AI powered

Sea ice forecasts

Tell Me More

About IceNet

What is this AI powered forecasting all about?

IceNet is a deep learning sea ice forecasting system developed by an international team and led by the British Antarctic Survey and The Alan Turing Institute. The original IceNet research model, published in Nature Communications was trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. This version advanced the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model (ECMWF SEAS5) in seasonal forecasts of summer sea ice, particularly for extreme sea ice events.

Since then, the IceNet team has focussed on building an operational version of the model which forecasts on a daily resolution. The original research code was refactored into icenet - a library for operational forecasting. The icenet library can support further research efforts into AI-based operational sea ice forecasting.

In addition, several use cases and an ecosystem of service components are contained within this organisation, supporting execution and downstream analysis.

For further information about the team involved, please look at the project pages at BAS or The Alan Turing Institute.”

Repositories

The various repositories under the IceNet project, click for more information

Getting started

How to get started with the IceNet ecosystem

This submission to the Alan Turing Institute’s Environmental Data Science Book demonstrates the use of the IceNet Python library API for forecasting sea ice for a reduced dataset to demonstrate its capabilities, trained using climate reanalysis and observational data.

A list of outputs

Here's a list of publications, videos and presentations around IceNet and it's infrastructure.

The IceNet Team

Here we name the ongoing collaborators who manage the project.

The IceNet project is a collaboration between The Alan Turing Institute and British Antarctic Survey. It’s only made possible thanks to the contributions of many across the environmental research, data science and international sea-ice and ecosystems communities at large. The names here are only those who continually manage the project, but many more have been responsible for the innovation and research that makes IceNet “an infrastructure for the future”!



Scott Hosking

Scott Hosking

Principal Investigation

James Byrne

James Byrne

Lead Research Software Engineer

Ellen Bowler

Ellen Bowler

Ecosystems Researcher

Alden Conner

Alden Conner

Research Application Manager

Tom Andersson

Tom Andersson

Original ML Researcher

James Robinson

James Robinson

Research Software Engineer

Andrew McDonald

Andrew McDonald

PhD Student

Bryn Noel Ubald

Bryn Noel Ubald

Research Software Engineer

Luigi Tommaso Luppino

Luigi Tommaso Luppino

ML Researcher

Lars Uebbing

Lars Uebbing

PhD Student

Peter Yatsyshin

Peter Yatsyshin

TRF Research Fellow

Ryan Chan

Ryan Chan

Research Software Engineer


Contact Us



Please contact jambyr <at> bas <dot> ac <dot> uk