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

Time-lapse seismic data inversion for estimating reservoir parameters using deep learning

Journal Article · · Interpretation
 [1];  [2];  [3];  [3]
  1. The University of Texas at Austin, Bureau of Economic Geology, John A. and Katherine G. Jackson School of Geosciences, University Station, Box X, Austin, Texas 78713-8924, USA. (corresponding author)
  2. China University of Geosciences, Wuhan 430074, China.
  3. The University of Texas at Austin, Bureau of Economic Geology, John A. and Katherine G. Jackson School of Geosciences, University Station, Box X, Austin, Texas 78713-8924, USA.

Geologic carbon sequestration involves the injection of captured carbon dioxide ([Formula: see text]) into subsurface formations for long-term storage. The movement and fate of the injected [Formula: see text] plume is of great concern to regulators because monitoring helps to identify potential leakage zones and determines the possibility of safe long-term storage. To address this concern, we design a deep-learning framework for [Formula: see text] saturation monitoring to determine the geologic controls on the storage of the injected [Formula: see text]. We use different combinations of porosities and permeabilities for a given reservoir to generate saturation and velocity models. We train the deep-learning model with a few time-lapse seismic images and their corresponding changes in saturation values for a particular [Formula: see text] injection site. The deep-learning model learns the mapping from the change in the time-lapse seismic response to the change in [Formula: see text] saturation during the training phase. We then apply the trained model to data sets comprising different time-lapse seismic image slices (corresponding to different time instances) generated using different porosity and permeability distributions that are not part of the training to estimate the [Formula: see text] saturation values along with the plume extent. Our algorithm provides a deep-learning assisted framework for the direct estimation of [Formula: see text] saturation values and plume migration in heterogeneous formations using the time-lapse seismic data. Our method improves the efficiency of time-lapse inversion by streamlining the large number of intermediate steps in the conventional time-lapse inversion workflow. This method also helps to incorporate the geologic uncertainty for a given reservoir by accounting for the statistical distribution of porosity and permeability during the training phase. Tests on different examples verify the effectiveness of our approach.

Research Organization:
Pennsylvania State Univ., University Park, PA (United States)
Sponsoring Organization:
USDOE Office of Fossil Energy (FE)
DOE Contract Number:
FE0031544
OSTI ID:
1980959
Journal Information:
Interpretation, Vol. 10, Issue 1; ISSN 2324-8858
Publisher:
Society of Exploration Geophysicists
Country of Publication:
United States
Language:
English

References (42)

A Methodology to Integrate Multiple Simulation Models and 4D Seismic Data Considering Their Uncertainties conference September 2016
Joint estimation of porosity and saturation using stochastic rock-physics modeling journal September 2006
Seismic properties of pore fluids journal November 1992
Bayesian time-lapse inversion journal May 2006
CO2 storage monitoring: leakage detection and measurement in subsurface volumes from 3D seismic data at Sleipner journal January 2014
Nonlinear inversion for estimating reservoir parameters from time-lapse seismic data journal November 2007
Uncertainty Quantification for CO2 Sequestration and Enhanced Oil Recovery journal January 2014
Stochastic reservoir characterization using prestack seismic data journal July 2004
Seismic wave extrapolation using lowrank symbol approximation: Lowrank wave extrapolation journal April 2012
Seismic waveform inversion using a neural network-based forward journal October 2019
Elastic Waves Through a Packing of Spheres journal October 1951
Probabilistic petrophysical-properties estimation integrating statistical rock physics with seismic inversion journal May 2010
Bayesian inversion of time-lapse seismic data for the estimation of static reservoir properties and dynamic property changes: Bayesian inversion of seismic data journal December 2014
Monitoring and volumetric estimation of injected CO2 using 4D seismic, petrophysical data, core measurements and well logging: a case study at Ketzin, Germany: Monitoring and volumetric estimation of injected CO2 using 4D seismic journal April 2012
Inverse rock physics modeling for reservoir quality prediction journal March 2013
Strategy for estimation of lithology and reservoir properties from seismic velocities and density conference March 2012
Monitoring CO2 response on surface seismic data; a rock physics and seismic modeling feasibility study at the CO2 sequestration site, Ketzin, Germany journal August 2010
Discrimination between pressure and fluid saturation changes from time‐lapse seismic data journal May 2001
Discrimination between pressure and fluid saturation changes from marine multicomponent time‐lapse seismic data journal September 2003
4D seismic monitoring of CO2 sequestration journal February 2010
Using simulation and production data to resolve ambiguity in interpreting 4D seismic inverted impedance in the Norne Field journal October 2017
A New Two-Constant Equation of State journal February 1976
4D surface seismic tracks small supercritical CO2 injection into the subsurface: CO2CRC Otway Project journal August 2017
Adversarial Attacks and Defenses in Deep Learning journal March 2020
The In Salah CO2 Storage Project: Lessons Learned and Knowledge Transfer journal January 2013
Learning from Simulated and Unsupervised Images through Adversarial Training conference July 2017
Assessing leakage detectability at geologic CO2 sequestration sites using the probabilistic collocation method journal June 2013
Model Calibration and Parameter Estimation book January 2015
Inverse Problem Theory and Methods for Model Parameter Estimation book January 2005
An Engineering-consistent Bayesian Scheme for 4D Seismic to Simulator Inversion conference June 2015
Estimation of changes in saturation and pressure from 4D seismic AVO and time-shift analysis journal March 2011
The Seismic Response to Injected Carbon Dioxide: Comparing Observations to Estimates Based Upon Fluid Flow Modeling journal July 2019
Well-Logging Constrained Seismic Inversion Based on Closed-Loop Convolutional Neural Network journal August 2020
Image Quality Assessment: From Error Visibility to Structural Similarity journal April 2004
Geophysical monitoring of the Weyburn CO2 flood: Results during 10 years of injection journal January 2011
Time-lapse seismic performance of a sparse permanent array: Experience from the Aquistore CO 2 storage site journal March 2015
Characterization of a fracture zone using seismic attributes at the In Salah CO2 storage project journal May 2015
Pre-Stack Seismic Inversion With Deep Learning conference November 2018
Numerical simulation of Water-alternating-gas Process for Optimizing EOR and Carbon Storage journal February 2019
Predicting CO 2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network journal July 2019
Inversion of Time‐Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning‐Based Approach for Estimating Dynamic Reservoir Property Changes journal March 2020
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks conference October 2017