earth2studio.models.dx.CBottleSR

class earth2studio.models.dx.CBottleSR(core_model, hr_latlon=(2161, 4320), sampler_steps=18, sigma_max=800)

Climate in a Bottle Super-Resolution (CBottleSR) model.

CBottleSR is a diffusion-based super-resolution model that learns mappings between low- and high-resolution climate data with high fidelity. This model generates results at 5km resolution on a healpix grid with 10 levels of resolution (1024x1024). The results are then regridded to a lat/lon grid. Suggested output dimensions are (2161, 4320) which corresponds to 10km resolution at the equator or (4321, 8640) which corresponds to 5km resolution at the equator.

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 implementing the diffusion-based super-resolution

• hr_latlon (Tuple[int, int], optional) – High-resolution output dimensions (lat, lon), by default (2161, 4320)

• sampler_steps (int, optional) – Number of diffusion steps, by default 18

• sigma_max (int, optional) – Maximum noise level for diffusion process, by default 800

__call__(x, coords)

Forward pass of diagnostic

Parameters:

• x (Tensor)

• coords (OrderedDict[str, ndarray])

Return type:

tuple[Tensor, OrderedDict[str, ndarray]]

classmethod load_default_package()

Default pre-trained CBottle3D model package from Nvidia model registry

Return type:

Package

classmethod load_model(package, sampler_steps=18, sigma_max=800, hr_latlon=(2161, 4320))

Load AI datasource from package

Parameters:

• package (Package)

• sampler_steps (int)

• sigma_max (int)

• hr_latlon (tuple[int, int])

Return type:

DiagnosticModel