udemirezen / gpinn

gPINN: Gradient-enhanced physics-informed neural networks

gPINN: Gradient-enhanced physics-informed neural networks

The data and code for the paper J. Yu, L. Lu, X. Meng, & G. E. Karniadakis. Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems. Computer Methods in Applied Mechanics and Engineering, 393, 114823, 2022.

Code

• Function approximation
• Forward PDE problems
  • Poisson equation in 1D
  • Diffusion-reaction equation
  • Poisson equation in 2D
• Inverse PDEs problems
  • Brinkman-Forchheimer model
    • Case 1
    • Case 2
  • Diffusion-reaction system
• gPINN enhanced by RAR
  • Burgers' equation
  • Allen-Cahn equation

Cite this work

If you use this data or code for academic research, you are encouraged to cite the following paper:

@article{yu2022gradient,
  title   = {Gradient-enhanced physics-informed neural networks for forward and inverse {PDE} problems},
  author  = {Yu, Jeremy and Lu, Lu and Meng, Xuhui and Karniadakis, George Em},
  journal = {Computer Methods in Applied Mechanics and Engineering},
  volume  = {393},
  pages   = {114823},
  year    = {2022},
  doi     = {https://doi.org/10.1016/j.cma.2022.114823}
}

Questions

To get help on how to use the data or code, simply open an issue in the GitHub "Issues" section.