Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic
The decline of sea ice in the Arctic region is a critical indicator of rapid global warming and can also influence the feedback processes in the Arctic, so the prediction of sea ice extent and thickness plays an important role in climate modeling and prediction. This paper uses machine learning meth...
Published in: | Atmosphere |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/atmos14061023 https://doaj.org/article/bc1c70773abe4c3c93e8d3cbd094c58c |
id |
ftdoajarticles:oai:doaj.org/article:bc1c70773abe4c3c93e8d3cbd094c58c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:bc1c70773abe4c3c93e8d3cbd094c58c 2023-07-23T04:17:21+02:00 Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic Siwen Chen Kehan Li Hongpeng Fu Ying Cheng Wu Yiyi Huang 2023-06-01T00:00:00Z https://doi.org/10.3390/atmos14061023 https://doaj.org/article/bc1c70773abe4c3c93e8d3cbd094c58c EN eng MDPI AG https://www.mdpi.com/2073-4433/14/6/1023 https://doaj.org/toc/2073-4433 doi:10.3390/atmos14061023 2073-4433 https://doaj.org/article/bc1c70773abe4c3c93e8d3cbd094c58c Atmosphere, Vol 14, Iss 1023, p 1023 (2023) sea ice extent machine learning subregional analysis climate modeling global warming Meteorology. Climatology QC851-999 article 2023 ftdoajarticles https://doi.org/10.3390/atmos14061023 2023-07-02T00:39:01Z The decline of sea ice in the Arctic region is a critical indicator of rapid global warming and can also influence the feedback processes in the Arctic, so the prediction of sea ice extent and thickness plays an important role in climate modeling and prediction. This paper uses machine learning methods to predict the sea ice extent, and by adjusting the methods and factors, which include the climate variables, the past sea ice extent, and the simple linear-regression-simulated sea ice extent, then we found the best combination to give the result with the highest R 2 score. We noticed that with longer periods of past sea ice extent data and shorter periods of climate data, the results appeared to be better. This might be related to the difference in climate and ocean memory. The sub-region sea ice extent prediction shows that the regions with whole-year ice cover are easier to predict and that those regions with sudden weather changes and significant seasonal variability appear to have lower R 2 scores in the sea ice extent prediction. Article in Journal/Newspaper Arctic Global warming Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Atmosphere 14 6 1023 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
sea ice extent machine learning subregional analysis climate modeling global warming Meteorology. Climatology QC851-999 |
spellingShingle |
sea ice extent machine learning subregional analysis climate modeling global warming Meteorology. Climatology QC851-999 Siwen Chen Kehan Li Hongpeng Fu Ying Cheng Wu Yiyi Huang Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic |
topic_facet |
sea ice extent machine learning subregional analysis climate modeling global warming Meteorology. Climatology QC851-999 |
description |
The decline of sea ice in the Arctic region is a critical indicator of rapid global warming and can also influence the feedback processes in the Arctic, so the prediction of sea ice extent and thickness plays an important role in climate modeling and prediction. This paper uses machine learning methods to predict the sea ice extent, and by adjusting the methods and factors, which include the climate variables, the past sea ice extent, and the simple linear-regression-simulated sea ice extent, then we found the best combination to give the result with the highest R 2 score. We noticed that with longer periods of past sea ice extent data and shorter periods of climate data, the results appeared to be better. This might be related to the difference in climate and ocean memory. The sub-region sea ice extent prediction shows that the regions with whole-year ice cover are easier to predict and that those regions with sudden weather changes and significant seasonal variability appear to have lower R 2 scores in the sea ice extent prediction. |
format |
Article in Journal/Newspaper |
author |
Siwen Chen Kehan Li Hongpeng Fu Ying Cheng Wu Yiyi Huang |
author_facet |
Siwen Chen Kehan Li Hongpeng Fu Ying Cheng Wu Yiyi Huang |
author_sort |
Siwen Chen |
title |
Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic |
title_short |
Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic |
title_full |
Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic |
title_fullStr |
Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic |
title_full_unstemmed |
Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic |
title_sort |
sea ice extent prediction with machine learning methods and subregional analysis in the arctic |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/atmos14061023 https://doaj.org/article/bc1c70773abe4c3c93e8d3cbd094c58c |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Global warming Sea ice |
genre_facet |
Arctic Global warming Sea ice |
op_source |
Atmosphere, Vol 14, Iss 1023, p 1023 (2023) |
op_relation |
https://www.mdpi.com/2073-4433/14/6/1023 https://doaj.org/toc/2073-4433 doi:10.3390/atmos14061023 2073-4433 https://doaj.org/article/bc1c70773abe4c3c93e8d3cbd094c58c |
op_doi |
https://doi.org/10.3390/atmos14061023 |
container_title |
Atmosphere |
container_volume |
14 |
container_issue |
6 |
container_start_page |
1023 |
_version_ |
1772178964560740352 |