Development of a hydrate risk assessment tool based on machine learning for CO₂ storage in depleted gas reservoirs

Development of a hydrate risk assessment tool based on machine learning for CO₂ storage in depleted gas reservoirs

Yamada, Kenta (The University of Texas at Austin)
Fernandes, Bruno Ramon Batista (The University of Texas at Austin)
Kalamkar, Atharva (The University of Texas at Austin)
Jeon, Jonghyeon (The University of Texas at Austin)
Delshad, Mojdeh (The University of Texas at Austin)
Farajzadeh, R. (TU Delft Reservoir Engineering; Shell Global Solutions International B.V.)
Sepehrnoori, Kamy (The University of Texas at Austin)

2023

Depleted gas reservoirs are attractive sites for Carbon Capture and Storage (CCS) due to their huge storage capacities, proven seal integrity, existing infrastructure and subsurface data availability. However, CO₂ injection into depleted formations can potentially lead to hydrate formation near the wellbore due to Joule-Thomson cooling, which might cause injectivity issues. Some challenges encountered when modeling and simulating this process are the computational time caused by Newton's convergence issues and instability. The objective of this work is to propose a novel approach for hydrate risk assessment during CO₂ injection into depleted gas reservoirs using physics-based Machine Learning (ML) approach. First, the selection of input parameters for the ML models is performed based on sensitivity study results using an analytical solution for different operational and petrophysical values. Then the ML models are tuned and tested using datasets from numerical reservoir simulation results based on a wide range of input parameter values. To the best of our knowledge, this is the first time that an ML approach is used for risk assessment of CO₂ hydrate in its storage in depleted gas reservoirs. The ML models developed in this study presented an efficient performance to predict hydrate-forming events. The deep neural network model performed best with a 95% recall value and 84% precision value. These results show that the ML model can be further utilized for risk assessment in the screening stage, and the combination of screening by ML, followed by detailed analysis with numerical simulation in high-risk cases can be an efficient probing workflow for future CCS projects.

Carbon capture and storage
CO hydrate
Cold CO injection
Depleted gas reservoir
Machine learning
Reservoir simulation

http://resolver.tudelft.nl/uuid:a2c6a55b-7caa-4fa3-9195-f17f6878e132

https://doi.org/10.1016/j.fuel.2023.129670

2024-03-04

0016-2361

Fuel: the science and technology of fuel and energy, 357

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2023 Kenta Yamada, Bruno Ramon Batista Fernandes, Atharva Kalamkar, Jonghyeon Jeon, Mojdeh Delshad, R. Farajzadeh, Kamy Sepehrnoori