Abstract
Carbon capture and storage (CCS) is one approach being studied by the U.S. Department of Energy to help mitigate global warming. The process involves capturing CO2 emissions from industrial sources and permanently storing them in deep geologic formations (storage reservoirs). However, CCS projects generally target “green field sites,” where there is often little characterization data and therefore large uncertainty about the petrophysical properties and other geologic attributes of the storage reservoir. Consequently, ensemble-based approaches are often used to forecast multiple realizations prior to CO2 injection to visualize a range of potential outcomes. In addition, monitoring data during injection operations are used to update the pre-injection forecasts and thereby improve agreement between forecasted and observed behavior. Thus, a system for generating accurate, timely forecasts of pressure buildup and CO2 movement and distribution within the storage reservoir and for updating those forecasts via monitoring measurements becomes crucial. This study proposes a learning-based prediction method that can accurately and rapidly forecast spatial distribution of CO2 concentration and pressure with uncertainty quantification without relying on traditional inverse modeling. The machine learning techniques include dimension reduction, multivariate data analysis, and Bayesian learning. The outcome is expected to provide CO2 storage site operators with an effective tool for timely and informative decision making based on limited simulation and monitoring data.
Highlights
Carbon capture and storage (CCS) has been proposed as a strategy to reduce greenhouse gas emissions entering the atmosphere from stationary sources and thereby help to mitigate the global climate crisis (Pacala and Socolow, 2004; Alcalde et al, 2018)
Our research aims to develop machine learning (ML) techniques with a potential to provide significant improvements to the conventional history matchingbased forecasts, enhancing the timeliness and accuracy of information provided to the operator
We discuss the results of additional cases (Case I – Case IV in Table 1) by incorporating 1, 2, 5, and 7 years of observations to assess the sensitivity of the Learning-based Inversion-free Prediction (LIP) prediction performance to the available monitoring data and to evaluate the capability of LIP to incorporate additional observations for improving the prediction
Summary
Carbon capture and storage (CCS) has been proposed as a strategy to reduce greenhouse gas emissions entering the atmosphere from stationary sources and thereby help to mitigate the global climate crisis (Pacala and Socolow, 2004; Alcalde et al, 2018). Depleted oil and gas reservoirs may provide important intermediate-scale storage, any CCSactivity, at a scale sufficient to impact the carbon problem (e.g., billions of metric tons), will necessarily involve largescale CO2 injections into deep saline aquifers (e.g., multiple projects inject one million metric tons per year or greater). Providing CO2 storage site operators and regulators with rapid forecasting tools for timely decision making is essential to addressing these challenges to CCS project development and management. Delivering on this need requires transformational changes in how we predict subsurface responses to CO2 injection and update those predictions using monitoring measurements
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
