Physics-informed deep-learning parameterization of ocean vertical mixing improves climate simulations
文献类型：CNKI期刊论文
| 作者 | Yuchao Zhu ; Rong-Hua Zhang; James N.Moum; Fan Wang; Xiaofeng Li; Delei Li
|
| 发表日期 | 2022-08-31 |
| 出处 | National Science Review
 |
| 关键词 | physics-informed deep learning climate model biases ocean vertical-mixing parameterizations long-term turbulence data artificial neural networks under physics constraint |
| 英文摘要 | Uncertainties in ocean-mixing parameterizations are primary sources for ocean and climate modeling biases. Due to lack of process understanding, traditional physics-driven parameterizations perform unsatisfactorily in the tropics. Recent advances in the deep-learning method and the new availability of long-term turbulence measurements provide an opportunity to explore data-driven approaches to parameterizing oceanic vertical-mixing processes. Here, we describe a novel parameterization based on an artificial neural network trained using a decadal-long time record of hydrographic and turbulence observations in the tropical Pacific. This data-driven parameterization achieves higher accuracy than current parameterizations, demonstrating good generalization ability under physical constraints. When integrated into an ocean model, our parameterization facilitates improved simulations in both ocean-only and coupled modeling. As a novel application of machine learning to the geophysical fluid, these results show the feasibility of using limited observations and well-understood physical constraints to construct a physics-informed deep-learning parameterization for improved climate simulations. |
| 文献子类 | CNKI期刊论文 |
| 资助机构 | supported by the National Natural Science Foundation of China (NSFC)(41906007 and 42030410) ; supported by the NSFC (41730534 and 42090040) ; the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA19060102, XDB40000000 and XDB42000000) ; supported by the US National Science Foundation(1256620, 1431518 and 2048631) ; supported by the NSFC-Shandong Science Foundation (U2006211) ; supported by the National Key Research and Development Program of China (2017YFA0604100) |
| 卷 | v.9期:08页:167-174 |
| 语种 | 英文; |
| 分类号 | TP18;P714.2 |
| ISSN号 | 2095-5138 |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/187342]  |
| 专题 | 中国科学院海洋研究所 |
| 作者单位 | 1.PilotNationalLaboratoryforMarineScienceandTechnology(Qingdao) 2.CollegeofEarth,OceanandAtmosphericSciences,OregonStateUniversity 3.CenterforExcellenceinQuaternaryScienceandGlobalChange,ChineseAcademyofSciences 4.CASKeyLaboratoryofOceanCirculationandWaves,InstituteofOceanology,andCenterforOceanMega-Science,ChineseAcademyofSciences 5.UniversityofChineseAcademyofSciences |
| 推荐引用方式 GB/T 7714 | Yuchao Zhu,Rong-Hua Zhang,James N.Moum,et al. Physics-informed deep-learning parameterization of ocean vertical mixing improves climate simulations. 2022. |
入库方式： OAI收割
来源：海洋研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。