GanZhang-GFD

Thanks @yaniyuval! Sorry for not seeing your reply earlier: > You can output the surface pressure from the model by adding to the config SurfacePressureDiagnostics. Something like this should do...

> Surface temperature would be useful. Agree. Before the functionality is implemented, it is relatively straightforward to approximate the surface temperature when surface pressure is available.

@yaniyuval Thanks! I managed to finish the run with the newer model version. 1) The surface pressure appears to be in the final state object. The data array does not...

@yaniyuval Thanks again! The code snippet didn't change the output values. The test was with the reference code with pip neuralgcm.git@main. I also tested other variants of the pressure unit...

Re drift in surface pressure: I also noticed drifts in other variables (e.g., temperature) of various magnitudes. Larger drifts usually come together with model instability. Smaller drifts appear to do...

@yaniyuval The updated snippet worked! Thanks. For the others watching this issue: The snippet helps put the surface pressure into the prediction object (along with other variables like u, v,...

> @GanZhang-GFD , what method would you use to calculate surface temperature, given surface pressure, and the model state? Would it be based on approximating a lapse rate? Thanks very...

Thanks. I misread the table and thought the benchmark chip was T4 of Colab. The lower performance on a local implementation also confused me. As a data point for the...

Interesting. Thanks for your quick replies. I looked at your paper figures and some of my cases. I agree that the instability often appears to originate from the near-surface. The...

@CldStlkr Thanks! The design will be helpful for VRAM-constrained users, especially if combined with improved flexibility of I/O and VRAM. My use case involves periodical saving of simulation data and...