Predicting the CO2 propagation in geological formations from sparsely available well data

Research output: Contribution to conferencePaperResearchpeer-review

50 Downloads (Pure)

Abstract

The storage of CO2 in geological formations is dependent on many uncertainties and poses as a challenge for the accurate description of the fluid flow pattern in the porous media where the carbon is stored. Conversely, accurate monitoring of the plume evolution is required for safe long-term operations, which is traditionally carried through the numerical simulation of the multiphase flow. These simulations require solving large non-linear systems of equations, thus precluding real-time monitoring with such tools, in which we dynamically anticipate and/or mitigate the risks involved with the CO2 storage. In this work, we propose the adaptation of continuous conditional generative adversarial networks (CCGAN) for a data-driven model of geologic CO2 storage and plume motion. The proposed model works in a sparse setting, meaning that it maps the sparsely available input data from three wells to the CO2 saturation over the whole domain. The obtained results show that our model enables fast prediction of the CO2 plume with reasonable accuracy, by conferring a substantial reduction in the computational cost when compared to traditional numerical simulations.
Original languageEnglish
Publication date2022
Number of pages9
Publication statusPublished - 2022
Event16th International Conference on Greenhouse Gas Control Technologies - Lyon, France
Duration: 23 Oct 202227 Oct 2022

Conference

Conference16th International Conference on Greenhouse Gas Control Technologies
Country/TerritoryFrance
CityLyon
Period23/10/202227/10/2022

Keywords

  • Monitoring tool
  • Multimodal machine learning
  • GANs
  • Reduced order modeling

Fingerprint

Dive into the research topics of 'Predicting the CO2 propagation in geological formations from sparsely available well data'. Together they form a unique fingerprint.

Cite this