Accurate prediction of relative permeability is essential for continuum-scale simulations of multiphase flow in porous media. Fluid configurations obtained from pore-scale simulations can be upscaled to derive relative permeability at the continuum-scale. To address the limitations of traditional methods, this study proposes a thermodynamically consistent workflow that employs a data-driven approach to predict relative permeability from fluid configurations based on wettability at the continuum-scale.   By leveraging pre-trained models, the workflow eliminates the need for repetitive pore-scale simulations. Validation using μCT images demonstrates the accuracy and reliability of the proposed workflow. The integration with continuum-scale simulators like MRST further highlights its practical applicability, providing robust and scalable modeling capabilities. This study introduces an innovative and efficient solution for modeling complex multiphase flow in porous media, advancing the computational tools available for continuum-scale simulations.

The role of phase topology in hysteresis during fluid injection and withdrawal in porous media is not fully understood. We address this by providing experimental and theoretical evidence on three key findings. (1) The topological evolution of the nonwetting fluid is distinct from capillary pressure and specific interfacial area, with the Euler characteristic not bounded by main imbibition and drainage curves, as shown by experiments and a generalized model. (2) Saturation paths with identical capillary pressure and interfacial area show different topologies, revealing insights into energy dissipation and phase connectivity. (3) The topological evolution of the nonwetting phase follows predictable, convex set interactions, captured by a piecewise nonlinear model. These findings offer practical implications for designing subsurface hydrogen and carbon dioxide storage systems and provide a novel approach for studying complex systems with topological singularities.