Physics Informed Deep Learning for Flow and Transport in Porous Media

@article{Gasmi2021PhysicsID,
  title={Physics Informed Deep Learning for Flow and Transport in Porous Media},
  author={Cedric Fraces Gasmi and Hamdi A. Tchelepi},
  journal={Day 1 Tue, October 26, 2021},
  year={2021}
}
We present our progress on the application of physics informed deep learning to reservoir simulation problems. The model is a neural network that is jointly trained to respect governing physical laws and match boundary conditions. The methodology is hereby used to simulate a 2-phase immiscible transport problem (Buckley-Leverett). The model is able to produce an accurate physical solution both in terms of shock and rarefaction and honors the governing partial differential equation along with… 
Physics-informed neural network solution of thermo-hydro-mechanical (THM) processes in porous media
TLDR
This work rewrite the THM governing equations in dimensionless form that is best suited for deep-learning algorithms and proposes a sequential training strategy that circumvents the need for a simultaneous solution of the multiphysics problem and facilitates the task of optimizers in the solution search.
Physics-informed attention-based neural network for solving non-linear partial differential equations
TLDR
PIANNs is a combination of recurrent neural networks and attention mechanisms that finds that PIANNs effectively capture the shock front in a hyperbolic model problem, and are capable of providing high-quality solutions inside and beyond the training set.
Physics-informed attention-based neural network for hyperbolic partial differential equations: application to the Buckley–Leverett problem
TLDR
It is found that PIANNs effectively capture the shock front in a hyperbolic model problem, and are capable of providing high-quality solutions inside the convex hull of the training set.
LSTM-driven Forecast of CO2 Injection in Porous Media
TLDR
This work applies ML techniques to approximate PDE solutions and focuses on the forecasting problem outside of the training domain, using two different ML architectures the feed forward neural (FFN) network and the long short-term memory (LSTM)-based neural network, to predict the PDE Solutions in future times based on the knowledge of the solutions in the past.
PINNs for the Solution of the Hyperbolic Buckley-Leverett Problem with a Non-convex Flux Function
TLDR
This paper presents a PINN approach to solve the hyperbolic B-L problem by embedding the Oleinik entropy condition into the neural network residual and uses the Adam optimizer with residual-based adaptive refinement (RAR) algorithm to achieve an ultra-low loss without weighting.
CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
Machine Learning in Heterogeneous Porous Materials
TLDR
This chapter discusses multi-scale modeling in heterogeneous porous materials via ML in porous and fractured media and recommendations to advance the field in ten years.
Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
TLDR
It is demonstrated that the challenge of training persists even when the boundary conditions are strictly enforced, and the loss landscapes of LPINNs are less sensitive to the so–called “complexity” of the problems, compared to those in the traditional PINNs in the Eulerian framework.
Physics-Informed Neural Networks with Adaptive Localized Artificial Viscosity
TLDR
The results show that the proposed methods are able to learn both a small AV value and the accurate shock location and improve the approximation error over a nonadaptive global AV alternative method.
...
1
2
...

References

SHOWING 1-10 OF 39 REFERENCES
LIMITATIONS OF PHYSICS INFORMED MACHINE LEARNING FOR NONLINEAR TWO-PHASE TRANSPORT IN POROUS MEDIA
TLDR
The overall finding is that PIML strategies that employ the nonlinear hyperbolic conservation equation in the loss function are inadequate, but it is found that employing a parabolic form of the conservation equation, whereby a small amount of diffusion is added, the neural network is consistently able to learn accurate approximation of the solutions containing shocks and mixed waves.
Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
TLDR
This two part treatise introduces physics informed neural networks – neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.
Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
  • M. Raissi
  • Computer Science
    J. Mach. Learn. Res.
  • 2018
TLDR
This work puts forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time by approximate the unknown solution as well as the nonlinear dynamics by two deep neural networks.
Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
TLDR
It is shown how general background knowledge gained from physics could be used as a guideline for designing efficient Deep Learning models and a formal link between the solution of a class of differential equations underlying a large family of physical phenomena and the proposed model is demonstrated.
DGM: A deep learning algorithm for solving partial differential equations
PDE-Net: Learning PDEs from Data
TLDR
Numerical experiments show that the PDE-Net has the potential to uncover the hidden PDE of the observed dynamics, and predict the dynamical behavior for a relatively long time, even in a noisy environment.
...
1
2
3
4
...