search

isds-neu / PhyCRNet

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs
MIT License
118 stars 35 forks source link

Boundary Condition #8

Open mengjie123 opened 2 years ago

mengjie123 commented 2 years ago

Hi,

Thanks for sharing your work and code. In your paper, I found that as for the Dirichlet BCs, you used the periodic padding. To be honest, I don't understand why this operator can achieve Dirichlet BCs. Besides, if it is Neumann BCs, how can we deal with?

Looking forward to your reply! Thanks!

paulpuren commented 2 years ago

Hi,

Thanks for sharing your work and code. In your paper, I found that as for the Dirichlet BCs, you used the periodic padding. To be honest, I don't understand why this operator can achieve Dirichlet BCs. Besides, if it is Neumann BCs, how can we deal with?

Looking forward to your reply! Thanks!

Hi - We conisder the peridoc boundary conditions in our experiments, which means the boundary values are periodic. The periodic padding (or called circular padding in Pytorch) has the functionality to make boundary values having periodic feature. For Neumann BCs, as you can see the illustration in the paper, we introduce ghost nodes for the forcible satisfaction beyond the boundaries, where the values of ghost nodes can be inferred by finite difference methods.

afrah commented 1 year ago

What if the boundary condition is something else not periodic?