polymathic-ai / FNO-planetswe

huggingface.co
Total runs: 23
24-hour runs: 0
7-day runs: 1
30-day runs: 11
Model's Last Updated: March 28 2025

Introduction of FNO-planetswe

Model Details of FNO-planetswe

Benchmarking Models on the Well

The Well is a 15TB dataset collection of physics simulations. This model is part of the models that have been benchmarked on the Well.

The models have been trained for a fixed time of 12 hours or up to 500 epochs, whichever happens first. The training was performed on a NVIDIA H100 96GB GPU. In the time dimension, the context length was set to 4. The batch size was set to maximize the memory usage. We experiment with 5 different learning rates for each model on each dataset. We use the model performing best on the validation set to report test set results.

The reported results are here to provide a simple baseline. They should not be considered as state-of-the-art . We hope that the community will build upon these results to develop better architectures for PDE surrogate modeling.

Fourier Neural Operator

Implementation of the Fourier Neural Operator provided by neuraloperator v0.3.0 .

Model Details

For benchmarking on the Well, we used the following parameters.

Parameters Values
Modes 16
Blocks 4
Hidden Size 128
Trained Model Versions

Below is the list of checkpoints available for the training of FNO on different datasets of the Well.

Dataset Best Learning Rate Epochs VRMSE
acoustic_scattering_maze 1E-3 27 0.5033
active_matter 5E-3 239 0.3157
convective_envelope_rsg 1E-4 14 0.0224
gray_scott_reaction_diffusion 1E-3 46 0.2044
helmholtz_staircase 5E-4 132 0.00160
MHD_64 5E-3 170 0.3352
planetswe 5E-4 49 0.0855
post_neutron_star_merger 5E-4 104 0.4144
rayleigh_benard 1E-4 32 0.6049
rayleigh_taylor_instability 5E-3 177 0.4013
shear_flow 1E-3 24 0.4450
supernova_explosion_64 1E-4 40 0.3804
turbulence_gravity_cooling 1E-4 13 0.2381
turbulent_radiative_layer_2D 5E-3 500 0.4906
viscoelastic_instability 5E-3 205 0.7195
Loading the model from Hugging Face

To load the FNO model trained on the planetswe of the Well, use the following commands.

from the_well.benchmark.models import FNO

model = FNO.from_pretrained("polymathic-ai/FNO-planetswe")

Runs of polymathic-ai FNO-planetswe on huggingface.co

23
Total runs
0
24-hour runs
1
3-day runs
1
7-day runs
11
30-day runs

More Information About FNO-planetswe huggingface.co Model

FNO-planetswe huggingface.co

FNO-planetswe huggingface.co is an AI model on huggingface.co that provides FNO-planetswe's model effect (), which can be used instantly with this polymathic-ai FNO-planetswe model. huggingface.co supports a free trial of the FNO-planetswe model, and also provides paid use of the FNO-planetswe. Support call FNO-planetswe model through api, including Node.js, Python, http.

polymathic-ai FNO-planetswe online free

FNO-planetswe huggingface.co is an online trial and call api platform, which integrates FNO-planetswe's modeling effects, including api services, and provides a free online trial of FNO-planetswe, you can try FNO-planetswe online for free by clicking the link below.

polymathic-ai FNO-planetswe online free url in huggingface.co:

https://huggingface.co/polymathic-ai/FNO-planetswe

FNO-planetswe install

FNO-planetswe is an open source model from GitHub that offers a free installation service, and any user can find FNO-planetswe on GitHub to install. At the same time, huggingface.co provides the effect of FNO-planetswe install, users can directly use FNO-planetswe installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

FNO-planetswe install url in huggingface.co:

https://huggingface.co/polymathic-ai/FNO-planetswe

Url of FNO-planetswe

Provider of FNO-planetswe huggingface.co

polymathic-ai
ORGANIZATIONS

Other API from polymathic-ai