Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties

  title={Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties},
  author={Teeratorn Kadeethum and Daniel O'Malley and Y. Choi and Hari S. Viswanathan and Nikolaos Bouklas and Hongkyu Yoon},
  journal={Comput. Geosci.},
3 Citations

Enhancing high-fidelity nonlinear solver with reduced order model

A novel ROM-assisted approach is developed to improve the computational efficiency of FOM nonlinear solvers by using ROM’s prediction as an initial guess to reduce the computational cost and improve the convergence rate of non linear solvers of full order models (FOM) for solving partial differential equations.

A generalized machine learning framework for brittle crack problems using transfer learning and graph neural networks

This work applies transfer learning (TL) approaches to an existing ML framework, trained to predict multiple crack propagation and stress evolution in brittle materials under Mode-I loading, to provide a universal computational fracture mechanics model that can be easily modified or extended in future work.

LaSDI: Parametric Latent Space Dynamics Identification



A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networks

This work is the first to employ and adapt the image-to-image translation concept based on conditional generative adversarial networks towards learning a forward and an inverse solution operator of partial differential equations (PDEs), and provides a speed-up of 120000 times compared to a Gaussian priorbased inverse modeling approach while also delivering more accurate inverse results.

Parametrization of Stochastic Inputs Using Generative Adversarial Networks With Application in Geology

Results show that the parametrization using generative adversarial networks is very effective in preserving visual realism as well as high order statistics of the flow responses, while achieving a dimensionality reduction of two orders of magnitude.

Predicting CO2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network

This work forms a conditional deep convolutional generative adversarial network (cDC‐GAN) surrogate model to learn the dynamic functional mappings in multiphase models and demonstrates the performance of this model for predicting the migration of carbon dioxide plume in heterogeneous carbon storage reservoirs.

Connectivity-informed drainage network generation using deep convolution generative adversarial networks

A comparison of generated images demonstrated that the novel connectivity-informed method outperformed the other two methods by training DCGANs more effectively and better reproducing accurate drainage networks due to its compact representation of the network complexity and connectivity.

Data-driven reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation

A non-intrusive model reduction framework using proper orthogonal decomposition (POD) and neural networks based on the usual offline-online paradigm that can capture sharp discontinuities of both displacement and pressure fields resulting from the heterogeneity in the media conductivity, which is generally challenging for intrusive reduced order methods.

Deep Convolutional Encoder‐Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media

A deep convolutional encoder‐decoder neural network methodology is proposed to tackle surrogate modeling problems in dynamic multiphase flow problems and is capable of accurately characterizing the spatiotemporal evolution of the pressure and discontinuous CO2 saturation fields.