Multi-Task Deep Learning Based Spatiotemporal Arctic Sea Ice Forecasting

Simple item page
dc.contributor.authorKim, Eliot
dc.contributor.authorKruse, Peter
dc.contributor.authorLama, Skylar
dc.contributor.authorBourne Jr., Jamal
dc.contributor.authorHu, Michael
dc.contributor.authorAli, Sahara
dc.contributor.authorHuang, Yiyi
dc.contributor.authorWang, Jianwu
dc.date.accessioned2022-09-26T15:27:02Z
dc.date.available2022-09-26T15:27:02Z
dc.date.issued2022-01-13
dc.description2021 IEEE International Conference on Big Data (Big Data), 15-18 December 2021, Orlando, FL, USAen_US
dc.description.abstractCritical natural resources and processes in the Arctic depend heavily on sea ice. Thus, accurate and timely predictions of Arctic sea ice changes is important. Arctic sea ice forecasting involves two connected tasks: predicting sea ice concentration (SIC) at each pixel and predicting overall sea ice extent (SIE). Instead of having two separate models for these two forecasting tasks, in this paper we study how to use multi- task learning techniques and leverage the connections between ice concentration and ice extent to improve accuracy for both forecasting tasks. Because of the spatiotemporal nature of the data, we designed two novel multi-task learning models based on the CNN and ConvLSTM, respectively. Further, in conjunction with multi-task models, we developed custom loss functions which train the models to ignore land pixels and optimize for both concentration and extent when making predictions. Our experiments show that multi-task models provide better accuracy for a 1-month lead time than models that predict sea ice extent and concentration separately. Our accuracies are better than or comparable to results in related state-of-the-art studies. Our best model in SIC prediction outperformed the best existing SIC prediction model in the literature with 1.78% less error, and our best model in SIE prediction outperformed the best existing SIE prediction model with 0.283 million km2 less error.en_US
dc.description.sponsorshipThis work is supported by the grant “REU Site: Online Interdisciplinary Big Data Analytics in Science and Engineer- ing” from the National Science Foundation (grant no. OAC– 2050943). Co-author Ali and Wang additionally acknowledge support by the grant “CAREER: Big Data Climate Causality Analytics” from the National Science Foundation (grant no. OAC–1942714). The hardware used in the computational studies is part of the UMBC High Performance Computing Facility (HPCF). The facility is supported by the U.S. Na- tional Science Foundation through the MRI program (grant nos. CNS–0821258, CNS–1228778, and OAC–1726023) and the SCREMS program (grant no. DMS–0821311), with ad- ditional substantial support from the University of Maryland, Baltimore County (UMBC).en_US
dc.description.urihttps://ieeexplore.ieee.org/document/9671491en_US
dc.format.extent11 pagesen_US
dc.genreconference papers and proceedingsen_US
dc.genrepreprintsen_US
dc.genrecomputer codeen_US
dc.identifierdoi:10.13016/m22s49-wraa
dc.identifier.citationE. Kim et al., "Multi-Task Deep Learning Based Spatiotemporal Arctic Sea Ice Forecasting," 2021 IEEE International Conference on Big Data (Big Data), 2021, pp. 1847-1857, doi: 10.1109/BigData52589.2021.9671491.en_US
dc.identifier.urihttps://doi.org/10.1109/BigData52589.2021.9671491
dc.identifier.urihttp://hdl.handle.net/11603/25881
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Information Systems Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rights© 2021 IEEE.  Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.subjectUMBC Big Data Analytics Laben_US
dc.subjectUMBC High Performance Computing Facility (HPCF)
dc.titleMulti-Task Deep Learning Based Spatiotemporal Arctic Sea Ice Forecastingen_US
dc.typeTexten_US
dcterms.creatorhttps://orcid.org/0000-0002-9933-1170en_US

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
team-1.zip
Size:
45.56 KB
Format:
Unknown data format
Description:
Code
Download
Thumbnail Image
Name:
2021-Multi-Task Deep Learning Based Spatiotemporal Arctic Sea Ice Forecasting-(Big Data 2021).pdf
Size:
2.14 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Information Systems Department
UMBC Faculty Collection
UMBC Student Collection