Seasonal Arctic sea ice forecasting with probabilistic deep learning
Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical m...
Main Authors: | , , , , , , , , , , , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://discovery.ucl.ac.uk/id/eprint/10134451/1/s41467-021-25257-4.pdf https://discovery.ucl.ac.uk/id/eprint/10134451/ |
id |
ftucl:oai:eprints.ucl.ac.uk.OAI2:10134451 |
---|---|
record_format |
openpolar |
spelling |
ftucl:oai:eprints.ucl.ac.uk.OAI2:10134451 2023-12-24T10:13:51+01:00 Seasonal Arctic sea ice forecasting with probabilistic deep learning Andersson, TR Hosking, JS Pérez-Ortiz, M Paige, B Elliott, A Russell, C Law, S Jones, DC Wilkinson, J Phillips, T Byrne, J Tietsche, S Sarojini, BB Blanchard-Wrigglesworth, E Aksenov, Y Downie, R Shuckburgh, E 2021-12-01 text https://discovery.ucl.ac.uk/id/eprint/10134451/1/s41467-021-25257-4.pdf https://discovery.ucl.ac.uk/id/eprint/10134451/ eng eng https://discovery.ucl.ac.uk/id/eprint/10134451/1/s41467-021-25257-4.pdf https://discovery.ucl.ac.uk/id/eprint/10134451/ open Nature Communications , 12 (1) , Article 5124. (2021) Computer science Cryospheric science Environmental impact Statistics Article 2021 ftucl 2023-11-27T13:07:30Z Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that 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. Article in Journal/Newspaper Arctic Sea ice University College London: UCL Discovery Arctic |
institution |
Open Polar |
collection |
University College London: UCL Discovery |
op_collection_id |
ftucl |
language |
English |
topic |
Computer science Cryospheric science Environmental impact Statistics |
spellingShingle |
Computer science Cryospheric science Environmental impact Statistics Andersson, TR Hosking, JS Pérez-Ortiz, M Paige, B Elliott, A Russell, C Law, S Jones, DC Wilkinson, J Phillips, T Byrne, J Tietsche, S Sarojini, BB Blanchard-Wrigglesworth, E Aksenov, Y Downie, R Shuckburgh, E Seasonal Arctic sea ice forecasting with probabilistic deep learning |
topic_facet |
Computer science Cryospheric science Environmental impact Statistics |
description |
Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that 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. |
format |
Article in Journal/Newspaper |
author |
Andersson, TR Hosking, JS Pérez-Ortiz, M Paige, B Elliott, A Russell, C Law, S Jones, DC Wilkinson, J Phillips, T Byrne, J Tietsche, S Sarojini, BB Blanchard-Wrigglesworth, E Aksenov, Y Downie, R Shuckburgh, E |
author_facet |
Andersson, TR Hosking, JS Pérez-Ortiz, M Paige, B Elliott, A Russell, C Law, S Jones, DC Wilkinson, J Phillips, T Byrne, J Tietsche, S Sarojini, BB Blanchard-Wrigglesworth, E Aksenov, Y Downie, R Shuckburgh, E |
author_sort |
Andersson, TR |
title |
Seasonal Arctic sea ice forecasting with probabilistic deep learning |
title_short |
Seasonal Arctic sea ice forecasting with probabilistic deep learning |
title_full |
Seasonal Arctic sea ice forecasting with probabilistic deep learning |
title_fullStr |
Seasonal Arctic sea ice forecasting with probabilistic deep learning |
title_full_unstemmed |
Seasonal Arctic sea ice forecasting with probabilistic deep learning |
title_sort |
seasonal arctic sea ice forecasting with probabilistic deep learning |
publishDate |
2021 |
url |
https://discovery.ucl.ac.uk/id/eprint/10134451/1/s41467-021-25257-4.pdf https://discovery.ucl.ac.uk/id/eprint/10134451/ |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Nature Communications , 12 (1) , Article 5124. (2021) |
op_relation |
https://discovery.ucl.ac.uk/id/eprint/10134451/1/s41467-021-25257-4.pdf https://discovery.ucl.ac.uk/id/eprint/10134451/ |
op_rights |
open |
_version_ |
1786186634663821312 |