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 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.
| Main Authors: | , , , |
|---|---|
| Format: | Article/Letter to editor biblioteca |
| Language: | English |
| Subjects: | Deep learning, Machine learning, Sea ice, Statistical forecasting, |
| Online Access: | https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-wur-nl-wurpubs-584901 |
|---|---|
| record_format |
koha |
| spelling |
dig-wur-nl-wurpubs-5849012024-10-02 Liu, Yang Bogaardt, Laurens Attema, Jisk Hazeleger, Wilco Article/Letter to editor Monthly Weather Review 149 (2021) 6 ISSN: 0027-0644 Extended-range arctic sea ice forecast with convolutional long short-Term memory networks 2021 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. en application/pdf https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh 10.1175/MWR-D-20-0113.1 https://edepot.wur.nl/550561 Deep learning Machine learning Sea ice Statistical forecasting https://creativecommons.org/licenses/by/4.0/ https://creativecommons.org/licenses/by/4.0/ Wageningen University & Research |
| institution |
WUR NL |
| collection |
DSpace |
| country |
Países bajos |
| countrycode |
NL |
| component |
Bibliográfico |
| access |
En linea |
| databasecode |
dig-wur-nl |
| tag |
biblioteca |
| region |
Europa del Oeste |
| libraryname |
WUR Library Netherlands |
| language |
English |
| topic |
Deep learning Machine learning Sea ice Statistical forecasting Deep learning Machine learning Sea ice Statistical forecasting |
| spellingShingle |
Deep learning Machine learning Sea ice Statistical forecasting 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 |
| 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/Letter to editor |
| topic_facet |
Deep learning Machine learning Sea ice Statistical forecasting |
| 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 |
| url |
https://research.wur.nl/en/publications/extended-range-arctic-sea-ice-forecast-with-convolutional-long-sh |
| work_keys_str_mv |
AT liuyang extendedrangearcticseaiceforecastwithconvolutionallongshorttermmemorynetworks AT bogaardtlaurens extendedrangearcticseaiceforecastwithconvolutionallongshorttermmemorynetworks AT attemajisk extendedrangearcticseaiceforecastwithconvolutionallongshorttermmemorynetworks AT hazelegerwilco extendedrangearcticseaiceforecastwithconvolutionallongshorttermmemorynetworks |
| _version_ |
1813438093023248384 |