Subsurface Flow and Transport Processes

Geologic Carbon Sequestration

Modeling density-driven flow for CO2 sequestration

 

Relevant papers:

  • He, Q., Tartakovsky, A. (2021). Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations. Water Resources Research, 57(7), e2020WR029479.
  • Du, H., Zhao, Z. Cheng, H., Yan, J., He, Q. (2023) Modeling density-driven flow in porous media by physics-informed neural networks for CO2 sequestration. Computers and Geotechnics.

Multiphysics Data Assimilation for Subsurface Flow and Transport

Schematic PINN for subsurface flow

Characterization of hydraulic conductivity and concentration fields from sparse multimodal data by using physics-informed neural networks

Relevant Papers:

  • He, Q., Barajas-Solano, D., Tartakovsky, G., Tartakovsky, A. (2020). Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport. Advances in Water Resources, 141, 103610.
  • He, Q., Tartakovsky, A. (2021). Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations. Water Resources Research, 57(7).
  • Zong, Y., He, Q., & Tartakovsky, A. M. (2023). Improved training of physics-informed neural networks for parabolic differential equations with sharply perturbed initial conditions. Computer Methods in Applied Mechanics and Engineering, 414, 116125.