Raw AI4Arctic Sea Ice Challenge 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 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 513 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 'raw'-version. The netCDF files are bundled together in groups ~25 with the filename format corresponding to the Sentinel-1 satellite from which the SAR image was acquired by, followed by the first file acquisition time to the last, i.e. S1(A/B)_FirstDate_LastDate.zip. 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 for the 'ready-to-train' dataset: https://github.com/astokholm/AI4ArcticSeaIceChallenge A quick challenge video overview of the challenge is available at: https://youtu.be/iuXIeLPyKfg This item is part of the Collection https://doi.org/10.11583/DTU.c.6244065 Version 2 has updated two zip files, which contained four corrupted netCDF files. The zip files in question are: S1A_20190419T203541_20190823T114541.zip S1B_20191028T132359_20200714T184241.zip In addition, 20 more scenes have been added in "added_v2.zip".

AI4Arctic海冰挑战数据集（AI4Arctic Sea Ice Challenge Datasets）是为欧洲空间局（European Space Agency, ESA）ɸ-lab发起的AI4EO海冰竞赛打造的专属数据集。本竞赛的目标是开发深度学习模型，以自动生成涵盖海冰密集度、发展阶段及浮冰尺寸（形态）信息的海冰图。

训练数据集包含Sentinel-1主动微波合成孔径雷达（Synthetic Aperture Radar, SAR）数据，以及来自AMSR2卫星传感器的被动微波辐射计（MicroWave Radiometer, MWR）配套数据。其中，SAR数据虽在开阔水域与海冰间存在识别歧义，但具备较高的空间分辨率；而MWR数据在开阔水域与海冰间对比度优异，不过AMSR2 MWR观测的粗分辨率带来了一系列新问题，例如陆地溢出效应，这会导致紧邻开阔水域的海岸线周边出现错误的海冰预测结果。

本挑战数据集的标签数据为海冰图，由丹麦气象研究所（Danish Meteorological Institute, DMI）格陵兰冰务部门与加拿大冰务中心（Canadian Ice Service, CIS）制作，用于保障航行安全。挑战数据集还包含其他辅助数据，例如距陆地距离数据与数值天气预报模型数据。所有场景的时间跨度为2018年1月8日至2021年12月21日。

本数据集共有两个版本，即"原始版"与"就绪训练版"，且各配有对应的测试数据集。两个版本均包含513个训练场景与20个无标签测试场景。"就绪训练版"已针对模型训练完成预处理，包括将像素间距从40米至80米进行下采样、标准化处理、转换海冰图格式（涵盖海冰密集度、发展阶段与浮冰尺寸）、去除缺失值（nan值）、掩码对齐等。原始版的netCDF文件以约25个为一组进行打包，文件名格式对应采集SAR图像的Sentinel-1卫星，后跟首个文件的采集时间至最后一个采集时间，即S1(A/B)_FirstDate_LastDate.zip。

更多细节可参阅与数据集同步发布的通用手册《AI4Arctic_challenge-dataset-manual》。"就绪训练版"数据集的入门工具包代码地址：https://github.com/astokholm/AI4ArcticSeaIceChallenge。本竞赛的快速视频概览可通过以下链接查看：https://youtu.be/iuXIeLPyKfg。本数据集隶属于合集 https://doi.org/10.11583/DTU.c.6244065。

版本2更新了两个包含损坏netCDF文件的压缩包，具体为：S1A_20190419T203541_20190823T114541.zip、S1B_20191028T132359_20200714T184241.zip。此外，"added_v2.zip"中新增了20个场景。

搜集汇总

背景与挑战

背景概述

该数据集是AI4Arctic海冰挑战赛的原始版本，专为开发深度学习模型以自动生成海冰图而设计，包含高分辨率Sentinel-1 SAR数据和AMSR2 MWR数据，以及由专业冰情服务机构制作的标签数据。数据集覆盖2018年至2021年的北极区域，提供513个训练场景和20个测试场景，总大小约244.17 GB，适用于海冰监测和机器学习研究。