Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks.
Operational Arctic sea ice forecasts are of crucial importance to commercial and scientific activities in the Arctic region. Currently, numerical climate models, including General Circulation Models (GCMs) and regional climate models, are widely used to generate the Arctic sea ice predictions at wea...
Main Authors: | , , , |
---|---|
Format: | Conference Object |
Language: | English |
Published: |
Zenodo
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.5281/zenodo.3899798 https://zenodo.org/record/3899798 |
id |
ftdatacite:10.5281/zenodo.3899798 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.5281/zenodo.3899798 2023-05-15T14:47:07+02:00 Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco 2020 https://dx.doi.org/10.5281/zenodo.3899798 https://zenodo.org/record/3899798 en eng Zenodo https://zenodo.org/communities/blue-actionh2020 https://dx.doi.org/10.5281/zenodo.3899797 https://zenodo.org/communities/blue-actionh2020 Open Access Creative Commons Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/legalcode info:eu-repo/semantics/openAccess CC-BY Text Presentation article-journal ScholarlyArticle 2020 ftdatacite https://doi.org/10.5281/zenodo.3899798 https://doi.org/10.5281/zenodo.3899797 2021-11-05T12:55:41Z Operational Arctic sea ice forecasts are of crucial importance to commercial and scientific activities in the Arctic region. Currently, numerical climate models, including General Circulation Models (GCMs) and regional climate models, are widely used to generate the Arctic sea ice predictions at weather time-scales. However, these numerical climate models require near real-time input of weather conditions to assure the quality of the predictions and these are hard to obtain and the simulations are computationally expensive. In this study, we propose a deep learning approach to forecasts of sea ice in the Barents sea at weather time scales. To work with such spatial-temporal sequence problems, Convolutional Long Short Term Memory Networks (ConvLSTM) are useful. ConvLSTM are LSTM (Long-Short Term Memory) networks with convolutional cells embedded in the LSTM cells. This approach is unsupervised learning and it can make use of enormous amounts of historical records of weather and climate. With input fields from atmospheric (ERA-Interim) and oceanic (ORAS4) reanalysis data sets, we demonstrate that the ConvLSTM is able to learn the variability of the Arctic sea ice within historical records and effectively predict regional sea ice concentration patterns at weekly to monthly time scales. Based on the known sources of predictability, sensitivity tests with different climate fields were also performed. The influences of different predictors on the quality of predictions are evaluated. This method outperforms predictions with climatology and persistence and is promising to act as a fast and cost-efficient operational sea ice forecast system in the future. : EGU 2020 Session ITS4.3/AS5.2 Conference Object Arctic Barents Sea Sea ice DataCite Metadata Store (German National Library of Science and Technology) Arctic Barents Sea |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
English |
description |
Operational Arctic sea ice forecasts are of crucial importance to commercial and scientific activities in the Arctic region. Currently, numerical climate models, including General Circulation Models (GCMs) and regional climate models, are widely used to generate the Arctic sea ice predictions at weather time-scales. However, these numerical climate models require near real-time input of weather conditions to assure the quality of the predictions and these are hard to obtain and the simulations are computationally expensive. In this study, we propose a deep learning approach to forecasts of sea ice in the Barents sea at weather time scales. To work with such spatial-temporal sequence problems, Convolutional Long Short Term Memory Networks (ConvLSTM) are useful. ConvLSTM are LSTM (Long-Short Term Memory) networks with convolutional cells embedded in the LSTM cells. This approach is unsupervised learning and it can make use of enormous amounts of historical records of weather and climate. With input fields from atmospheric (ERA-Interim) and oceanic (ORAS4) reanalysis data sets, we demonstrate that the ConvLSTM is able to learn the variability of the Arctic sea ice within historical records and effectively predict regional sea ice concentration patterns at weekly to monthly time scales. Based on the known sources of predictability, sensitivity tests with different climate fields were also performed. The influences of different predictors on the quality of predictions are evaluated. This method outperforms predictions with climatology and persistence and is promising to act as a fast and cost-efficient operational sea ice forecast system in the future. : EGU 2020 Session ITS4.3/AS5.2 |
format |
Conference Object |
author |
Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco |
spellingShingle |
Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. |
author_facet |
Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco |
author_sort |
Liu, Yang |
title |
Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. |
title_short |
Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. |
title_full |
Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. |
title_fullStr |
Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. |
title_full_unstemmed |
Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks. |
title_sort |
extended range arctic sea ice forecast with convolutional long-short term memory networks. |
publisher |
Zenodo |
publishDate |
2020 |
url |
https://dx.doi.org/10.5281/zenodo.3899798 https://zenodo.org/record/3899798 |
geographic |
Arctic Barents Sea |
geographic_facet |
Arctic Barents Sea |
genre |
Arctic Barents Sea Sea ice |
genre_facet |
Arctic Barents Sea Sea ice |
op_relation |
https://zenodo.org/communities/blue-actionh2020 https://dx.doi.org/10.5281/zenodo.3899797 https://zenodo.org/communities/blue-actionh2020 |
op_rights |
Open Access Creative Commons Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/legalcode info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.5281/zenodo.3899798 https://doi.org/10.5281/zenodo.3899797 |
_version_ |
1766318261008334848 |