Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ...
Spatiotemporal projections in marine science are essential for understanding ocean systems and their impact on Earth's climate. However, existing AI-based and statistics-based inversion methods face challenges in leveraging ocean data, generating continuous outputs, and incorporating physical c...
Main Authors: | , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2024
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2408.01509 https://arxiv.org/abs/2408.01509 |
id |
ftdatacite:10.48550/arxiv.2408.01509 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2408.01509 2024-09-30T14:30:59+00:00 Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... Xiong, Zhixi Jiang, Yukang Lu, Wenfang Wang, Xueqin Tian, Ting 2024 https://dx.doi.org/10.48550/arxiv.2408.01509 https://arxiv.org/abs/2408.01509 unknown arXiv Creative Commons Attribution Non Commercial No Derivatives 4.0 International https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode cc-by-nc-nd-4.0 Applications stat.AP FOS: Computer and information sciences CreativeWork Preprint Article article 2024 ftdatacite https://doi.org/10.48550/arxiv.2408.01509 2024-09-02T07:59:33Z Spatiotemporal projections in marine science are essential for understanding ocean systems and their impact on Earth's climate. However, existing AI-based and statistics-based inversion methods face challenges in leveraging ocean data, generating continuous outputs, and incorporating physical constraints. We propose the Marine Dynamic Reconstruction and Forecast Neural Networks (MDRF-Net), which integrates marine physical mechanisms and observed data to reconstruct and forecast continuous ocean temperature-salinity and dynamic fields. MDRF-Net leverages statistical theories and techniques, incorporating parallel neural network sharing initial layer, two-step training strategy, and ensemble methodology, facilitating in exploring challenging marine areas like the Arctic zone. We have theoretically justified the efficacy of our ensemble method and the rationality of it by providing an upper bound on its generalization error.The effectiveness of MDRF-Net's is validated through a comprehensive simulation study, ... : 35 pages, 6 figures ... Article in Journal/Newspaper Arctic DataCite Arctic |
institution |
Open Polar |
collection |
DataCite |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Applications stat.AP FOS: Computer and information sciences |
spellingShingle |
Applications stat.AP FOS: Computer and information sciences Xiong, Zhixi Jiang, Yukang Lu, Wenfang Wang, Xueqin Tian, Ting Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... |
topic_facet |
Applications stat.AP FOS: Computer and information sciences |
description |
Spatiotemporal projections in marine science are essential for understanding ocean systems and their impact on Earth's climate. However, existing AI-based and statistics-based inversion methods face challenges in leveraging ocean data, generating continuous outputs, and incorporating physical constraints. We propose the Marine Dynamic Reconstruction and Forecast Neural Networks (MDRF-Net), which integrates marine physical mechanisms and observed data to reconstruct and forecast continuous ocean temperature-salinity and dynamic fields. MDRF-Net leverages statistical theories and techniques, incorporating parallel neural network sharing initial layer, two-step training strategy, and ensemble methodology, facilitating in exploring challenging marine areas like the Arctic zone. We have theoretically justified the efficacy of our ensemble method and the rationality of it by providing an upper bound on its generalization error.The effectiveness of MDRF-Net's is validated through a comprehensive simulation study, ... : 35 pages, 6 figures ... |
format |
Article in Journal/Newspaper |
author |
Xiong, Zhixi Jiang, Yukang Lu, Wenfang Wang, Xueqin Tian, Ting |
author_facet |
Xiong, Zhixi Jiang, Yukang Lu, Wenfang Wang, Xueqin Tian, Ting |
author_sort |
Xiong, Zhixi |
title |
Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... |
title_short |
Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... |
title_full |
Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... |
title_fullStr |
Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... |
title_full_unstemmed |
Reconstructing and Forecasting Marine Dynamic Variable Fields across Space and Time Globally and Gaplessly ... |
title_sort |
reconstructing and forecasting marine dynamic variable fields across space and time globally and gaplessly ... |
publisher |
arXiv |
publishDate |
2024 |
url |
https://dx.doi.org/10.48550/arxiv.2408.01509 https://arxiv.org/abs/2408.01509 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_rights |
Creative Commons Attribution Non Commercial No Derivatives 4.0 International https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode cc-by-nc-nd-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2408.01509 |
_version_ |
1811635690109140992 |