Your browser doesn't support javascript.
loading
Seasonal Arctic sea ice forecasting with probabilistic deep learning.
Andersson, Tom R; Hosking, J Scott; Pérez-Ortiz, María; Paige, Brooks; Elliott, Andrew; Russell, Chris; Law, Stephen; Jones, Daniel C; Wilkinson, Jeremy; Phillips, Tony; Byrne, James; Tietsche, Steffen; Sarojini, Beena Balan; Blanchard-Wrigglesworth, Eduardo; Aksenov, Yevgeny; Downie, Rod; Shuckburgh, Emily.
Afiliação
  • Andersson TR; British Antarctic Survey, NERC, UKRI, Cambridge, UK. tomand@bas.ac.uk.
  • Hosking JS; British Antarctic Survey, NERC, UKRI, Cambridge, UK.
  • Pérez-Ortiz M; The Alan Turing Institute, London, UK.
  • Paige B; Department of Computer Science, University College London, London, UK.
  • Elliott A; The Alan Turing Institute, London, UK.
  • Russell C; Department of Computer Science, University College London, London, UK.
  • Law S; The Alan Turing Institute, London, UK.
  • Jones DC; School of Mathematics and Statistics, University of Glasgow, Glasgow, UK.
  • Wilkinson J; Amazon Web Services, Tübingen, Germany.
  • Phillips T; The Alan Turing Institute, London, UK.
  • Byrne J; Department of Geography, University College London, London, UK.
  • Tietsche S; British Antarctic Survey, NERC, UKRI, Cambridge, UK.
  • Sarojini BB; British Antarctic Survey, NERC, UKRI, Cambridge, UK.
  • Blanchard-Wrigglesworth E; British Antarctic Survey, NERC, UKRI, Cambridge, UK.
  • Aksenov Y; British Antarctic Survey, NERC, UKRI, Cambridge, UK.
  • Downie R; European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, UK.
  • Shuckburgh E; European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, UK.
Nat Commun ; 12(1): 5124, 2021 08 26.
Article em En | MEDLINE | ID: mdl-34446701
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.

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Ano de publicação: 2021 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Ano de publicação: 2021 Tipo de documento: Article