AutoICE: results of the sea ice classification challenge
AutoICE: results of the sea ice classification challenge
Editor(s): Anton Korosov, Juha Karvonen, Anthony Doulgeris, Suman Singha, and Christian Haas

The Norwegian Computing Center, the Danish Meteorological Institute (DMI), the Technical University of Denmark (DTU), Polar View, the Nansen Environmental and Remote Sensing Center (NERSC), and ESA (European Space Agency) have created an extraordinary sea ice challenge, with the aim to bring together artificial intelligence (AI) and Earth observation players to address the challenge of automated sea ice mapping from Sentinel-1 synthetic aperture radar (SAR) data.

The objective of the AutoICE challenge is to advance the state of the art of sea ice parameter retrieval from SAR data, resulting in an increased capacity to derive more robust and accurate automated sea ice maps. In this challenge, we aim to push forward the new capability to retrieve multiple parameters, specifically, sea ice concentration, stage of development, and floe size (form). The relevance of these capabilities should also be seen in the context of the upcoming Copernicus next-generation Sentinel-1 SAR mission and the Copernicus Polar Expansion mission CIMR (Copernicus Imaging Microwave Radiometer).

The participants of the challenge are welcome to publish their results and approaches in a special issue dedicated to it. In addition, an overview paper will be published describing the challenge and summarizing the results.

Download citations of all papers

24 Oct 2023
MMSeaIce: Multi-task Mapping of Sea Ice Parameters from AI4Arctic Sea Ice Challenge Dataset
Xinwei Chen, Muhammed Patel, Fernando Pena Cantu, Jinman Park, Javier Noa Turnes, Linlin Xu, K. Andrea Scott, and David A. Clausi
EGUsphere, https://doi.org/10.5194/egusphere-2023-1297,https://doi.org/10.5194/egusphere-2023-1297, 2023
Preprint under review for TC (discussion: open, 2 comments)
Short summary
CC BY 4.0