ShihengATM

Results 9 issues of ShihengATM

Hi, thanks for the code. I just have a quick question about `rel_pos_length`. If I set it to none, does it mean the network just use content attention without any...

I'm using VIC 5 and following the documentation [here](https://vic.readthedocs.io/en/master/). It seems confusing that in the sample global parameter [file](https://vic.readthedocs.io/en/master/Documentation/Drivers/Image/GlobalParam/#example-global-parameter-file), precipitation is in kg/m2/s and temperature with Kelvin. In the description...

Hi, I appreciate the effort and resources you've made available through the open-sourced scripts and data. Currently, I'm reproducing the tas NRMSE values as reported in the manuscript. However, I've...

### What happened? I'm using ```r*i1p1f1``` in the parameter file to calculate variability indices for all realizations but with ```i1p1f1``` (only change ```r``` numbers). This seems to work but the...

Hi NeuralGCM team, I'm following the tutorial to modify the model checkpoint and fix global surface temperature, as the following: ``` model = 'gs://neuralgcm/models/v1_precip/stochastic_precip_2_8_deg.pkl' with gcs.open(model, 'rb') as f: ckpt...

Hi NeuralGCM team, Is it expected to have noisy predictions from the stochastic model? The code to generate forecast is: ``` t0 = np.datetime64('2021-06-26') inputs, forcings = model.data_from_xarray(eval_era5.sel(time=t0)) print(forcings['sea_ice_cover'].shape) state...

Hi NeuralGCM team, Thanks for maintaining the NeuralGCM! We encounter an issue when using NeuralGCM for applications, and wonder if nudging is available in the current version (either from dynamical...

Hi, Thanks for open-sourcing the NeuralGCM. I noticed sea level pressure is used to detect tropical cyclones, but it seems SLP is not a standard output. How should we output...

### Is your feature request related to a problem? I'm trying to calculate the monthly modes of variability with some daily sea level pressure data. It shows the error when...