George Tom M, Manucharyan Georgy E, Thompson Andrew F
Division of Geological and Planetary Sciences, California Institute of Technology, Pasadena, 1200 E California Blvd, CA, 91125, USA.
The Cavendish Laboratory of Physics, University of Cambridge, JJ Thompson Avenue, Cambridge, CB1 3FZ, UK.
Nat Commun. 2021 Feb 5;12(1):800. doi: 10.1038/s41467-020-20779-9.
Mesoscale eddies have strong signatures in sea surface height (SSH) anomalies that are measured globally through satellite altimetry. However, monitoring the transport of heat associated with these eddies and its impact on the global ocean circulation remains difficult as it requires simultaneous observations of upper-ocean velocity fields and interior temperature and density properties. Here we demonstrate that for quasigeostrophic baroclinic turbulence the eddy patterns in SSH snapshots alone contain sufficient information to estimate the eddy heat fluxes. We use simulations of baroclinic turbulence for the supervised learning of a deep Convolutional Neural Network (CNN) to predict up to 64% of eddy heat flux variance. CNNs also significantly outperform other conventional data-driven techniques. Our results suggest that deep CNNs could provide an effective pathway towards an operational monitoring of eddy heat fluxes using satellite altimetry and other remote sensing products.
中尺度涡旋在通过卫星测高全球测量的海面高度（SSH）异常中具有强烈特征。然而，监测与这些涡旋相关的热量输送及其对全球海洋环流的影响仍然很困难，因为这需要同时观测上层海洋速度场以及内部温度和密度特性。在这里，我们证明，对于准地转斜压湍流，仅SSH快照中的涡旋模式就包含足够的信息来估计涡旋热通量。我们使用斜压湍流模拟对深度卷积神经网络（CNN）进行监督学习，以预测高达64%的涡旋热通量方差。CNN也显著优于其他传统数据驱动技术。我们的结果表明，深度CNN可以为利用卫星测高和其他遥感产品对涡旋热通量进行业务监测提供一条有效途径。
