Preprints
https://doi.org/10.5194/tc-2021-282
https://doi.org/10.5194/tc-2021-282
 
21 Sep 2021
21 Sep 2021
Status: a revised version of this preprint is currently under review for the journal TC.

Probabilistic Gridded Seasonal Sea Ice Presence Forecasting using Sequence to Sequence Learning

Nazanin Asadi1, Philippe Lamontagne2, Matthew King2,3, Martin Richard2, and K. Andrea Scott1 Nazanin Asadi et al.
  • 1Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada
  • 2Ocean, Coastal and River Engineering Research Centre, National Research Council Canada, Ottawa, Canada
  • 3Memorial University of Newfoundland, Newfoundland and Labrador, Canada

Abstract. Accurate and timely forecasts of sea ice conditions are crucial for safe shipping operations in the Canadian Arctic and other ice-infested waters. Given the recent observations on the declining trend of Arctic sea ice extent over the past decades due to global warming, machine learning (ML) approaches are deployed to provide accurate short-term to long-term forecasting. This study unlike previous ML approaches in the sea-ice forecasting domain provides a daily spatial map of the probability of ice in the study domain up to 90 days of lead time. The predictions are further used to predict freeze-up/breakup dates and show their capability to capture these events within a valid time period (7 days) at specific locations of interest to communities.

Nazanin Asadi et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on tc-2021-282', Anonymous Referee #1, 27 Oct 2021
  • RC2: 'Comment on tc-2021-282', Anonymous Referee #2, 27 Oct 2021
  • RC3: 'Comment on tc-2021-282', Anonymous Referee #3, 23 Nov 2021

Nazanin Asadi et al.

Nazanin Asadi et al.

Viewed

Total article views: 822 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
581 213 28 822 15 16
  • HTML: 581
  • PDF: 213
  • XML: 28
  • Total: 822
  • BibTeX: 15
  • EndNote: 16
Views and downloads (calculated since 21 Sep 2021)
Cumulative views and downloads (calculated since 21 Sep 2021)

Viewed (geographical distribution)

Total article views: 794 (including HTML, PDF, and XML) Thereof 794 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 30 Jun 2022
Download
Short summary
This study has focused on daily sea ice presence probability forecasting up to 90 days in advance with input variables from the last 3 days before the initial forecast date. The trained models have higher accuracy at early lead days and lower accuracy at longer lead days and freeze-up/breakup season. The analysis shows the model's capability on accurately predicting breakup/freeze-up date within 7 days at early lead day with major improvement over climate normal for breakup date prediction.