Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset
The AI4Arctic Sea Ice Challenge Datasets are produced for the AI4EO sea ice competition initiated by the European Space Agency (ESA) ɸ-lab. The purpose of the competition is to develop deep learning models to automatically produce sea ice charts including sea ice concentration, stage-of-development...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Dataset |
Language: | unknown |
Published: |
2022
|
Subjects: | |
Online Access: | https://doi.org/10.11583/dtu.21317463.v1 https://figshare.com/articles/dataset/Ready-To-Train_AI4Arctic_Sea_Ice_Challenge_Test_Dataset/21317463 |
id |
ftdtufig:oai:figshare.com:article/21317463 |
---|---|
record_format |
openpolar |
spelling |
ftdtufig:oai:figshare.com:article/21317463 2023-05-15T15:18:35+02:00 Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset Jørgen Buus-Hinkler Tore Wulf Andreas Rønne Stokholm Anton Korosov Roberto Saldo Leif Toudal Pedersen David Arthurs Rune Solberg Nicolas Longépé Matilde Brandt Kreiner 2022-11-21T12:45:57Z https://doi.org/10.11583/dtu.21317463.v1 https://figshare.com/articles/dataset/Ready-To-Train_AI4Arctic_Sea_Ice_Challenge_Test_Dataset/21317463 unknown doi:10.11583/dtu.21317463.v1 https://figshare.com/articles/dataset/Ready-To-Train_AI4Arctic_Sea_Ice_Challenge_Test_Dataset/21317463 CC BY 4.0 CC-BY Other earth sciences not elsewhere classified sea ice Sentinel 1 Synthetic aperture radar (SAR) microwave radiometry Arctic research Cryosphere deep learning dataset Dataset 2022 ftdtufig https://doi.org/10.11583/dtu.21317463.v1 2022-11-24T00:11:02Z The AI4Arctic Sea Ice Challenge Datasets are produced for the AI4EO sea ice competition initiated by the European Space Agency (ESA) ɸ-lab. The purpose of the competition is to develop deep learning models to automatically produce sea ice charts including sea ice concentration, stage-of-development and floe size (form) information. The training datasets contain Sentinel-1 active microwave Synthetic Aperture Radar (SAR) data and corresponding passive MicroWave Radiometer (MWR) data from the AMSR2 satellite sensor. While SAR data has ambiguities between open water and sea ice, it has a high spatial resolution, whereas MWR data has good contrast between open water and ice. However, the coarse resolution of the AMSR2 MWR observations introduces a new set of obstacles, e.g. land spill-over, which can lead to erroneous sea ice predictions along the coastline adjacent to open water. Label data in the challenge datasets are ice charts, that have been produced by the Greenland ice service at the Danish Meteorological Institute (DMI) and the Canadian Ice Service (CIS) for the safety of navigation. The challenge datasets also contain other auxiliary data such as the distance to land and numerical weather prediction model data. The scenes are from the time period from January 8 2018 to December 21 2021. Two versions of the dataset exist, the ' raw' and ' ready-to-train'- versions with corresponding test datasets . The datasets each consist of the same 493 training and 20 test (without label data) scenes. The ‘ ready-to-train’ -version has been further prepared for model training, such as downsampled data from 40 to 80 m pixel spacing, standard scaled, converted ice charts (sea ice concentration, stage of development and floe size), removal of nan values, mask alignment etc. This is the Test data for the Ready-To-Train version. Reference data is not included. Further details are described in the common manual that is published together with the datasets; “AI4Arctic_challenge-dataset-manual”. Code with a get-started toolkit ... Dataset Arctic Greenland Sea ice Technical University of Denmark (DTU): Fighsare Arctic Greenland |
institution |
Open Polar |
collection |
Technical University of Denmark (DTU): Fighsare |
op_collection_id |
ftdtufig |
language |
unknown |
topic |
Other earth sciences not elsewhere classified sea ice Sentinel 1 Synthetic aperture radar (SAR) microwave radiometry Arctic research Cryosphere deep learning dataset |
spellingShingle |
Other earth sciences not elsewhere classified sea ice Sentinel 1 Synthetic aperture radar (SAR) microwave radiometry Arctic research Cryosphere deep learning dataset Jørgen Buus-Hinkler Tore Wulf Andreas Rønne Stokholm Anton Korosov Roberto Saldo Leif Toudal Pedersen David Arthurs Rune Solberg Nicolas Longépé Matilde Brandt Kreiner Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset |
topic_facet |
Other earth sciences not elsewhere classified sea ice Sentinel 1 Synthetic aperture radar (SAR) microwave radiometry Arctic research Cryosphere deep learning dataset |
description |
The AI4Arctic Sea Ice Challenge Datasets are produced for the AI4EO sea ice competition initiated by the European Space Agency (ESA) ɸ-lab. The purpose of the competition is to develop deep learning models to automatically produce sea ice charts including sea ice concentration, stage-of-development and floe size (form) information. The training datasets contain Sentinel-1 active microwave Synthetic Aperture Radar (SAR) data and corresponding passive MicroWave Radiometer (MWR) data from the AMSR2 satellite sensor. While SAR data has ambiguities between open water and sea ice, it has a high spatial resolution, whereas MWR data has good contrast between open water and ice. However, the coarse resolution of the AMSR2 MWR observations introduces a new set of obstacles, e.g. land spill-over, which can lead to erroneous sea ice predictions along the coastline adjacent to open water. Label data in the challenge datasets are ice charts, that have been produced by the Greenland ice service at the Danish Meteorological Institute (DMI) and the Canadian Ice Service (CIS) for the safety of navigation. The challenge datasets also contain other auxiliary data such as the distance to land and numerical weather prediction model data. The scenes are from the time period from January 8 2018 to December 21 2021. Two versions of the dataset exist, the ' raw' and ' ready-to-train'- versions with corresponding test datasets . The datasets each consist of the same 493 training and 20 test (without label data) scenes. The ‘ ready-to-train’ -version has been further prepared for model training, such as downsampled data from 40 to 80 m pixel spacing, standard scaled, converted ice charts (sea ice concentration, stage of development and floe size), removal of nan values, mask alignment etc. This is the Test data for the Ready-To-Train version. Reference data is not included. Further details are described in the common manual that is published together with the datasets; “AI4Arctic_challenge-dataset-manual”. Code with a get-started toolkit ... |
format |
Dataset |
author |
Jørgen Buus-Hinkler Tore Wulf Andreas Rønne Stokholm Anton Korosov Roberto Saldo Leif Toudal Pedersen David Arthurs Rune Solberg Nicolas Longépé Matilde Brandt Kreiner |
author_facet |
Jørgen Buus-Hinkler Tore Wulf Andreas Rønne Stokholm Anton Korosov Roberto Saldo Leif Toudal Pedersen David Arthurs Rune Solberg Nicolas Longépé Matilde Brandt Kreiner |
author_sort |
Jørgen Buus-Hinkler |
title |
Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset |
title_short |
Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset |
title_full |
Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset |
title_fullStr |
Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset |
title_full_unstemmed |
Ready-To-Train AI4Arctic Sea Ice Challenge Test Dataset |
title_sort |
ready-to-train ai4arctic sea ice challenge test dataset |
publishDate |
2022 |
url |
https://doi.org/10.11583/dtu.21317463.v1 https://figshare.com/articles/dataset/Ready-To-Train_AI4Arctic_Sea_Ice_Challenge_Test_Dataset/21317463 |
geographic |
Arctic Greenland |
geographic_facet |
Arctic Greenland |
genre |
Arctic Greenland Sea ice |
genre_facet |
Arctic Greenland Sea ice |
op_relation |
doi:10.11583/dtu.21317463.v1 https://figshare.com/articles/dataset/Ready-To-Train_AI4Arctic_Sea_Ice_Challenge_Test_Dataset/21317463 |
op_rights |
CC BY 4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.11583/dtu.21317463.v1 |
_version_ |
1766348785763483648 |