Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ...
Sea ice at the North Pole is vital to global climate dynamics. However, accurately forecasting sea ice poses a significant challenge due to the intricate interaction among multiple variables. Leveraging the capability to integrate multiple inputs and powerful performances seamlessly, many studies ha...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2024
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2405.03929 https://arxiv.org/abs/2405.03929 |
id |
ftdatacite:10.48550/arxiv.2405.03929 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2405.03929 2024-09-09T19:58:41+00:00 Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... Park, Jaesung Hong, Sungchul Cho, Yoonseo Jeon, Jong-June 2024 https://dx.doi.org/10.48550/arxiv.2405.03929 https://arxiv.org/abs/2405.03929 unknown arXiv Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 Artificial Intelligence cs.AI Atmospheric and Oceanic Physics physics.ao-ph FOS Computer and information sciences FOS Physical sciences Article article Preprint CreativeWork 2024 ftdatacite https://doi.org/10.48550/arxiv.2405.03929 2024-06-17T09:14:11Z Sea ice at the North Pole is vital to global climate dynamics. However, accurately forecasting sea ice poses a significant challenge due to the intricate interaction among multiple variables. Leveraging the capability to integrate multiple inputs and powerful performances seamlessly, many studies have turned to neural networks for sea ice forecasting. This paper introduces a novel deep architecture named Unicorn, designed to forecast weekly sea ice. Our model integrates multiple time series images within its architecture to enhance its forecasting performance. Moreover, we incorporate a bottleneck layer within the U-Net architecture, serving as neural ordinary differential equations with convolution operations, to capture the spatiotemporal dynamics of latent variables. Through real data analysis with datasets spanning from 1998 to 2021, our proposed model demonstrates significant improvements over state-of-the-art models in the sea ice concentration forecasting task. It achieves an average MAE improvement ... Article in Journal/Newspaper North Pole Sea ice DataCite North Pole |
institution |
Open Polar |
collection |
DataCite |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Artificial Intelligence cs.AI Atmospheric and Oceanic Physics physics.ao-ph FOS Computer and information sciences FOS Physical sciences |
spellingShingle |
Artificial Intelligence cs.AI Atmospheric and Oceanic Physics physics.ao-ph FOS Computer and information sciences FOS Physical sciences Park, Jaesung Hong, Sungchul Cho, Yoonseo Jeon, Jong-June Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... |
topic_facet |
Artificial Intelligence cs.AI Atmospheric and Oceanic Physics physics.ao-ph FOS Computer and information sciences FOS Physical sciences |
description |
Sea ice at the North Pole is vital to global climate dynamics. However, accurately forecasting sea ice poses a significant challenge due to the intricate interaction among multiple variables. Leveraging the capability to integrate multiple inputs and powerful performances seamlessly, many studies have turned to neural networks for sea ice forecasting. This paper introduces a novel deep architecture named Unicorn, designed to forecast weekly sea ice. Our model integrates multiple time series images within its architecture to enhance its forecasting performance. Moreover, we incorporate a bottleneck layer within the U-Net architecture, serving as neural ordinary differential equations with convolution operations, to capture the spatiotemporal dynamics of latent variables. Through real data analysis with datasets spanning from 1998 to 2021, our proposed model demonstrates significant improvements over state-of-the-art models in the sea ice concentration forecasting task. It achieves an average MAE improvement ... |
format |
Article in Journal/Newspaper |
author |
Park, Jaesung Hong, Sungchul Cho, Yoonseo Jeon, Jong-June |
author_facet |
Park, Jaesung Hong, Sungchul Cho, Yoonseo Jeon, Jong-June |
author_sort |
Park, Jaesung |
title |
Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... |
title_short |
Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... |
title_full |
Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... |
title_fullStr |
Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... |
title_full_unstemmed |
Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations ... |
title_sort |
unicorn: u-net for sea ice forecasting with convolutional neural ordinary differential equations ... |
publisher |
arXiv |
publishDate |
2024 |
url |
https://dx.doi.org/10.48550/arxiv.2405.03929 https://arxiv.org/abs/2405.03929 |
geographic |
North Pole |
geographic_facet |
North Pole |
genre |
North Pole Sea ice |
genre_facet |
North Pole Sea ice |
op_rights |
Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2405.03929 |
_version_ |
1809929711535521792 |