71820e7d-c628-4e32-969f-464b7efb187c eng utf8 dataset dataset NERC EDS UK Polar Data Centre +44 (0)1223 221400 British Antarctic Survey, High Cross, Madingley Road Cambridge Cambridgeshire CB3 0ET United Kingdom polardatacentre@bas.ac.uk https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/ information pointOfContact 2021-07-16 ISO 19115 Geographic Information - Metadata ISO 19115:2003(E) European Petroleum Survey Group (EPSG) Geodetic Parameter Registry 2008-11-12 publication European Petroleum Survey Group EPSGadministrator@iogp.org https://www.epsg-registry.org/ EPSG Geodetic Parameter Dataset The EPSG Geodetic Parameter Dataset is a structured dataset of Coordinate Reference Systems and Coordinate Transformations, accessible through this online registry. information publisher urn:ogc:def:crs:EPSG::3031 6.18.3 Forecasts, neural networks, and results from the paper: 'Seasonal Arctic sea ice forecasting with probabilistic deep learning' 2021-07-16 creation 2021-07-16 revision 2021-07-16 publication 2021-07-16 released 1.0 https://doi.org/10.5285/71820e7d-c628-4e32-969f-464b7efb187c doi GB/NERC/BAS/PDC/01526 https://data.bas.ac.uk/ NE/N018028/1 award Please cite this item as: Andersson, T., & Hosking, J. (2021). Forecasts, neural networks, and results from the paper: 'Seasonal Arctic sea ice forecasting with probabilistic deep learning' (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/71820e7d-c628-4e32-969f-464b7efb187c This dataset encompasses data produced in the study 'Seasonal Arctic sea ice forecasting with probabilistic deep learning', published in Nature Communications. The study introduces a new Arctic sea ice forecasting AI system, IceNet, which predicts monthly-averaged sea ice probability (SIP; probability of sea ice concentration > 15%) up to 6 months ahead at 25 km resolution. The study demonstrated IceNet's superior seasonal forecasting skill over a state-of-the-art physics-based sea ice forecasting system, ECMWF SEAS5, and a statistical benchmark. This dataset includes three types of data from the study. Firstly, IceNet's SIP forecasts from 2012/1 - 2020/9. Secondly, the 25 neural network files underlying the IceNet model. Thirdly, CSV files of results from the study. The codebase associated with this work includes a script to download this dataset and reproduce all the paper's figures. This dataset is supported by Wave 1 of The UKRI Strategic Priorities Fund under the EPSRC Grant EP/T001569/1, particularly the "AI for Science" theme within that grant and The Alan Turing Institute. The dataset is also supported by the NERC ACSIS project (grant NE/N018028/1). No credit. completed Andersson, Tom R. British Antarctic Survey Researcher author Hosking, J. Scott British Antarctic Survey Researcher author NERC EDS UK Polar Data Centre +44 (0)1223 221400 British Antarctic Survey, High Cross, Madingley Road Cambridge Cambridgeshire CB3 0ET United Kingdom PDCServiceDesk@bas.ac.uk https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/ information pointOfContact asNeeded completed EARTH SCIENCE > Cryosphere > Sea Ice EARTH SCIENCE > Oceans > Sea Ice theme Global Change Master Directory (GCMD) Science Keywords 2026-01-27 publication 23 Global Change Data Center, Science and Exploration Directorate, Goddard Space Flight Center (GSFC) National Aeronautics and Space Administration (NASA) Greenbelt MD United States of America https://earthdata.nasa.gov/about/gcmd/global-change-master-directory-gcmd-keywords Global Change Master Directory (GCMD) Keywords The information provided on this page seeks to define how the GCMD Keywords are structured, used and accessed. It also provides information on how users can participate in the further development of the keywords. information publisher deep learning forecasting machine learning sea ice theme Arctic place Oceanographic geographical features theme GEMET - INSPIRE themes, version 1.0 2021-01-06 revision otherRestrictions no limitations to public access otherRestrictions no limitations license Open Government Licence v3.0 otherRestrictions This data is governed by the NERC Data Policy: https://www.ukri.org/who-we-are/nerc/our-policies-and-standards/nerc-data-policy/ otherRestrictions This data is governed by the NERC data policy and supplied under Open Government Licence v.3 url url crossReference url url largerWorkCitation url url dependency url url dependency url url dependency doi doi crossReference url url crossReference url url crossReference url url crossReference url url crossReference url url crossReference textTable eng utf8 climatologyMeteorologyAtmosphere -180.0 180.0 16.0 90.0 2012-01-01 2020-09-30 It is recommended that careful attention be paid to the contents of any data, and that the author be contacted with any questions regarding appropriate use. If you find any errors or omissions, please report them to polardatacentre@bas.ac.uk. NERC EDS UK Polar Data Centre +44 (0)1223 221400 British Antarctic Survey, High Cross, Madingley Road Cambridge Cambridgeshire CB3 0ET United Kingdom PDCServiceDesk@bas.ac.uk https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/ information distributor application/x-hdf application/netcdf text/csv bytes 7408818586 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=71820e7d-c628-4e32-969f-464b7efb187c WWW:LINK-1.0-http--link Get Data Download data download bytes 7408818586 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=71820e7d-c628-4e32-969f-464b7efb187c WWW:LINK-1.0-http--link Get Data Download data download bytes 7408818586 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=71820e7d-c628-4e32-969f-464b7efb187c WWW:LINK-1.0-http--link Get Data Download data download dataset Methodology: The IceNet model comprises an ensemble of 25 individual U-Net deep learning models, whose forecasts are averaged to compute the ensemble mean. IceNet's monthly-averaged inputs comprise sea ice concentration (SIC), 11 climate variables, statistical SIC forecasts, and metadata. IceNet is trained to forecast the next 6 months of monthly-averaged SIC classification maps at 25 km resolution. At each grid cell and lead time, IceNet's ensemble members produce a discrete probability distribution over three SIC classes: SIC < 15%, 15% < SIC < 80%, and SIC > 80%. The latter two SIC classes are summed to obtain the sea ice probability, P(SIC > 15%). IceNet's training data comprises climate simulations covering 1850-2100 and observational (reanalysis and satellite) data from 1979-2011. Observational data from 2012-2017 was used to validate the model during production, and 2018-2020 was used as the final test set. After training the IceNet model, we calibrated IceNet's probabilities using 2012-2017 data using an approach called temperature scaling. We then used the held-out data from 2012-2020 to compare IceNet's forecasting skill with a dynamical model (ECMWF SEAS5) and a statistical benchmark (a linear trend extrapolation model). A binary accuracy metric was used to measure performance, which computes the percentage of grid cells with the correct binary prediction for SIC > 15%. We then devised a framework for bounding the ice edge based on predicted SIP values and analysed the ability of IceNet and SEAS5 to bound the ice edge. Finally, we used a variable importance method (permute-and-predict) to identify the climate variables most important for IceNet's forecasts. Full details on the methodology behind the generation of this dataset can be found in the associated paper, particularly the Methods section, as well as the GitHub codebase. We thank the contributors to the Sea Ice Outlooks from 2012 to 2020, whose sea ice extent predictions are used for the sea_ice_outlook_errors.csv file. Data collection: All data was generated using Python v3.7. The IceNet model was developed using the Python package TensorFlow v2.2 Data quality: IceNet makes predictions based on ERA5 reanalysis data and OSI-SAF SIC data - for information on their errors see their associated documentation. IceNet's SIP values were set to zero over a land mask and outside of a monthly maximum SIC climatology mask obtained from OSI-SAF. asNeeded completed