Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR
Abstract
Fast forecasting of the reservoir pressure distribution during geologic carbon storage (GCS) by assimilating monitoring data is a challenging problem. Due to high drilling cost, GCS projects usually have spatially sparse measurements from few wells, leading to high uncertainties in reservoir pressure prediction. To address this challenge, we use low-cost Interferometric Synthetic-Aperture Radar (InSAR) data as monitoring data to infer reservoir pressure build up. We develop a deep learning-accelerated workflow to assimilate surface displacement maps interpreted from InSAR and to forecast dynamic reservoir pressure. Employing an Ensemble Smoother Multiple Data Assimilation (ES-MDA) framework, the workflow updates three-dimensional (3D) geologic properties and predicts reservoir pressure with quantified uncertainties. We use a synthetic commercial-scale GCS model with bimodally distributed permeability and porosity to demonstrate the efficacy of the workflow. A two-step CNN-PCA approach is employed to parameterize the bimodal fields. The computational efficiency of the workflow is boosted by two residual U-Net based surrogate models for surface displacement and reservoir pressure predictions, respectively. The workflow can complete data assimilation and reservoir pressure forecasting in half an hour on a personal computer.
- Authors:
-
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- TotalEnergies E&P Research and Technology, Houston, TX (United States)
- University of North Dakota, Grand Forks, ND (United States)
- Publication Date:
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 2005124
- Report Number(s):
- LLNL-JRNL-830880
Journal ID: ISSN 1750-5836; 1047530
- Grant/Contract Number:
- AC52-07NA27344
- Resource Type:
- Accepted Manuscript
- Journal Name:
- International Journal of Greenhouse Gas Control
- Additional Journal Information:
- Journal Volume: 120; Journal ID: ISSN 1750-5836
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 25 ENERGY STORAGE; Data assimilation; Deep learning; InSAR data; Reservoir pressure forecast; ES-MDA
Citation Formats
Tang, Hewei, Fu, Pengcheng, Jo, Honggeun, Jiang, Su, Sherman, Christopher S., Hamon, François, Azzolina, Nicholas A., and Morris, Joseph P. Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR. United States: N. p., 2022.
Web. doi:10.1016/j.ijggc.2022.103765.
Tang, Hewei, Fu, Pengcheng, Jo, Honggeun, Jiang, Su, Sherman, Christopher S., Hamon, François, Azzolina, Nicholas A., & Morris, Joseph P. Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR. United States. https://doi.org/10.1016/j.ijggc.2022.103765
Tang, Hewei, Fu, Pengcheng, Jo, Honggeun, Jiang, Su, Sherman, Christopher S., Hamon, François, Azzolina, Nicholas A., and Morris, Joseph P. Fri .
"Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR". United States. https://doi.org/10.1016/j.ijggc.2022.103765. https://www.osti.gov/servlets/purl/2005124.
@article{osti_2005124,
title = {Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR},
author = {Tang, Hewei and Fu, Pengcheng and Jo, Honggeun and Jiang, Su and Sherman, Christopher S. and Hamon, François and Azzolina, Nicholas A. and Morris, Joseph P.},
abstractNote = {Fast forecasting of the reservoir pressure distribution during geologic carbon storage (GCS) by assimilating monitoring data is a challenging problem. Due to high drilling cost, GCS projects usually have spatially sparse measurements from few wells, leading to high uncertainties in reservoir pressure prediction. To address this challenge, we use low-cost Interferometric Synthetic-Aperture Radar (InSAR) data as monitoring data to infer reservoir pressure build up. We develop a deep learning-accelerated workflow to assimilate surface displacement maps interpreted from InSAR and to forecast dynamic reservoir pressure. Employing an Ensemble Smoother Multiple Data Assimilation (ES-MDA) framework, the workflow updates three-dimensional (3D) geologic properties and predicts reservoir pressure with quantified uncertainties. We use a synthetic commercial-scale GCS model with bimodally distributed permeability and porosity to demonstrate the efficacy of the workflow. A two-step CNN-PCA approach is employed to parameterize the bimodal fields. The computational efficiency of the workflow is boosted by two residual U-Net based surrogate models for surface displacement and reservoir pressure predictions, respectively. The workflow can complete data assimilation and reservoir pressure forecasting in half an hour on a personal computer.},
doi = {10.1016/j.ijggc.2022.103765},
journal = {International Journal of Greenhouse Gas Control},
number = ,
volume = 120,
place = {United States},
year = {Fri Sep 02 00:00:00 EDT 2022},
month = {Fri Sep 02 00:00:00 EDT 2022}
}
Works referenced in this record:
Continuous monitoring system for safe managements of CO2 storage and geothermal reservoirs
journal, September 2021
- Tsuji, Takeshi; Ikeda, Tatsunori; Matsuura, Ryosuke
- Scientific Reports, Vol. 11, Issue 1
A New Differentiable Parameterization Based on Principal Component Analysis for the Low-Dimensional Representation of Complex Geological Models
journal, July 2014
- Vo, Hai X.; Durlofsky, Louis J.
- Mathematical Geosciences, Vol. 46, Issue 7
Reservoir monitoring and characterization using satellite geodetic data: Interferometric synthetic aperture radar observations from the Krechba field, Algeria
journal, November 2008
- Vasco, D. W.; Ferretti, Alessandro; Novali, Fabrizio
- GEOPHYSICS, Vol. 73, Issue 6
Integration of Adversarial Autoencoders With Residual Dense Convolutional Networks for Estimation of Non‐Gaussian Hydraulic Conductivities
journal, February 2020
- Mo, Shaoxing; Zabaras, Nicholas; Shi, Xiaoqing
- Water Resources Research, Vol. 56, Issue 2
A deep learning-accelerated data assimilation and forecasting workflow for commercial-scale geologic carbon storage
journal, December 2021
- Tang, Hewei; Fu, Pengcheng; Sherman, Christopher S.
- International Journal of Greenhouse Gas Control, Vol. 112
Deconvolution and Checkerboard Artifacts
journal, October 2016
- Odena, Augustus; Dumoulin, Vincent; Olah, Chris
- Distill, Vol. 1, Issue 10
General Theory of Three‐Dimensional Consolidation
journal, February 1941
- Biot, Maurice A.
- Journal of Applied Physics, Vol. 12, Issue 2
The latest monitoring progress for Shenhua CO 2 storage project in China
journal, May 2017
- Zhao, Xinglei; Ma, Rui; Zhang, Feng
- International Journal of Greenhouse Gas Control, Vol. 60
Coupled reservoir-geomechanical analysis of CO2 injection and ground deformations at In Salah, Algeria
journal, March 2010
- Rutqvist, Jonny; Vasco, Donald W.; Myer, Larry
- International Journal of Greenhouse Gas Control, Vol. 4, Issue 2
Quantifying the effects of depositional environment on deep saline formation co2 storage efficiency and rate
journal, February 2018
- Bosshart, Nicholas W.; Azzolina, Nicholas A.; Ayash, Scott C.
- International Journal of Greenhouse Gas Control, Vol. 69
3D CNN-PCA: A deep-learning-based parameterization for complex geomodels
journal, March 2021
- Liu, Yimin; Durlofsky, Louis J.
- Computers & Geosciences, Vol. 148
Potential for Satellite Remote Sensing of Ground Water
journal, September 2005
- Becker, Matthew W.
- Groundwater, Vol. 44, Issue 2
Uncertainty quantification in Bayesian inverse problems with model and data dimension reduction
journal, November 2019
- Grana, Dario; Passos de Figueiredo, Leandro; Azevedo, Leonardo
- GEOPHYSICS, Vol. 84, Issue 6
Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
journal, April 2021
- Tang, Meng; Liu, Yimin; Durlofsky, Louis J.
- Computer Methods in Applied Mechanics and Engineering, Vol. 376
Bayesian Poroelastic Aquifer Characterization From InSAR Surface Deformation Data. Part I: Maximum A Posteriori Estimate
journal, October 2020
- Alghamdi, Amal; Hesse, Marc A.; Chen, Jingyi
- Water Resources Research, Vol. 56, Issue 10
Ensemble smoother with multiple data assimilation
journal, June 2013
- Emerick, Alexandre A.; Reynolds, Albert C.
- Computers & Geosciences, Vol. 55
Data inversion in coupled subsurface flow and geomechanics models
journal, October 2012
- Iglesias, Marco A.; McLaughlin, Dennis
- Inverse Problems, Vol. 28, Issue 11
An improved model calculating CO2 solubility in pure water and aqueous NaCl solutions from 273 to 533 K and from 0 to 2000 bar
journal, February 2003
- Duan, Zhenhao; Sun, Rui
- Chemical Geology, Vol. 193, Issue 3-4
Risk‐based area of review estimation in overpressured reservoirs to support injection well storage facility permit requirements for CO
2
storage projects
journal, June 2021
- Burton‐Kelly, Matthew E.; Azzolina, Nicholas A.; Connors, Kevin C.
- Greenhouse Gases: Science and Technology, Vol. 11, Issue 5
Predicting Thermal Performance of an Enhanced Geothermal System From Tracer Tests in a Data Assimilation Framework
journal, December 2021
- Wu, Hui; Fu, Pengcheng; Hawkins, Adam J.
- Water Resources Research, Vol. 57, Issue 12
Reducing uncertainty in geologic CO2 sequestration risk assessment by assimilating monitoring data
journal, March 2020
- Chen, Bailian; Harp, Dylan R.; Lu, Zhiming
- International Journal of Greenhouse Gas Control, Vol. 94
Dynamic characterization of geologic CO2 storage aquifers from monitoring data with ensemble Kalman filter
journal, February 2019
- Ma, Wei; Jafarpour, Behnam; Qin, Joe
- International Journal of Greenhouse Gas Control, Vol. 81
CO2 Plume Tracking and History Matching Using Multilevel Pressure Monitoring at the Illinois Basin – Decatur Project
journal, January 2014
- Strandli, Christin W.; Mehnert, Edward; Benson, Sally M.
- Energy Procedia, Vol. 63
Petrophysical characterization of deep saline aquifers for CO2 storage using ensemble smoother and deep convolutional autoencoder
journal, August 2020
- Liu, Mingliang; Grana, Dario
- Advances in Water Resources, Vol. 142
Geomechanical behavior of the reservoir and caprock system at the In Salah CO2 storage project
journal, May 2014
- White, J. A.; Chiaramonte, L.; Ezzedine, S.
- Proceedings of the National Academy of Sciences, Vol. 111, Issue 24
Deep Convolutional Encoder‐Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media
journal, January 2019
- Mo, Shaoxing; Zhu, Yinhao; Zabaras, Nicholas
- Water Resources Research, Vol. 55, Issue 1