The AutoICE Challenge

˜The œcryosphere, vol. 18, pp. 3471–3494

Abstract

Mapping sea ice in the Arctic is essential for maritime navigation, and growing vessel traffic highlights the necessity of the timeliness and accuracy of sea ice charts. In addition, with the increased availability of satellite imagery, automation is becoming more important. The AutoICE Challenge investigates the possibility of creating deep learning models capable of mapping multiple sea ice parameters automatically from spaceborne synthetic aperture radar (SAR) imagery and assesses the current state of the automatic-sea-ice-mapping scientific field. This was achieved by providing the tools and encouraging participants to adopt the paradigm of retrieving multiple sea ice parameters rather than the current focus on single sea ice parameters, such as concentration. The paper documents the efforts and analyses, compares, and discusses the performance of the top-five participants’ submissions. Participants were tasked with the development of machine learning algorithms mapping the total sea ice concentration, stage of development, and floe size using a state-of-the-art sea ice dataset with dual-polarised Sentinel-1 SAR images and 22 other relevant variables while using professionally labelled sea ice charts from multiple national ice services as reference data. The challenge had 129 teams representing a total of 179 participants, with 34 teams delivering 494 submissions, resulting in a participation rate of 26.4 %, and it was won by a team from the University of Waterloo. Participants were successful in training models capable of retrieving multiple sea ice parameters with convolutional neural networks and vision transformer models. The top participants scored best on the total sea ice concentration and stage of development, while the floe size was more difficult. Furthermore, participants offered intriguing approaches and ideas that could help propel future research within automatic sea ice mapping, such as applying high downsampling of SAR data to improve model efficiency and produce better results.

Authors 34

1. Andreas Stokholm corresponding

   European Space Agency · European Space Research Institute · DTU Space · Technical University of Denmark

   Affiliation as printed

   European Space Research Institute (Frascati, Italy)

   Technical University of Denmark (Kongens Lyngby, Denmark)

   DTU Space, Department of Space Research and Technology, Technical University of Denmark (DTU), Kgs. Lyngby, Denmark

   ϕ-lab, European Space Research Institute (ESRIN), European Space Agency (ESA), Frascati, Italy

2. Jørgen Buus-Hinkler

   Danish Meteorological Institute

   Affiliation as printed

   Danish Meteorological Institute (DMI), Copenhagen, Denmark

3. Tore Wulf

   Danish Meteorological Institute

   Affiliation as printed

   Danish Meteorological Institute (DMI), Copenhagen, Denmark

4. Anton Andreevich Korosov

   Nansen Environmental and Remote Sensing Center

   Affiliation as printed

   Nansen Environmental and Remote Sensing Center (NERSC), Bergen, Norway

5. Roberto Saldo

   DTU Space · Technical University of Denmark

   Affiliation as printed

   DTU Space, Department of Space Research and Technology, Technical University of Denmark (DTU), Kgs. Lyngby, Denmark

6. Leif Toudal Pedersen

   DTU Space · Technical University of Denmark

   Affiliation as printed

   DTU Space, Department of Space Research and Technology, Technical University of Denmark (DTU), Kgs. Lyngby, Denmark

7. David Arthurs
   Affiliation as printed

   Polar View, Herlev, Denmark

8. Ionut Dragan

   SpaceTec Partners

   Affiliation as printed

   SpaceTec Partners, Brussels, Belgium

9. Iacopo Modica
   Affiliation as printed

   GMATICS, Rome, Italy

10. Juan Pedro
    Affiliation as printed

    EarthPulse, Barcelona, Spain

11. Annekatrien Debien

    SpaceTec Partners

    Affiliation as printed

    SpaceTec Partners, Brussels, Belgium

12. Xinwei Chen

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

13. Muhammed Patel

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

14. Fernando J. Pena Cantu

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

15. Javier Noa Turnes

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

16. Jinman Park

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

17. Linlin Xu

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

18. David A. Clausi

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

19. Yuan Fang

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

20. Mingzhe Jiang

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

21. Saeid Taleghanidoozdoozan

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

22. Neil C. Brubacher

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

23. Armina Soleymani

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

24. Zacharie Gousseau

    University of Waterloo

    Affiliation as printed

    Department of System Design Engineering, University of Waterloo, Waterloo, Canada

25. Jacek Komorowski

    Warsaw University of Technology

    Affiliation as printed

    Warsaw University of Technology, Warsaw, Poland

26. David Rijlaarsdam
    Affiliation as printed

    Ubotica Technologies, Dublin, Ireland

27. Jan N. van Rijn Aachen Leiden Institute of Advanced Computer Science

    Leiden University

    Affiliation as printed

    Leiden Institute of Advanced Computer Science, Leiden University, Leiden, the Netherlands

28. Jens Jakobsen

    Danish Meteorological Institute

    Affiliation as printed

    Danish Meteorological Institute (DMI), Copenhagen, Denmark

29. Martin S. J. Rogers

    British Antarctic Survey

    Affiliation as printed

    AI Lab, British Antarctic Survey, Cambridge, United Kingdom

30. Nick Hughes

    Norwegian Meteorological Institute

    Affiliation as printed

    Norwegian Ice Service, Norwegian Meteorological Institute, Oslo, Norway

31. Tom Zagon

    Environment and Climate Change Canada

    Affiliation as printed

    Canadian Ice Service, Environment and Climate Change Canada, Ottawa, Canada

32. Rune Solberg

    Norwegian Computing Center

    Affiliation as printed

    Norwegian Computing Center (NR), Oslo, Norway

33. Nicolas Longépé

    European Space Agency · European Space Research Institute

    Affiliation as printed

    φ-lab , European Space Research Institute (ESRIN) , European Space Agency (ESA) , Frascati , Italy

    ϕ-lab, European Space Research Institute (ESRIN), European Space Agency (ESA), Frascati, Italy

34. Matilde Brandt Kreiner

    Danish Meteorological Institute

    Affiliation as printed

    Danish Meteorological Institute (DMI), Copenhagen, Denmark