earth2studio.data.CBottle3D

class earth2studio.data.CBottle3D(core_model, sst_ds, lat_lon=True, sigma_max=80, batch_size=4, seed=0, cache=False, verbose=True)

Climate in a bottle data source Climate in a Bottle (cBottle) is an AI model for emulating global km-scale climate simulations and reanalysis on the equal-area HEALPix grid. The cBottle data source uses the a globally-trained coarse-resolution image generator that generates 100km (50k-pixel) fields given monthly average sea surface temperatures and solar conditioning.

Note

For more information see the following references:

• https://arxiv.org/abs/2505.06474v1

• NVlabs/cBottle

• https://catalog.ngc.nvidia.com/orgs/nvidia/teams/earth-2/models/cbottle

Parameters:

• core_model (torch.nn.Module) – Core Pytorch model

• sst_ds (xr.Dataset) – Sea surface temperature xarray dataset

• lat_lon (bool, optional) – Lat/lon toggle, if true data source will return output on a 0.25 deg lat/lon grid. If false, the native nested HealPix grid will be returned, by default True

• sigma_max (float, optional) – Noise amplitude used to generate latent variables, by default 80

• batch_size (int, optional) – Batch size to generate time samples at, consider adjusting based on hardware being used, by default 4

• seed (int, optional) – Random generator seed for latent variables, by default 0

• cache (bool, optional) – Does nothing at the moment, by default False

• verbose (bool, optional) – Print generation progress, by default True

__call__(time, variable)

Function to get data.

Parameters:

• time (datetime | list[datetime] | TimeArray) – Timestamps to return data for (UTC).

• variable (str | list[str] | VariableArray) – String, list of strings or array of strings that refer to variables to return. Must be in CBottle3D lexicon.

Returns:

Generated data from CBottle

Return type:

xr.DataArray

classmethod load_default_package()

Default pre-trained CBottle3D model package from Nvidia model registry

Return type:

Package

classmethod load_model(package, lat_lon=True, sigma_max=80, batch_size=4, seed=0, verbose=True)

Load AI datasource from package

Parameters:

• package (Package) – CBottle AI model package

• lat_lon (bool, optional) – Lat/lon toggle, if true data source will return output on a 0.25 deg lat/lon grid. If false, the native nested HealPix grid will be returned, by default True

• sigma_max (float, optional) – Noise amplitude used to generate latent variables, by default 80

• batch_size (int, optional) – Batch size to generate time samples at, consider adjusting based on hardware being used, by default 4

• seed (int, optional) – Random generator seed for latent variables, by default 0

• verbose (bool, optional) – Print generation progress, by default True

Returns:

Data source

Return type:

DataSource