Sea Ice Forecasting using Attention-based Ensemble LSTM ...
Accurately forecasting Arctic sea ice from subseasonal to seasonal scales has been a major scientific effort with fundamental challenges at play. In addition to physics-based earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting....
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Maryland Shared Open Access Repository
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.13016/m2gbqc-q97l https://mdsoar.org/handle/11603/22515 |
id |
ftdatacite:10.13016/m2gbqc-q97l |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.13016/m2gbqc-q97l 2023-08-27T04:07:20+02:00 Sea Ice Forecasting using Attention-based Ensemble LSTM ... Ali, Sahara Huang, Yiyi Huang, Xin Wang, Jianwu 2021 https://dx.doi.org/10.13016/m2gbqc-q97l https://mdsoar.org/handle/11603/22515 unknown Maryland Shared Open Access Repository Creative Commons Attribution 4.0 International Attribution 4.0 International (CC BY 4.0) This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CreativeWork article 2021 ftdatacite https://doi.org/10.13016/m2gbqc-q97l 2023-08-07T14:24:23Z Accurately forecasting Arctic sea ice from subseasonal to seasonal scales has been a major scientific effort with fundamental challenges at play. In addition to physics-based earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven sea ice forecasting, we propose an attention-based Long Short Term Memory (LSTM) ensemble method to predict monthly sea ice extent up to 1 month ahead. Using daily and monthly satellite retrieved sea ice data from NSIDC and atmospheric and oceanic variables from ERA5 reanalysis product for 39 years, we show that our multi-temporal ensemble method outperforms several baseline and recently proposed deep learning models. This will substantially improve our ability in predicting future Arctic sea ice changes, which is fundamental for forecasting transporting routes, resource development, coastal erosion, threats to Arctic coastal communities and wildlife. ... Article in Journal/Newspaper Arctic Sea ice DataCite Metadata Store (German National Library of Science and Technology) Arctic |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
description |
Accurately forecasting Arctic sea ice from subseasonal to seasonal scales has been a major scientific effort with fundamental challenges at play. In addition to physics-based earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven sea ice forecasting, we propose an attention-based Long Short Term Memory (LSTM) ensemble method to predict monthly sea ice extent up to 1 month ahead. Using daily and monthly satellite retrieved sea ice data from NSIDC and atmospheric and oceanic variables from ERA5 reanalysis product for 39 years, we show that our multi-temporal ensemble method outperforms several baseline and recently proposed deep learning models. This will substantially improve our ability in predicting future Arctic sea ice changes, which is fundamental for forecasting transporting routes, resource development, coastal erosion, threats to Arctic coastal communities and wildlife. ... |
format |
Article in Journal/Newspaper |
author |
Ali, Sahara Huang, Yiyi Huang, Xin Wang, Jianwu |
spellingShingle |
Ali, Sahara Huang, Yiyi Huang, Xin Wang, Jianwu Sea Ice Forecasting using Attention-based Ensemble LSTM ... |
author_facet |
Ali, Sahara Huang, Yiyi Huang, Xin Wang, Jianwu |
author_sort |
Ali, Sahara |
title |
Sea Ice Forecasting using Attention-based Ensemble LSTM ... |
title_short |
Sea Ice Forecasting using Attention-based Ensemble LSTM ... |
title_full |
Sea Ice Forecasting using Attention-based Ensemble LSTM ... |
title_fullStr |
Sea Ice Forecasting using Attention-based Ensemble LSTM ... |
title_full_unstemmed |
Sea Ice Forecasting using Attention-based Ensemble LSTM ... |
title_sort |
sea ice forecasting using attention-based ensemble lstm ... |
publisher |
Maryland Shared Open Access Repository |
publishDate |
2021 |
url |
https://dx.doi.org/10.13016/m2gbqc-q97l https://mdsoar.org/handle/11603/22515 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_rights |
Creative Commons Attribution 4.0 International Attribution 4.0 International (CC BY 4.0) This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_doi |
https://doi.org/10.13016/m2gbqc-q97l |
_version_ |
1775348117140406272 |