OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913347886120960 |
|---|---|
| author | Lu, Bin Zhao, Ze Han, Luyu Gan, Xiaoying Zhou, Yuntao Zhou, Lei Fu, Luoyi Wang, Xinbing Zhou, Chenghu Zhang, Jing |
| author_facet | Lu, Bin Zhao, Ze Han, Luyu Gan, Xiaoying Zhou, Yuntao Zhou, Lei Fu, Luoyi Wang, Xinbing Zhou, Chenghu Zhang, Jing |
| contents | Accurately reconstructing the global ocean deoxygenation over a century is crucial for assessing and protecting marine ecosystem. Existing expert-dominated numerical simulations fail to catch up with the dynamic variation caused by global warming and human activities. Besides, due to the high-cost data collection, the historical observations are severely sparse, leading to big challenge for precise reconstruction. In this work, we propose OxyGenerator, the first deep learning based model, to reconstruct the global ocean deoxygenation from 1920 to 2023. Specifically, to address the heterogeneity across large temporal and spatial scales, we propose zoning-varying graph message-passing to capture the complex oceanographic correlations between missing values and sparse observations. Additionally, to further calibrate the uncertainty, we incorporate inductive bias from dissolved oxygen (DO) variations and chemical effects. Compared with in-situ DO observations, OxyGenerator significantly outperforms CMIP6 numerical simulations, reducing MAPE by 38.77%, demonstrating a promising potential to understand the "breathless ocean" in data-driven manner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07233 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning Lu, Bin Zhao, Ze Han, Luyu Gan, Xiaoying Zhou, Yuntao Zhou, Lei Fu, Luoyi Wang, Xinbing Zhou, Chenghu Zhang, Jing Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Accurately reconstructing the global ocean deoxygenation over a century is crucial for assessing and protecting marine ecosystem. Existing expert-dominated numerical simulations fail to catch up with the dynamic variation caused by global warming and human activities. Besides, due to the high-cost data collection, the historical observations are severely sparse, leading to big challenge for precise reconstruction. In this work, we propose OxyGenerator, the first deep learning based model, to reconstruct the global ocean deoxygenation from 1920 to 2023. Specifically, to address the heterogeneity across large temporal and spatial scales, we propose zoning-varying graph message-passing to capture the complex oceanographic correlations between missing values and sparse observations. Additionally, to further calibrate the uncertainty, we incorporate inductive bias from dissolved oxygen (DO) variations and chemical effects. Compared with in-situ DO observations, OxyGenerator significantly outperforms CMIP6 numerical simulations, reducing MAPE by 38.77%, demonstrating a promising potential to understand the "breathless ocean" in data-driven manner. |
| title | OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning |
| topic | Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2405.07233 |