1887

Abstract

Summary

The present study adopts a two-phase formulation for oil and water in porous media, augmented with terms that capture the physics of emulsion transport and retention. Physics-informed neural networks (PINNs) provide an alternative route than reservoir simulation: instead of learning from labelled data, the network is trained to minimize residuals of the governing equations and boundary/initial conditions ( ). For porous flow with sharp fronts and retention kinetics this is non-trivial, yet promising as a mesh-free, differentiable surrogate that can also assimilate sparse measurements during training. Here we present, to the best of our knowledge, the first PINN formulation tailored to emulsion flooding, building on a two-phase Darcy framework with an emulsion transport–retention subsystem. We report 1D proof-of-concept simulations (pressure and saturation fields) and discuss how permeability reduction and droplet kinetics are encoded in the loss.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202521282
2025-10-27
2026-01-14

  • From This Site

    /content/papers/10.3997/2214-4609.202521282
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Abou-Kassem, J.H., Ali, S.M.F., [1995]. Modeling of Emulsion Flow In Porous Media. Journal of Canadian Petroleum Technology, 34(06).
     [Google Scholar]
  2. Ding, B., Dong, M., Chen, Z., Kantzas, A., [2022]. Enhanced oil recovery by emulsion injection in heterogeneous heavy oil reservoirs: Experiments, modeling and reservoir simulation. Journal of Petroleum Science and Engineering, 209, 109882.
     [Google Scholar]
  3. Hanna, J.M., Aguado, J.V., Comas-Cardona, S., Askri, R., Borzacchiello, D., [2022]. Residual-based adaptivity for two-phase flow simulation in porous media using Physics-informed Neural Networks. Computer Methods in Applied Mechanics and Engineering, 396, 115100.
     [Google Scholar]
  4. Raissi, M., Perdikaris, P., Karniadakis, G.E., [2017]. Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations.
     [Google Scholar]
  5. Wu, C., Zhu, M., Tan, Q., Kartha, Y., Lu, L., [2023]. A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks. Computer Methods in Applied Mechanics and Engineering, 403, 115671.
     [Google Scholar]
  6. Yu, J., Lu, L., Meng, X., Karniadakis, G.E., [2022]. Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems. Computer Methods in Applied Mechanics and Engineering, 393, 114823.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202521282
Loading

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error