Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network
To meet the increasing sailing demand of the Northeast Passage of the Arctic, a daily prediction model of sea ice concentration (SIC) based on the convolutional long short-term memory network (ConvLSTM) algorithm was proposed in this study. Previously, similar deep learning algorithms (such as convo...
Published in: | Journal of Marine Science and Engineering |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/jmse9030330 |
id |
ftmdpi:oai:mdpi.com:/2077-1312/9/3/330/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2077-1312/9/3/330/ 2023-08-20T04:03:57+02:00 Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network Quanhong Liu Ren Zhang Yangjun Wang Hengqian Yan Mei Hong agris 2021-03-16 application/pdf https://doi.org/10.3390/jmse9030330 EN eng Multidisciplinary Digital Publishing Institute Physical Oceanography https://dx.doi.org/10.3390/jmse9030330 https://creativecommons.org/licenses/by/4.0/ Journal of Marine Science and Engineering; Volume 9; Issue 3; Pages: 330 SIC daily prediction ConvLSTM CNNs predictability arctic Text 2021 ftmdpi https://doi.org/10.3390/jmse9030330 2023-08-01T01:17:49Z To meet the increasing sailing demand of the Northeast Passage of the Arctic, a daily prediction model of sea ice concentration (SIC) based on the convolutional long short-term memory network (ConvLSTM) algorithm was proposed in this study. Previously, similar deep learning algorithms (such as convolutional neural networks; CNNs) were frequently used to predict monthly changes in sea ice. To verify the validity of the model, the ConvLSTM and CNNs models were compared based on their spatiotemporal scale by calculating the spatial structure similarity, root-mean-square-error, and correlation coefficient. The results show that in the entire test set, the single prediction effect of ConvLSTM was better than that of CNNs. Taking 15 December 2018 as an example, ConvLSTM was superior to CNNs in simulating the local variations in the sea ice concentration in the Northeast Passage, particularly in the vicinity of the East Siberian Sea. Finally, the predictability of ConvLSTM and CNNs was analysed following the iteration prediction method, demonstrating that the predictability of ConvLSTM was better than that of CNNs. Text Arctic East Siberian Sea Northeast Passage Sea ice MDPI Open Access Publishing Arctic East Siberian Sea ENVELOPE(166.000,166.000,74.000,74.000) Journal of Marine Science and Engineering 9 3 330 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
SIC daily prediction ConvLSTM CNNs predictability arctic |
spellingShingle |
SIC daily prediction ConvLSTM CNNs predictability arctic Quanhong Liu Ren Zhang Yangjun Wang Hengqian Yan Mei Hong Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network |
topic_facet |
SIC daily prediction ConvLSTM CNNs predictability arctic |
description |
To meet the increasing sailing demand of the Northeast Passage of the Arctic, a daily prediction model of sea ice concentration (SIC) based on the convolutional long short-term memory network (ConvLSTM) algorithm was proposed in this study. Previously, similar deep learning algorithms (such as convolutional neural networks; CNNs) were frequently used to predict monthly changes in sea ice. To verify the validity of the model, the ConvLSTM and CNNs models were compared based on their spatiotemporal scale by calculating the spatial structure similarity, root-mean-square-error, and correlation coefficient. The results show that in the entire test set, the single prediction effect of ConvLSTM was better than that of CNNs. Taking 15 December 2018 as an example, ConvLSTM was superior to CNNs in simulating the local variations in the sea ice concentration in the Northeast Passage, particularly in the vicinity of the East Siberian Sea. Finally, the predictability of ConvLSTM and CNNs was analysed following the iteration prediction method, demonstrating that the predictability of ConvLSTM was better than that of CNNs. |
format |
Text |
author |
Quanhong Liu Ren Zhang Yangjun Wang Hengqian Yan Mei Hong |
author_facet |
Quanhong Liu Ren Zhang Yangjun Wang Hengqian Yan Mei Hong |
author_sort |
Quanhong Liu |
title |
Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network |
title_short |
Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network |
title_full |
Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network |
title_fullStr |
Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network |
title_full_unstemmed |
Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network |
title_sort |
daily prediction of the arctic sea ice concentration using reanalysis data based on a convolutional lstm network |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/jmse9030330 |
op_coverage |
agris |
long_lat |
ENVELOPE(166.000,166.000,74.000,74.000) |
geographic |
Arctic East Siberian Sea |
geographic_facet |
Arctic East Siberian Sea |
genre |
Arctic East Siberian Sea Northeast Passage Sea ice |
genre_facet |
Arctic East Siberian Sea Northeast Passage Sea ice |
op_source |
Journal of Marine Science and Engineering; Volume 9; Issue 3; Pages: 330 |
op_relation |
Physical Oceanography https://dx.doi.org/10.3390/jmse9030330 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/jmse9030330 |
container_title |
Journal of Marine Science and Engineering |
container_volume |
9 |
container_issue |
3 |
container_start_page |
330 |
_version_ |
1774714391461101568 |