Extended-range arctic sea ice forecast with convolutional long short-Term memory networks
Operational Arctic sea ice forecasts are of crucial importance to science and to society in the Arctic region. Currently, statistical and numerical climate models are widely used to generate the Arctic sea ice forecasts at weather time scales. Numerical models require near-real-Time input of relevan...
Published in: | Monthly Weather Review |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh https://doi.org/10.1175/MWR-D-20-0113.1 |
id |
ftunivwagenin:oai:library.wur.nl:wurpubs/584901 |
---|---|
record_format |
openpolar |
spelling |
ftunivwagenin:oai:library.wur.nl:wurpubs/584901 2024-02-11T09:59:19+01:00 Extended-range arctic sea ice forecast with convolutional long short-Term memory networks Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco 2021 application/pdf https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh https://doi.org/10.1175/MWR-D-20-0113.1 en eng https://edepot.wur.nl/550561 https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh doi:10.1175/MWR-D-20-0113.1 https://creativecommons.org/licenses/by/4.0/ Wageningen University & Research Monthly Weather Review 149 (2021) 6 ISSN: 0027-0644 Deep learning Machine learning Sea ice Statistical forecasting Article/Letter to editor 2021 ftunivwagenin https://doi.org/10.1175/MWR-D-20-0113.1 2024-01-24T23:14:45Z Operational Arctic sea ice forecasts are of crucial importance to science and to society in the Arctic region. Currently, statistical and numerical climate models are widely used to generate the Arctic sea ice forecasts at weather time scales. Numerical models require near-real-Time input of relevant environmental conditions consistent with the model equations and they are computationally expensive. In this study, we propose a deep learning approach, namely convolutional long short-Term memory networks (ConvLSTM), to forecast sea ice in the Barents Sea at weather to subseasonal time scales. This is an unsupervised learning approach. It makes use of historical records and it exploits the covariances between different variables, including spatial and temporal relations. With input fields from reanalysis data, we demonstrate that ConvLSTM is able to learn the variability of the Arctic sea ice and can forecast regional sea ice concentration skillfully at weekly to monthly time scales. It preserves the physical consistency between predictors and predictands, and generally outperforms forecasts with climatology, persistence, and a statistical model. Based on the known sources of predictability, sensitivity tests with different climate fields as input for learning were performed. The impact of different predictors on the quality of the forecasts are evaluated and we demonstrate that the surface energy budget components have a large impact on the predictability of sea ice at weather time scales. This method is a promising way to enhance operational Arctic sea ice forecasting in the near future. Article in Journal/Newspaper Arctic Arctic Barents Sea Sea ice Wageningen UR (University & Research Centre): Digital Library Arctic Barents Sea Monthly Weather Review |
institution |
Open Polar |
collection |
Wageningen UR (University & Research Centre): Digital Library |
op_collection_id |
ftunivwagenin |
language |
English |
topic |
Deep learning Machine learning Sea ice Statistical forecasting |
spellingShingle |
Deep learning Machine learning Sea ice Statistical forecasting Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco Extended-range arctic sea ice forecast with convolutional long short-Term memory networks |
topic_facet |
Deep learning Machine learning Sea ice Statistical forecasting |
description |
Operational Arctic sea ice forecasts are of crucial importance to science and to society in the Arctic region. Currently, statistical and numerical climate models are widely used to generate the Arctic sea ice forecasts at weather time scales. Numerical models require near-real-Time input of relevant environmental conditions consistent with the model equations and they are computationally expensive. In this study, we propose a deep learning approach, namely convolutional long short-Term memory networks (ConvLSTM), to forecast sea ice in the Barents Sea at weather to subseasonal time scales. This is an unsupervised learning approach. It makes use of historical records and it exploits the covariances between different variables, including spatial and temporal relations. With input fields from reanalysis data, we demonstrate that ConvLSTM is able to learn the variability of the Arctic sea ice and can forecast regional sea ice concentration skillfully at weekly to monthly time scales. It preserves the physical consistency between predictors and predictands, and generally outperforms forecasts with climatology, persistence, and a statistical model. Based on the known sources of predictability, sensitivity tests with different climate fields as input for learning were performed. The impact of different predictors on the quality of the forecasts are evaluated and we demonstrate that the surface energy budget components have a large impact on the predictability of sea ice at weather time scales. This method is a promising way to enhance operational Arctic sea ice forecasting in the near future. |
format |
Article in Journal/Newspaper |
author |
Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco |
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 |
publishDate |
2021 |
url |
https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh https://doi.org/10.1175/MWR-D-20-0113.1 |
geographic |
Arctic Barents Sea |
geographic_facet |
Arctic Barents Sea |
genre |
Arctic Arctic Barents Sea Sea ice |
genre_facet |
Arctic Arctic Barents Sea Sea ice |
op_source |
Monthly Weather Review 149 (2021) 6 ISSN: 0027-0644 |
op_relation |
https://edepot.wur.nl/550561 https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh doi:10.1175/MWR-D-20-0113.1 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ Wageningen University & Research |
op_doi |
https://doi.org/10.1175/MWR-D-20-0113.1 |
container_title |
Monthly Weather Review |
_version_ |
1790595276934742016 |