Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations"
All the needed code and data to reproduce the results from the paper: "Generative diffusion for regional surrogate models from sea-ice simulations". While most of the code is a frozen clone of the original Repository , this capsule also includes the dataset and neural network weights to tr...
Main Authors: | , , , , , |
---|---|
Format: | Other/Unknown Material |
Language: | English |
Published: |
Zenodo
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5281/zenodo.10949057 |
id |
ftzenodo:oai:zenodo.org:10949057 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:10949057 2024-09-09T19:28:24+00:00 Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" Finn, Tobias Durand, Charlotte Farchi, Alban Bocquet, Marc Rampal, Pierre Carrassi, Alberto Finn, Tobias Durand, Charlotte Farchi, Alban Bocquet, Marc Rampal, Pierre Carrassi, Alberto 2024-04-09 https://doi.org/10.5281/zenodo.10949057 eng eng Zenodo https://doi.org/10.5281/zenodo.10949056 https://doi.org/10.5281/zenodo.10949057 oai:zenodo.org:10949057 info:eu-repo/semantics/openAccess MIT License https://opensource.org/licenses/MIT Machine learning Deep learning Sea-ice model Geophysical model Generative deep learning info:eu-repo/semantics/other 2024 ftzenodo https://doi.org/10.5281/zenodo.1094905710.5281/zenodo.10949056 2024-07-27T06:44:51Z All the needed code and data to reproduce the results from the paper: "Generative diffusion for regional surrogate models from sea-ice simulations". While most of the code is a frozen clone of the original Repository , this capsule also includes the dataset and neural network weights to train and apply the surrogate models. The dataset for training and evaluation can be found at data/nextsim , which includes three different Zarr folders for training/validation/testing. The dataset is based on neXtSIM simulation data and ERA5 forcing data and extracted from the SASIP shared data OpenDAP server : The neXtSIM simulations were performed by Gauillaume Boutin and published in the paper " Arctic sea ice mass balance in a new coupled ice–ocean model using a brittle rheology framework " (Boutin et al., 2023) and available as Zenodo dataset (Boutin et al., 2022). The forcing data is based on the ERA5 reanalysis dataset published in the paper: " The ERA5 global reanalysis " (Hersbach et al., 2020) and available as dataset from the Copernicus Climate Change Service (C3S, Copernicus Climate Change Service, 2023). The here used forcing data is based on the hourly reanalysis data on single levels and interpolated with nearest neighbors to the curvilinear grid as used in the output from the neXtSIM simulations. Disclaimer: The results contain modified Copernicus Climate Change Service information, 2023. Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains. The neural network weights are included under data/models and split into weights for the deterministic models and the diffusion models. These neural network weights have been used to generate the results presented in the paper. In this capsule, the notebooks folder includes also the figures used within the paper and additional trajectory data used in the qualitative analysis of the paper. Generally, we recommend to just download the data.tar.gz file and use otherwise the original Repository , ... Other/Unknown Material Arctic Climate change Sea ice Zenodo Arctic |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
English |
topic |
Machine learning Deep learning Sea-ice model Geophysical model Generative deep learning |
spellingShingle |
Machine learning Deep learning Sea-ice model Geophysical model Generative deep learning Finn, Tobias Durand, Charlotte Farchi, Alban Bocquet, Marc Rampal, Pierre Carrassi, Alberto Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" |
topic_facet |
Machine learning Deep learning Sea-ice model Geophysical model Generative deep learning |
description |
All the needed code and data to reproduce the results from the paper: "Generative diffusion for regional surrogate models from sea-ice simulations". While most of the code is a frozen clone of the original Repository , this capsule also includes the dataset and neural network weights to train and apply the surrogate models. The dataset for training and evaluation can be found at data/nextsim , which includes three different Zarr folders for training/validation/testing. The dataset is based on neXtSIM simulation data and ERA5 forcing data and extracted from the SASIP shared data OpenDAP server : The neXtSIM simulations were performed by Gauillaume Boutin and published in the paper " Arctic sea ice mass balance in a new coupled ice–ocean model using a brittle rheology framework " (Boutin et al., 2023) and available as Zenodo dataset (Boutin et al., 2022). The forcing data is based on the ERA5 reanalysis dataset published in the paper: " The ERA5 global reanalysis " (Hersbach et al., 2020) and available as dataset from the Copernicus Climate Change Service (C3S, Copernicus Climate Change Service, 2023). The here used forcing data is based on the hourly reanalysis data on single levels and interpolated with nearest neighbors to the curvilinear grid as used in the output from the neXtSIM simulations. Disclaimer: The results contain modified Copernicus Climate Change Service information, 2023. Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains. The neural network weights are included under data/models and split into weights for the deterministic models and the diffusion models. These neural network weights have been used to generate the results presented in the paper. In this capsule, the notebooks folder includes also the figures used within the paper and additional trajectory data used in the qualitative analysis of the paper. Generally, we recommend to just download the data.tar.gz file and use otherwise the original Repository , ... |
author2 |
Finn, Tobias Durand, Charlotte Farchi, Alban Bocquet, Marc Rampal, Pierre Carrassi, Alberto |
format |
Other/Unknown Material |
author |
Finn, Tobias Durand, Charlotte Farchi, Alban Bocquet, Marc Rampal, Pierre Carrassi, Alberto |
author_facet |
Finn, Tobias Durand, Charlotte Farchi, Alban Bocquet, Marc Rampal, Pierre Carrassi, Alberto |
author_sort |
Finn, Tobias |
title |
Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" |
title_short |
Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" |
title_full |
Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" |
title_fullStr |
Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" |
title_full_unstemmed |
Dataset and neural network weights to the paper: "Generative diffusion for regional surrogate models from sea-ice simulations" |
title_sort |
dataset and neural network weights to the paper: "generative diffusion for regional surrogate models from sea-ice simulations" |
publisher |
Zenodo |
publishDate |
2024 |
url |
https://doi.org/10.5281/zenodo.10949057 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Sea ice |
genre_facet |
Arctic Climate change Sea ice |
op_relation |
https://doi.org/10.5281/zenodo.10949056 https://doi.org/10.5281/zenodo.10949057 oai:zenodo.org:10949057 |
op_rights |
info:eu-repo/semantics/openAccess MIT License https://opensource.org/licenses/MIT |
op_doi |
https://doi.org/10.5281/zenodo.1094905710.5281/zenodo.10949056 |
_version_ |
1809897646355120128 |