Symposium, American Rock Mechanics Association.
  23. Applied geostatistics with SGeMS: A user’s guide. Cambridge University Press.
  24. New trapping mechanism in carbon sequestration. Transp. Porous Media. 82, 3–17.
  25. Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index. Comput. Phys. Commun. 181, 259–270.
  26. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Math. Comput. Simul. 55, 271–280.
  27. Data-space approaches for uncertainty quantification of CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT plume location in geological carbon storage. Adv. Water Resour. 123, 234–255.
  28. Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR. Int. J. Greenh. Gas Control. 120, 103765.
  29. Deep-learning-based coupled flow-geomechanics surrogate model for CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT sequestration. Int. J. Greenh. Gas Control. 118, 103692.
  30. A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems. J. Comput. Phys. 413, 109456.
  31. Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow. Comput. Methods Appl. Mech. Eng. 376, 113636.
  32. Comparison of ensemble filtering algorithms and null-space Monte Carlo for parameter estimation and uncertainty quantification using CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT sequestration data. Water Resour. Res. 49, 8108–8127.
  33. Efficient uncertainty quantification for dynamic subsurface flow with surrogate by theory-guided neural network. Comput. Methods Appl. Mech. Eng. 373, 113492.
  34. CCSNet: a deep learning modeling suite for CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT storage. Adv. Water Resour. 155, 104009.
  35. U-FNO—An enhanced Fourier neural operator-based deep-learning model for multiphase flow. Adv. Water Resour. 163, 104180.
  36. Real-time high-resolution CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT geological storage prediction using nested Fourier neural operators. Energy Environ. Sci. 16, 1732–1741.
  37. Geomechanical behavior of the reservoir and caprock system at the In Salah CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT storage project. Proc. Natl. Acad. Sci. 111, 8747–8752.
  38. Model-reduced adjoint-based inversion using deep-learning: Example of geological carbon sequestration modeling. Water Resour. Res. 58, e2021WR031041.
  39. Bayesian inversion of multi-Gaussian log-conductivity fields with uncertain hyperparameters: An extension of preconditioned Crank-Nicolson Markov chain Monte Carlo with parallel tempering. Water Resour. Res. 57, e2021WR030313.
  40. A robust deep learning workflow to predict multiphase flow behavior during geological CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT sequestration injection and post-injection periods. J. Hydrol. 607, 127542.
  41. A gradient-based deep neural network model for simulating multiphase flow in porous media. J. Comput. Phys. 463, 111277.
  42. Sobol sensitivity analysis: a tool to guide the development and evaluation of systems pharmacology models. CPT: Pharmacomet. Syst. Pharmacol. 4, 69–79.
  43. Predicting CO22{}_{2}start_FLOATSUBSCRIPT 2 end_FLOATSUBSCRIPT plume migration in heterogeneous formations using conditional deep convolutional generative adversarial network. Water Resour. Res. 55, 5830–5851.
  44. Markov chain Monte Carlo with neural network surrogates: application to contaminant source identification. Stoch. Environ. Res. Risk Assess. 35, 639–651.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Yifu Han (2 papers)
  2. Francois P. Hamon (25 papers)
  3. Su Jiang (8 papers)
  4. Louis J. Durlofsky (23 papers)
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now