Articles | Volume 16, issue 9
https://doi.org/10.5194/tc-16-3753-2022
https://doi.org/10.5194/tc-16-3753-2022
Research article
 | 
22 Sep 2022
Research article |  | 22 Sep 2022

Probabilistic spatiotemporal seasonal sea ice presence forecasting using sequence-to-sequence learning and ERA5 data in the Hudson Bay region

Nazanin Asadi, Philippe Lamontagne, Matthew King, Martin Richard, and K. Andrea Scott

Data sets

The sub-seasonal to seasonal prediction project (S2S) and the prediction of extreme events (https://apps.ecmwf.int/datasets/data/s2s-realtime-daily-averaged-ecmf/levtype=sfc/type=cf/) Frédéric Vitart and Andrew W. Robertson https://doi.org/10.1038/s41612-018-0013-0

ERA5 hourly data on single levels from 1959 to present H. Hersbach, B. Bell, P. Berrisford, G. Biavati, A. Horànyi, J. Muñoz Sabater, J. Nicolas, C. Peubey, R. Radu, I. Rozum, D. Schepers, A. Simmons, C. Soci, D. Dee, and J.-N. Thépaut https://doi.org/10.24381/cds.adbb2d47

Sea Ice Climatic Atlas for the Northern Canadian Waters 1981-2010 CIS https://publications.gc.ca/pub?id=9.697531&sl=0

Ice Archive - Search Criteria CIS https://iceweb1.cis.ec.gc.ca/Archive/page1.xhtml?lang=en

Model code and software

zach-gousseau/sifnet_public: v0.1.0 Zach Gousseau https://doi.org/10.5281/zenodo.6855080

Download
Short summary
Machine learning approaches are deployed to provide accurate daily spatial maps of sea ice presence probability based on ERA5 data as input. Predictions are capable of predicting freeze-up/breakup dates within a 7 d period at specific locations of interest to shipping operators and communities. Forecasts of the proposed method during the breakup season have skills comparing to Climate Normal and sea ice concentration forecasts from a leading subseasonal-to-seasonal forecasting system.