Title: Deep learning inversion of gravity data for detection of CO₂ plumes in overlying aquifers

Abstract

In this work, we developed an effective U-Net based deep learning (DL) model for inversion of surface gravity data on a rectangular grid to predict 2-D high-resolution subsurface CO₂ distribution along a vertical cross-section due to CO₂ leakage through a wellbore within a deep CO₂ storage reservoir. We used synthetic data to model two types of CO₂ leakage scenarios: one CO₂ plume in a shallow aquifer (single plume case), and two plumes present at different depths (double plume case). The 3-D synthetic plume samples were created by sampling among predetermined CO₂ plume depths, saturations, and volumes. The corresponding surface gravity data on a rectangular grid were generated by a 3-D forward model. The U-Net model detected 72% of single-plume samples, and one or both plumes in 75% of double-plume samples. Most of the undetected single plumes have small gravity field strengths below the typical noise level of 5 μGal. This model generated reproducible, reliable predictions with acceptable errors and demonstrated improved spatial resolution over the conventional least-squares inversion. In contrast to the conventional least-squares inversion, which often overestimates the size of its target and underestimates its density, this U-Net model accurately delineated the boundary of a target. Furthermore, this DLmore » inversion detected deep, small, or low saturation CO₂ plumes that are often more difficult to resolve with conventional gravity inversion methods. We note the limitations of this feasibility study, including the use of synthetic data with regular CO₂ plume shapes, and the prediction of a 2-D plume cross-section rather than the full 3-D plume, as well, we recognize the lower detection fraction for double-plume scenarios. Nevertheless, this study demonstrates that DL gravity inversion is a promising and potentially superior method to conventional least-squares inversion. Our U-Net based deep learning inversion approach may be adapted for inversion of other types of geophysical data. DL inversion can facilitate near real-time monitoring of geologic carbon sequestration to provide site operators with prompt information about subsurface CO₂ distribution for risk management and mitigation.« less

Authors:

Yang, Xianjin ^[1]; Chen, Xiao ^[1]; Smith, Megan M. ^[1]

---

+ Show Author Affiliations

1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Publication Date:

Tue Nov 23 00:00:00 EST 2021

Research Org.:

Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Org.:

USDOE Office of Fossil Energy (FE); USDOE Office of Fossil Energy and Carbon Management (FECM)

OSTI Identifier:

1834488

Alternate Identifier(s):

OSTI ID: 1862482

Report Number(s):

LLNL-JRNL-820456
Journal ID: ISSN 0926-9851; 1031719

Grant/Contract Number:  

AC52-07NA27344

Resource Type:

Accepted Manuscript

Journal Name:

Journal of Applied Geophysics

Additional Journal Information:

Journal Volume: 196; Journal Issue: na; Journal ID: ISSN 0926-9851

Publisher:

Elsevier

Country of Publication:

United States

Language:

English

Subject:

58 GEOSCIENCES; Deep learning; Inversion; Gravity; U-Net; CO2; Detection