A machine learning based framework for brine-gas interfacial tension prediction: Implications for H2, CH4 and CO2 Geo-Storage
Document Type
Conference Proceeding
Publication Title
Society of Petroleum Engineers - GOTECH Conference 2024
Publisher
Society of Petroleum Engineers
School
Centre for Sustainable Energy and Resources
Funders
National Natural Science Foundation of China
Grant Number
52304019
Abstract
Brine-gas interfacial tension (γ) is an important parameter to determine fluid dynamics, trapping and distributions at pore-scale, thus influencing gas (H2, CH4 and CO2) geo-storage (GGS) capacity and security at reservoir-scale. However, γ is a complex function of pressure, temperature, ionic strength, gas type and mole fraction, thus time-consuming to measure experimentally and challenging to predict theoretically. Therefore herein, a genetic algorithm-based automatic machine learning and symbolic regression (GA-AutoML-SR) framework was developed to predict γ systematically under GGS conditions. In addition, the sensitivity of γ to all influencing factors was analyzed. The prediction results have shown that: 1. the GA-AutoML-SR model prediction accuracy was high with the coefficient of determination (R2) of 0.994 and 0.978 for the training and testing sets, respectively; 2. a quantitative mathematical correlation was derived as a function of pressure, temperature, ionic strength, gas type and mole fraction, with R2= 0.72; 3. the most dominant influencing factor for γ was identified as pressure. These insights will promote the energy transition, balance energy supply-demand and reduce carbon emissions.
DOI
10.2118/219225-MS
Access Rights
subscription content
Comments
Pan, B., Song, T., Yin, X., Jiang, Y., Yue, M., Hoteit, H., ... & Iglauer, S. (2024). A machine learning based framework for brine-gas interfacial tension prediction: Implications for H2, CH4 and CO2 Geo-Storage. In SPE Gas & Oil Technology Showcase and Conference (p. D022S001R005). SPE. https://doi.org/10.2118/219225-MS