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

Journal Article · 05 August 2022 · Computers and Geosciences

DOI: https://doi.org/10.1016/j.cageo.2022.105212 · OSTI ID:1888551

Kadeethum, Teeratorn ^[1]; O’Malley, Daniel ^[2]; Choi, Youngsoo ^[3]; Viswanathan, Hari Suthan ^[2]; Bouklas, Nikolaos ^[4]; Yoon, H. ^[5]

---

1. Sandia National Laboratory (SNL-NM), Albuquerque, NM (United States); Cornell University, Ithaca, NY (United States)
2. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
3. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
4. Cornell University, Ithaca, NY (United States)
5. Sandia National Laboratory (SNL-NM), Albuquerque, NM (United States)

Machine learning-based data-driven modeling can allow computationally efficient time-dependent solutions of PDEs, such as those that describe subsurface multiphysical problems. In this work, our previous approach (Kadeethum et al., 2021d) of conditional generative adversarial networks (cGAN) developed for the solution of steady-state problems involving highly heterogeneous material properties is extended to time-dependent problems by adopting the concept of continuous cGAN (CcGAN). The CcGAN that can condition continuous variables is developed to incorporate the time domain through either element-wise addition or conditional batch normalization. Moreover, this framework can handle training data that contain different timestamps and then predict timestamps that do not exist in the training data. As a numerical example, the transient response of the coupled poroelastic process is studied in two different permeability fields: Zinn & Harvey transformation and a bimodal transformation. The proposed CcGAN uses heterogeneous permeability fields as input parameters while pressure and displacement fields over time are model output. Our results show that the model provides sufficient accuracy with computational speed-up. This robust framework will enable us to perform real-time reservoir management and robust uncertainty quantification in poroelastic problems.

• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States); Los Alamos National Laboratory (LANL), Los Alamos, NM (United States); Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
• Sponsoring Organization: Cornell University; USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA); USDOE Office of Fossil Energy (FE); USDOE Office of Fossil Energy (FE), Oil & Natural Gas; USDOE Office of Science (SC), Basic Energy Sciences (BES)
• Grant/Contract Number: AC52-07NA27344; NA0003525
• OSTI ID: 1888551
• Report Number(s): LLNL-JRNL-827590; SAND2022-10731J; 708927
• Journal Information: Computers and Geosciences, Journal Name: Computers and Geosciences Vol. 167; ISSN 0098-3004
• Publisher: ElsevierCopyright Statement
• Country of Publication: United States
• Language: English