首页|Machine learning prediction of methane,ethane,and propane solubility in pure water and electrolyte solutions:Implications for stray gas migration modeling

Machine learning prediction of methane,ethane,and propane solubility in pure water and electrolyte solutions:Implications for stray gas migration modeling

扫码查看
原文链接
  • 万方数据
  • 维普
Machine learning prediction of methane,ethane,and propane solubility in pure water and electrolyte solutions:Implications for stray gas migration modeling
Hydraulic fracturing is an effective technology for hydrocarbon extraction from unconventional shale and tight gas reservoirs.A potential risk of hydraulic fractur-ing is the upward migration of stray gas from the deep sub-surface to shallow aquifers.The stray gas can dissolve in groundwater leading to chemical and biological reactions,which could negatively affect groundwater quality and con-tribute to atmospheric emissions.The knowledge of light hydrocarbon solubility in the aqueous environment is essen-tial for the numerical modelling of flow and transport in the subsurface.Herein,we compiled a database containing 2129 experimental data of methane,ethane,and propane solu-bility in pure water and various electrolyte solutions over wide ranges of operating temperature and pressure.Two machine learning algorithms,namely regression tree(RT)and boosted regression tree(BRT)tuned with a Bayesian optimization algorithm(BO)were employed to determine the solubility of gases.The predictions were compared with the experimental data as well as four well-established ther-modynamic models.Our analysis shows that the BRT-BO is sufficiently accurate,and the predicted values agree well with those obtained from the thermodynamic models.The coefficient of determination(R2)between experimental and predicted values is 0.99 and the mean squared error(MSE)is 9.97 × 10-8.The leverage statistical approach further con-firmed the validity of the model developed.

Gas solubilityHydraulic fracturingThermodynamic modelsRegression treeBoosted regression treeGroundwater contamination

Ghazal Kooti、Reza Taherdangkoo、Chaofan Chen、Nikita Sergeev、Faramarz Doulati Ardejani、Tao Meng、Christoph Butscher

展开 >

Institute of Geotechnics,TU Bergakademie Freiberg,Gustav-Zeuner-Str.1,09599 Freiberg,Germany

Department of Petroleum Engineering,Amirkabir University of Technology,Tehran,Iran

Freiberg Center for Water Research ZeWaF,TU Bergakademie Freiberg,09599 Freiberg,Germany

School of Mining,College of Engineering,University of Tehran,Tehran,Iran

Taiyuan University of Science and Technology,Taiyuan 030024,China

展开 >

Gas solubility Hydraulic fracturing Thermodynamic models Regression tree Boosted regression tree Groundwater contamination

2024

10.1007/s11631-024-00680-8

地球化学学报(英文版)
中国科学院地球化学研究所

地球化学学报(英文版)

EI
影响因子：0.33
ISSN：2096-0956
年,卷(期)：2024.43(5)