Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration
In this paper, we applied an artificial neural network (ANN) to the short-term prediction of the Arctic sea ice concentration (SIC). The prediction was performed using encoding and decoding processes, in which a gated recurrent unit encodes sequential sea ice data, and a feed-forward neural network...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs11091071 https://doaj.org/article/f7ee8d04d58b4a0eb28ef0b688f0b80d |
id |
ftdoajarticles:oai:doaj.org/article:f7ee8d04d58b4a0eb28ef0b688f0b80d |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:f7ee8d04d58b4a0eb28ef0b688f0b80d 2023-05-15T14:46:38+02:00 Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration Minjoo Choi Liyanarachchi Waruna Arampath De Silva Hajime Yamaguchi 2019-05-01T00:00:00Z https://doi.org/10.3390/rs11091071 https://doaj.org/article/f7ee8d04d58b4a0eb28ef0b688f0b80d EN eng MDPI AG https://www.mdpi.com/2072-4292/11/9/1071 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs11091071 https://doaj.org/article/f7ee8d04d58b4a0eb28ef0b688f0b80d Remote Sensing, Vol 11, Iss 9, p 1071 (2019) artificial neural network gated recurrent unit Arctic sea ice prediction short-term prediction Science Q article 2019 ftdoajarticles https://doi.org/10.3390/rs11091071 2022-12-30T20:19:48Z In this paper, we applied an artificial neural network (ANN) to the short-term prediction of the Arctic sea ice concentration (SIC). The prediction was performed using encoding and decoding processes, in which a gated recurrent unit encodes sequential sea ice data, and a feed-forward neural network model decodes the encoded input data. Because of the large volume of Arctic sea ice data, the ANN predicts the future SIC of each cell individually. The limitation of these singular predictions is that they do not use information from other cells. This results in low accuracy, particularly when there are drastic changes during melting and freezing seasons. To address this issue, we present a new data scheme including global and local SIC information, where the global information is represented by sea ice statistics. We trained ANNs using different data schemes and network architectures, and then compared their performances quantitatively and visually. The results show that, compared with a data scheme that uses only local sea ice information, the newly proposed scheme leads to a significant improvement in prediction accuracy. Article in Journal/Newspaper Arctic Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Remote Sensing 11 9 1071 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
artificial neural network gated recurrent unit Arctic sea ice prediction short-term prediction Science Q |
spellingShingle |
artificial neural network gated recurrent unit Arctic sea ice prediction short-term prediction Science Q Minjoo Choi Liyanarachchi Waruna Arampath De Silva Hajime Yamaguchi Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration |
topic_facet |
artificial neural network gated recurrent unit Arctic sea ice prediction short-term prediction Science Q |
description |
In this paper, we applied an artificial neural network (ANN) to the short-term prediction of the Arctic sea ice concentration (SIC). The prediction was performed using encoding and decoding processes, in which a gated recurrent unit encodes sequential sea ice data, and a feed-forward neural network model decodes the encoded input data. Because of the large volume of Arctic sea ice data, the ANN predicts the future SIC of each cell individually. The limitation of these singular predictions is that they do not use information from other cells. This results in low accuracy, particularly when there are drastic changes during melting and freezing seasons. To address this issue, we present a new data scheme including global and local SIC information, where the global information is represented by sea ice statistics. We trained ANNs using different data schemes and network architectures, and then compared their performances quantitatively and visually. The results show that, compared with a data scheme that uses only local sea ice information, the newly proposed scheme leads to a significant improvement in prediction accuracy. |
format |
Article in Journal/Newspaper |
author |
Minjoo Choi Liyanarachchi Waruna Arampath De Silva Hajime Yamaguchi |
author_facet |
Minjoo Choi Liyanarachchi Waruna Arampath De Silva Hajime Yamaguchi |
author_sort |
Minjoo Choi |
title |
Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration |
title_short |
Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration |
title_full |
Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration |
title_fullStr |
Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration |
title_full_unstemmed |
Artificial Neural Network for the Short-Term Prediction of Arctic Sea Ice Concentration |
title_sort |
artificial neural network for the short-term prediction of arctic sea ice concentration |
publisher |
MDPI AG |
publishDate |
2019 |
url |
https://doi.org/10.3390/rs11091071 https://doaj.org/article/f7ee8d04d58b4a0eb28ef0b688f0b80d |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Remote Sensing, Vol 11, Iss 9, p 1071 (2019) |
op_relation |
https://www.mdpi.com/2072-4292/11/9/1071 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs11091071 https://doaj.org/article/f7ee8d04d58b4a0eb28ef0b688f0b80d |
op_doi |
https://doi.org/10.3390/rs11091071 |
container_title |
Remote Sensing |
container_volume |
11 |
container_issue |
9 |
container_start_page |
1071 |
_version_ |
1766317842541576192 |