Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Deep learning multiphysics network for imaging CO2 saturation and estimating uncertainty in geological carbon storage

Journal Article · · Geophysical Prospecting
 [1];  [1];  [1];  [2];  [1];  [3];  [2];  [3]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  3. Colorado School of Mines, Golden, CO (United States)
+ Show Author Affiliations

Multiphysics inversion exploits different types of geophysical data that often complement each other and aims to improve overall imaging resolution and reduce uncertainties in geophysical interpretation. Despite the advantages, traditional multiphysics inversion is challenging because it requires a large amount of computational time and intensive human interactions for preprocessing data and finding trade-off parameters. These issues make it nearly impossible for traditional multiphysics inversion to be applied as a real-time monitoring tool for geological carbon storage. In this paper, we present a deep learning (DL) multiphysics network for imaging CO2 saturation in real time. The multiphysics network consists of three encoders for analysing seismic, electromagnetic and gravity data and shares one decoder for combining imaging capabilities of the different geophysical data for better predicting CO2 saturation. The network is trained on pairs of CO2 label models and multiphysics data so that it can directly image CO2 saturation. Here we use the bootstrap aggregating method to enhance the imaging accuracy and estimate uncertainties associated with CO2 saturation images. Using realistic CO2 label models and multiphysics data derived from the Kimberlina CO2 storage model, we evaluate the performance of the deep learning multiphysics network and compare its imaging results to those from the deep learning single-physics networks. Our modelling experiments show that the deep learning multiphysics network for seismic, electromagnetic, and gravity data not only improves the imaging accuracy but also reduces uncertainties associated with CO2 saturation images. Our results also suggest that the deep learning multiphysics network for the non-seismic data (i.e., electromagnetic and gravity) can be used as an effective low-cost monitoring tool in between regular seismic monitoring.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER); USDOE Office of Fossil Energy (FE)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1894062
Journal Information:
Geophysical Prospecting, Journal Name: Geophysical Prospecting Journal Issue: 1 Vol. 72; ISSN 0016-8025
Publisher:
WileyCopyright Statement
Country of Publication:
United States
Language:
English

References (47)

On scale and magnitude of pressure build-up induced by large-scale geologic storage of CO2 journal March 2011
An Introduction to Statistical Learning book January 2021
U-Net: Convolutional Networks for Biomedical Image Segmentation
  • Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas
  • Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28
book November 2015
The Geomechanics of CO2 Storage in Deep Sedimentary Formations journal January 2012
Monitoring of CO2 Injected at Sleipner Using Time Lapse Seismic Data book January 2003
Results from Sleipner gravity monitoring: Updated density and temperature distribution of the CO2 plume journal January 2011
High-resolution characterization of a CO2 plume using crosswell seismic tomography: Cranfield, MS, USA journal October 2013
Modeling the performance of large-scale CO2 storage systems: A comparison of different sensitivity analysis methods journal September 2013
The state of the art in monitoring and verification—Ten years on journal September 2015
Progress in monitoring strategies for risk reduction in geologic CO2 storage journal August 2016
Modeling of time-lapse seismic monitoring using CO2 leakage simulations for a model CO2 storage site with realistic geology: Application in assessment of early leak-detection capabilities journal September 2018
Assessment of geophysical monitoring methods for detection of brine and CO2 leakage in drinking water aquifers journal November 2019
Time-lapse full waveform inversion based on curvelet transform: Case study of CO2 storage monitoring journal September 2021
Sensitivity of geophysical techniques for monitoring secondary CO2 storage plumes journal February 2022
Deep learning inversion of gravity data for detection of CO2 plumes in overlying aquifers journal January 2022
The Rock Physics Handbook book March 2020
Earthquake triggering and large-scale geologic storage of carbon dioxide journal June 2012
Utilizing the onset of time-lapse changes: a robust basis for reservoir monitoring and characterization journal January 2014
Deep learning electromagnetic inversion with convolutional neural networks journal May 2019
How Convolutional Neural Networks Deal with Aliasing conference June 2021
InversionNet: An Efficient and Accurate Data-Driven Full Waveform Inversion journal January 2020
Data-Driven Seismic Waveform Inversion: A Study on the Robustness and Generalization journal October 2020
Joint Inversion of Audio-Magnetotelluric and Seismic Travel Time Data With Deep Learning Constraint journal September 2021
New advances in three-dimensional controlled-source electromagnetic inversion journal February 2008
Waveform inversion in the Laplace-Fourier domain journal June 2009
Full waveform inversion in the time lapse mode applied to CO 2 storage at Sleipner: Full waveform inversion in the time lapse mode journal May 2012
Crosswell seismic imaging of reservoir changes caused by CO 2 injection journal September 1997
Accuracy of Finite‐Difference Modeling of the Acoustic wave Equation journal December 1974
A feasibility study of nonseismic geophysical methods for monitoring geologic CO2 sequestration journal October 2006
Gravimetric monitoring of gas production from the Troll field journal November 2008
An overview of full-waveform inversion in exploration geophysics journal November 2009
Quantitative analysis of time-lapse seismic monitoring data at the Sleipner CO2 storage operation journal February 2010
A strategy for coupled 3D imaging of large-scale seismic and electromagnetic data sets: Application to subsalt imaging journal May 2014
Advantages of borehole vector gravity in density imaging journal January 2015
Deep-learning inversion: A next-generation seismic velocity model building method journal July 2019
Regularized elastic full-waveform inversion using deep learning journal September 2019
3D borehole-to-surface and surface electromagnetic modeling and inversion in the presence of steel infrastructure journal September 2020
Deep-learning electromagnetic monitoring coupled to fluid flow simulators journal January 2020
Cooperative deep learning inversion of controlled-source electromagnetic data for salt delineation journal June 2020
Electrical imaging of hydraulic fracturing fluid using steel-cased wells and a deep-learning method journal July 2021
Deep learning-enhanced multiphysics joint inversion conference September 2021
Deep-learning tomography journal January 2018
Time-lapse electromagnetic and gravity methods in carbon storage monitoring journal June 2021
Modeling the Performance of Large-Scale CO2 Storage Systems: dataset January 2012
CO2 Sequestration in Deep Sedimentary Formations journal October 2008
Experimental Study on CO2 Monitoring and Saturation with Combined P-wave Velocity and Resistivity conference June 2010
TOUGH2 User's Guide Version 2 report November 1999

Similar Records

Real-time deep-learning inversion of seismic full waveform data for CO2 saturation and uncertainty in geological carbon storage monitoring
Journal Article · Thu Apr 07 00:00:00 EDT 2022 · Geophysical Prospecting · OSTI ID:1865313

Related Subjects

58 GEOSCIENCES
electromagnetics
full waveform
gravity
inversion and monitoring