Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport

1 code implementation • 6 Dec 2019 • QiZhi He, David Brajas-Solano, Guzel Tartakovsky, Alexandre M. Tartakovsky

We apply this approach to assimilate conductivity, hydraulic head, and concentration measurements for joint inversion of the conductivity, hydraulic head, and concentration fields in a steady-state advection--dispersion problem.

Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence

no code implementations • 24 Nov 2018 • Xiu Yang, David Barajas-Solano, Guzel Tartakovsky, Alexandre Tartakovsky

In this work, we propose a new Gaussian process regression (GPR)-based multifidelity method: physics-informed CoKriging (CoPhIK).

Active Learning GPR +1

Physics-Information-Aided Kriging: Constructing Covariance Functions using Stochastic Simulation Models

no code implementations • 10 Sep 2018 • Xiu Yang, Guzel Tartakovsky, Alexandre Tartakovsky

We also provide an error estimate in preserving the physical constraints when errors are included in the stochastic model realizations.

Active Learning GPR