Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting

Global warming has made the Arctic increasingly available for marine operations and created a demand for reliable operational sea ice forecasts to increase safety. Because ocean-ice numerical models are highly computationally intensive, relatively lightweight ML-based methods may be more efficient f...

Full description

Bibliographic Details
Published in:Remote Sensing
Main Authors: Timofey Grigoryev, Polina Verezemskaya, Mikhail Krinitskiy, Nikita Anikin, Alexander Gavrikov, Ilya Trofimov, Nikita Balabin, Aleksei Shpilman, Andrei Eremchenko, Sergey Gulev, Evgeny Burnaev, Vladimir Vanovskiy
Format: Article in Journal/Newspaper
Language:English
Published: MDPI AG 2022
Subjects:
Q
Online Access:https://doi.org/10.3390/rs14225837
https://doaj.org/article/ff8d86b5fefd489d978a618f0e75a73b
id ftdoajarticles:oai:doaj.org/article:ff8d86b5fefd489d978a618f0e75a73b
record_format openpolar
spelling ftdoajarticles:oai:doaj.org/article:ff8d86b5fefd489d978a618f0e75a73b 2023-05-15T14:57:11+02:00 Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting Timofey Grigoryev Polina Verezemskaya Mikhail Krinitskiy Nikita Anikin Alexander Gavrikov Ilya Trofimov Nikita Balabin Aleksei Shpilman Andrei Eremchenko Sergey Gulev Evgeny Burnaev Vladimir Vanovskiy 2022-11-01T00:00:00Z https://doi.org/10.3390/rs14225837 https://doaj.org/article/ff8d86b5fefd489d978a618f0e75a73b EN eng MDPI AG https://www.mdpi.com/2072-4292/14/22/5837 https://doaj.org/toc/2072-4292 doi:10.3390/rs14225837 2072-4292 https://doaj.org/article/ff8d86b5fefd489d978a618f0e75a73b Remote Sensing, Vol 14, Iss 5837, p 5837 (2022) data-driven models short-term sea ice forecasting deep learning computer vision U-Net remote sensing Science Q article 2022 ftdoajarticles https://doi.org/10.3390/rs14225837 2022-12-30T20:13:19Z Global warming has made the Arctic increasingly available for marine operations and created a demand for reliable operational sea ice forecasts to increase safety. Because ocean-ice numerical models are highly computationally intensive, relatively lightweight ML-based methods may be more efficient for sea ice forecasting. Many studies have exploited different deep learning models alongside classical approaches for predicting sea ice concentration in the Arctic. However, only a few focus on daily operational forecasts and consider the real-time availability of data needed for marine operations. In this article, we aim to close this gap and investigate the performance of the U-Net model trained in two regimes for predicting sea ice for up to the next 10 days. We show that this deep learning model can outperform simple baselines by a significant margin, and we can improve the model’s quality by using additional weather data and training on multiple regions to ensure its generalization abilities. As a practical outcome, we build a fast and flexible tool that produces operational sea ice forecasts in the Barents Sea, the Labrador Sea, and the Laptev Sea regions. Article in Journal/Newspaper Arctic Barents Sea Global warming Labrador Sea laptev Laptev Sea Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Barents Sea Laptev Sea Remote Sensing 14 22 5837
institution Open Polar
collection Directory of Open Access Journals: DOAJ Articles
op_collection_id ftdoajarticles
language English
topic data-driven models
short-term sea ice forecasting
deep learning
computer vision
U-Net
remote sensing
Science
Q
spellingShingle data-driven models
short-term sea ice forecasting
deep learning
computer vision
U-Net
remote sensing
Science
Q
Timofey Grigoryev
Polina Verezemskaya
Mikhail Krinitskiy
Nikita Anikin
Alexander Gavrikov
Ilya Trofimov
Nikita Balabin
Aleksei Shpilman
Andrei Eremchenko
Sergey Gulev
Evgeny Burnaev
Vladimir Vanovskiy
Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
topic_facet data-driven models
short-term sea ice forecasting
deep learning
computer vision
U-Net
remote sensing
Science
Q
description Global warming has made the Arctic increasingly available for marine operations and created a demand for reliable operational sea ice forecasts to increase safety. Because ocean-ice numerical models are highly computationally intensive, relatively lightweight ML-based methods may be more efficient for sea ice forecasting. Many studies have exploited different deep learning models alongside classical approaches for predicting sea ice concentration in the Arctic. However, only a few focus on daily operational forecasts and consider the real-time availability of data needed for marine operations. In this article, we aim to close this gap and investigate the performance of the U-Net model trained in two regimes for predicting sea ice for up to the next 10 days. We show that this deep learning model can outperform simple baselines by a significant margin, and we can improve the model’s quality by using additional weather data and training on multiple regions to ensure its generalization abilities. As a practical outcome, we build a fast and flexible tool that produces operational sea ice forecasts in the Barents Sea, the Labrador Sea, and the Laptev Sea regions.
format Article in Journal/Newspaper
author Timofey Grigoryev
Polina Verezemskaya
Mikhail Krinitskiy
Nikita Anikin
Alexander Gavrikov
Ilya Trofimov
Nikita Balabin
Aleksei Shpilman
Andrei Eremchenko
Sergey Gulev
Evgeny Burnaev
Vladimir Vanovskiy
author_facet Timofey Grigoryev
Polina Verezemskaya
Mikhail Krinitskiy
Nikita Anikin
Alexander Gavrikov
Ilya Trofimov
Nikita Balabin
Aleksei Shpilman
Andrei Eremchenko
Sergey Gulev
Evgeny Burnaev
Vladimir Vanovskiy
author_sort Timofey Grigoryev
title Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
title_short Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
title_full Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
title_fullStr Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
title_full_unstemmed Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
title_sort data-driven short-term daily operational sea ice regional forecasting
publisher MDPI AG
publishDate 2022
url https://doi.org/10.3390/rs14225837
https://doaj.org/article/ff8d86b5fefd489d978a618f0e75a73b
geographic Arctic
Barents Sea
Laptev Sea
geographic_facet Arctic
Barents Sea
Laptev Sea
genre Arctic
Barents Sea
Global warming
Labrador Sea
laptev
Laptev Sea
Sea ice
genre_facet Arctic
Barents Sea
Global warming
Labrador Sea
laptev
Laptev Sea
Sea ice
op_source Remote Sensing, Vol 14, Iss 5837, p 5837 (2022)
op_relation https://www.mdpi.com/2072-4292/14/22/5837
https://doaj.org/toc/2072-4292
doi:10.3390/rs14225837
2072-4292
https://doaj.org/article/ff8d86b5fefd489d978a618f0e75a73b
op_doi https://doi.org/10.3390/rs14225837
container_title Remote Sensing
container_volume 14
container_issue 22
container_start_page 5837
_version_ 1766329267878100992