气候变化领域集成服务门户(CCPortal): Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization

CCPortal

DOI	10.1029/2018MS001472
	Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization
	Bolton T.; Zanna L.
发表日期	2019
ISSN	19422466
起始页码	376
结束页码	399
卷号	11 期号:1
英文摘要	Oceanographic observations are limited by sampling rates, while ocean models are limited by finite resolution and high viscosity and diffusion coefficients. Therefore, both data from observations and ocean models lack information at small and fast scales. Methods are needed to either extract information, extrapolate, or upscale existing oceanographic data sets, to account for or represent unresolved physical processes. Here we use machine learning to leverage observations and model data by predicting unresolved turbulent processes and subsurface flow fields. As a proof of concept, we train convolutional neural networks on degraded data from a high-resolution quasi-geostrophic ocean model. We demonstrate that convolutional neural networks successfully replicate the spatiotemporal variability of the subgrid eddy momentum forcing, are capable of generalizing to a range of dynamical behaviors, and can be forced to respect global momentum conservation. The training data of our convolutional neural networks can be subsampled to 10–20% of the original size without a significant decrease in accuracy. We also show that the subsurface flow field can be predicted using only information at the surface (e.g., using only satellite altimetry data). Our results indicate that data-driven approaches can be exploited to predict both subgrid and large-scale processes, while respecting physical principles, even when data are limited to a particular region or external forcing. Our in-depth study presents evidence for the successful design of ocean eddy parameterizations for implementation in coarse-resolution climate models. ©2019. The Authors.
英文关键词	data inference; eddies; machine learning; oceanography; turbulence
语种	英语
scopus关键词	Climate models; Convolution; Flow fields; Learning systems; Machine learning; Neural networks; Oceanography; Turbulence; Convolutional neural network; data inference; Data-driven approach; eddies; Momentum conservations; Satellite altimetry data; Spatiotemporal variability; Subgrid parameterization; Deep learning; artificial neural network; data interpretation; eddy; flow field; machine learning; model; oceanography; parameterization; satellite altimetry; spatiotemporal analysis; turbulence
来源期刊	Journal of Advances in Modeling Earth Systems
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/156981
作者单位	Department of Physics, University of Oxford, Oxford, United Kingdom
推荐引用方式 GB/T 7714	Bolton T.,Zanna L.. Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization[J],2019,11(1).
APA	Bolton T.,&Zanna L..(2019).Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization.Journal of Advances in Modeling Earth Systems,11(1).
MLA	Bolton T.,et al."Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization".Journal of Advances in Modeling Earth Systems 11.1(2019).