Weak Supervision Multigeophysical Inversion for CO2 Saturation Imaging
- 19 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-17
Abstract
In CO2 sequestration projects, multi-physics inversion has been widely used to reconstruct various geophysical properties (such as velocity and conductivity). However, the saturation of CO2 is not feasible through partial differential equations (PDEs), which poses a challenge to traditional multi-physics inversion techniques in directly inverting CO2 saturation from geophysical measurements. Typically, a rock physics model is constructed to tackle this challenge. Nevertheless, the construction of such a model is intricate due to the inherent complexities and uncertainties within subsurface geology and geophysical data. Data-driven inversion methods present an alternative solution, as they can connect CO2 saturation to geophysical measurements and directly learn their relationships from labeled data. Nonetheless, the efficacy of these methods hinges on extensive data labeling, incurring considerable costs. To address this challenge, we propose a novel data-driven technique for the inversion of multi-physics data called Weakly Supervised Multi-Geophysical Inversion (WS-MGI), which reduces the need for labeling and promises to be a more cost-effective solution. In particular, we focus on the multi-physics inversion problem from two geophysical data (electromagnetic (EM) and seismic) to CO2 saturation. By learning the local relationship between velocity and CO2 saturation at a few well logs, we construct the pseudo labels for CO2 saturation, thus enabling the data-driven inversion with few labels. We verify our method using synthetic data based on the Kimberlina storage reservoir in California. Experiments show that compared to the supervised counterpart, our method can achieve similar inversion results with only 2% labels.Keywords
Funding Information
- School of Data Science and Society at the University of North Carolina at Chapel Hill. (Faculty start-up Grant)
- Los Alamos National Laboratory (20210542MFR)
- Hydrocarbons and Geothermal Energy Office (Science-Informed Machine Learning to Accelerate Re)
This publication has 67 references indexed in Scilit:
- The Kimberlina synthetic multiphysics dataset for CO2 monitoring investigationsGeoscience Data Journal, 2023
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images2018
- 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 capabilitiesInternational Journal of Greenhouse Gas Control, 2018
- Foundations of Geophysical Electromagnetic Theory and Methods2018
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learningGenetic Programming and Evolvable Machines, 2017
- 2.5D Inversion and Joint Interpretation of CSEM Data at Sleipner CO2 StorageEnergy Procedia, 2017
- Support Vector Regression2015
- Uncertainty quantification of CO2 saturation estimated from electrical resistance tomography data at the Cranfield siteInternational Journal of Greenhouse Gas Control, 2014
- Well Logging for Earth Scientists2007
- Electrical Conductivity and Total Dissolved Solids—What is Their Precise Relationship?Desalination, 1989