1. Modeling the thermal transport properties of hydrogen and its mixtures with greenhouse gas impurities: A data-driven machine learning approach.
- Author
-
Vo Thanh, Hung, Rahimi, Mohammad, Tangparitkul, Suparit, and Promsuk, Natthanan
- Abstract
This study introduces machine learning (ML) algorithms to predict hydrogen (H 2) thermodynamic properties for geological storage, focusing on its mixtures with natural gas, nitrogen (N 2), and carbon dioxide (CO 2). Employing 1167 data samples, this research utilizes multiple linear regression (MLR), random forest (RF), gradient boosting (GB), and decision tree (DT) models, enhanced by sensitivity analysis for feature engineering. GB model's superior accuracy and efficiency over conventional statistical linear regression methods. The finding reveals that the GB model achieves superior performance, with an R2 value of 0.9998 for thermal capacity and the lowest mean absolute error (MAE)/root mean square error (RMSE) across all H 2 properties—density (1.51%, 2.06 kg/m3), viscosity (0.000078%, 0.000117 cp), thermal conductivity (0.000427%, 0.000849 W/m.K), and thermal capacity (8.79%, 26.06 J/g.K). Moreover, this ML-based approach not only demonstrates remarkable accuracy and efficiency but also suggests the potential of smart paradigms to further enhance the safety and transportability of underground hydrogen storage projects. Ultimately, this work will help the reservoir simulation at field scale to be more robust and reliable. [Display omitted] • Machine learning employed in the prediction of hydrogen's thermodynamic properties. • Four advanced ML-based models constructed by variables such as pressure, temperature, and hydrogen fraction. • Gradient boosting algorithm comparatively showed the highest accuracies. • ML achieved the lowest MAE/RMSE values for viscosity 0.000078/0.000117. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF