IceNet is a probabilistic, deep learning sea ice forecasting system developed by an international team and led by British Antarctic Survey and The Alan Turing Institute [Andersson et al., 2021]. IceNet has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. IceNet advances the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model in seasonal forecasts of summer sea ice, particularly for extreme sea ice events. This step-change in sea ice forecasting ability brings us closer to conservation tools that mitigate risks associated with rapid sea ice loss.

this is a placeholder image
Maps showing IceNet’s 1-month-ahead forecasts for Arctic sea ice over the 2018 melting season (June to August). Overlaid are the predicted and true ice edges, and the error between them.

Research Projects

Code and Data

icenet_architecture
IceNet’s U-Net neural network architecture.

Media

News, Blogs and Podcasts

Talks

Collaborators

British Antarctic Survey | The Alan Turing Institute | others [to do]

Citations

[1] Andersson et al. Seasonal Arctic sea ice forecasting with probabilistic deep learning. Nat Commun 12, 5124 (2021). https://doi.org/10.1038/s41467-021-25257-4

Acknowledgements