search

lu-group / deeponet-fno

DeepONet & FNO (with practical extensions)
Other
202 stars 41 forks source link

Handling 3D data like time evolution of 2D fluid flow. #2

Open hammermm opened 2 years ago

hammermm commented 2 years ago

Thank you Lu for such exciting work.

RIght now, I want to use DeepONet for flow problems. My input is of the dimension (Samples, Height, Width, Time) or images corresponding to different time steps depicting the evolution of flow. Being specific, my input is velocity from. t = 1 to m time steps and I want to predict the velocity for next n time steps [ batch, :,:,:m] -> [ batch,:,:, m: m+n].

How should I preprocess the data for such a problem? Is there any available code implementation for such flow problem using deepOnet?

Also, can we use DeepOnet like FNO-2D-time( more of RNN type structure)?

lululxvi commented 2 years ago

Yes, you can use DeepONet. There are different possible ways for input and output. The easiest way is using time step t as the input, and time step t+1 as the output. Or you can use multiple time steps as the input.