https://github.com/cerea-daml/diffusion-nextsim-regional

Official implementation for "Generative diffusion for regional surrogate models from sea-ice simulations"

https://github.com/cerea-daml/diffusion-nextsim-regional

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 2 DOI reference(s) in README
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.6%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Official implementation for "Generative diffusion for regional surrogate models from sea-ice simulations"

Basic Info
  • Host: GitHub
  • Owner: cerea-daml
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 4.18 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License

README.md

Generative diffusion for regional surrogate modeling of sea-ice physics

This repository is the official implementation for the paper: Finn et al. (2024), Generative diffusion for regional surrogate models from sea-ice simulations, submitted to the "Journal of Advances in Modeling Earth Systems (JAMES)" and available as preprint soon.

The full repository including the dataset and neural network weights is available on Zenodo.

The notebooks included in this repository are used to generate the data and Figures included in the paper. The Weights & Biases projects needed to recreate the Figures will be made available as soon as possible.


This repository is a project about generative diffusion for regional surrogate modeling from sea-ice simulation data, here neXtSIM. To instantiate the diffusion models, the model makes extensive use of the accompanying repository https://github.com/cerea-daml/ddm-dynamical.


This readme will be further extended in the future, e.g., showing how the surrogate models can be used for forecasting.

If you have further questions, please feel free to contact me (@tobifinn) or to create a GitHub issue.

Owner

  • Name: CEREA DA-ML team
  • Login: cerea-daml
  • Kind: organization
  • Location: Paris, France

GitHub Events

Total
  • Fork event: 1
Last Year
  • Fork event: 1

Dependencies

environment.yml pypi
  • cmocean *
  • einops *
  • hydra-core *
  • hydra-joblib-launcher *
  • hydra-optuna-sweeper *
  • hydra-submitit-launcher *
  • k_diffusion *
  • lightning *
  • pykeops *
  • rich *
  • torch *
  • torchaudio *
  • torchvision *
  • wandb *
setup.py pypi