Skip to main content

Run graphcast ai weather models with capabilities for GFS and GDAS initial conditions and NetCDF output

Project description

ai-models-graphcast-gfs

ai-models-graphcast-gfs is an extension of the ai-models-graphcast package, which itself is a plugin to run Google Deepmind's GraphCast with ai-models.

GraphCast: Learning skillful medium-range global weather forecasting, arXiv preprint: 2212.12794, 2022. https://arxiv.org/abs/2212.12794

GraphCast was created by Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson, Peter Wirnsberger, Meire Fortunato, Ferran Alet, Suman Ravuri, Timo Ewalds, Zach Eaton-Rosen, Weihua Hu, Alexander Merose, Stephan Hoyer, George Holland, Oriol Vinyals, Jacklynn Stott, Alexander Pritzel, Shakir Mohamed and Peter Battaglia.

The model weights are made available for use under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0). You may obtain a copy of the License at: https://creativecommons.org/licenses/by-nc-sa/4.0/.

Installation

To install the package, run:

pip install ai-models-graphcast-gfs

This will install the package and most of its dependencies.

Then to install graphcast dependencies (and Jax on GPU):

Graphcast and Jax

Graphcast depends on Jax, which needs special installation instructions for your specific hardware.

Please see the installation guide to follow the correct instructions.

We have prepared two requirements.txt you can use. A CPU and a GPU version:

For the preferred GPU usage:

pip install -r requirements-gpu.txt -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html

For the slower CPU usage:

pip install -r requirements.txt

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_models_graphcast_gfs-0.0.12.tar.gz (16.2 kB view details)

Uploaded Source

Built Distribution

ai_models_graphcast_gfs-0.0.12-py3-none-any.whl (18.2 kB view details)

Uploaded Python 3

File details

Details for the file ai_models_graphcast_gfs-0.0.12.tar.gz.

File metadata

File hashes

Hashes for ai_models_graphcast_gfs-0.0.12.tar.gz
Algorithm Hash digest
SHA256 98597ad99c0f9e66434f0869cb438f2828ff57f67b0620bc37960cfe96e733a9
MD5 0651dfa6337c53b87eb03ba9ea06f200
BLAKE2b-256 0b63d3851dbcd5d8a905af136b327a17cbfc60948de1a1125b062a3091e0d16e

See more details on using hashes here.

File details

Details for the file ai_models_graphcast_gfs-0.0.12-py3-none-any.whl.

File metadata

File hashes

Hashes for ai_models_graphcast_gfs-0.0.12-py3-none-any.whl
Algorithm Hash digest
SHA256 23e153e0f4bee9f321e32b228dbdb29b2aa82567d3ee398e41ed34392be0d2a2
MD5 5d4b14e871b7bfea286df7ca338e5500
BLAKE2b-256 f1aa5f0a82931bba791fc893ee249632e514e1474fb29162350303a745b16c53

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page