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 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 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 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

Version 2 includes the reference sea ice charts (previously absent) as the AutoICE Challenge has been finalised. The ice charts are both included in numerical format in the netCDF files and in quicklook images containing the SIC, SOD and FLOE for each scene in png format.

This item is part of the Collection https://doi.org/10.11583/DTU.c.6244065

AI4Arctic 海冰挑战数据集由欧洲空间局（ESA）ɸ-lab 发起的 AI4EO 海冰竞赛所产出。竞赛旨在开发深度学习模型，以自动生成海冰图，包括海冰浓度、发育阶段及冰块尺寸（形态）信息。训练数据集包含来自哨兵-1号（Sentinel-1）主动微波合成孔径雷达（SAR）数据和对应的无源微波辐射计（MWR）数据，这些数据由美国宇航局（AMSR2）卫星传感器提供。尽管SAR数据在开放水域与海冰之间存在模糊性，但其空间分辨率较高；而MWR数据在开放水域与冰之间存在良好的对比度。然而，AMSR2 MWR 观测的粗糙分辨率引入了一系列新的障碍，例如陆地溢出，可能导致开放水域附近海岸线海冰预测出现误差。挑战数据集中的标签数据为冰图，由丹麦气象研究所（DMI）的格陵兰冰服务和加拿大冰服务（CIS）为航行安全所制作。挑战数据集还包含其他辅助数据，如陆地向距离和数值天气预报模型数据。场景时间跨度为2018年1月8日至2021年12月21日。数据集存在两种版本，'raw' 和 'ready-to-train' 版本，以及相应的测试数据集。每个数据集均包含相同的513个训练场景和20个测试场景（无标签数据）。
'ready-to-train' 版本已进一步准备用于模型训练，例如将数据从40米像素间距下采样到80米，标准化缩放，转换冰图（海冰浓度、发育阶段和冰块尺寸），移除空值，掩膜对齐等。这是 'ready-to-train' 版本的测试数据，不包含参考数据。更多详细信息请参阅与数据集一同发布的通用手册：“AI4Arctic_challenge-dataset-manual”。获取 'ready-to-train' 数据集的入门工具包的代码：https://github.com/astokholm/AI4ArcticSeaIceChallenge。关于挑战的快速视频概述可在：https://youtu.be/iuXIeLPyKfg 查看。
版本2包含参考海冰图（之前缺失），因为 AutoICE 挑战赛已圆满结束。冰图既包含在 netCDF 文件中的数值格式，也包含在 png 格式的快速查看图像中，每个场景包含 SIC、SOD 和 FLOE。
该条目是收藏品的一部分：https://doi.org/10.11583/DTU.c.6244065