Stochastic-Deep Learning Parameterization of Ocean Momentum Forcing
Stochastic-Deep Learning Parameterization of Ocean Momentum Forcing
复制标题
DOI：
10.1029/2021ms002534
复制
发表时间：
2021-09-01
影响因子：
6.8
通讯作者：
Zanna, Laure
中科院分区：
文献类型：
--
作者：
Guillaumin, Arthur P.;Zanna, Laure
跨越数百年的耦合气候模拟无法以足够高的空间分辨率运行，以解决中尺度海洋动力学问题。最近，一些研究已经考虑使用深度学习来参数化宏观海洋方程中的子网格强迫，这些数据来自具有理想化几何形状的仅海洋模拟。我们提出了一个随机深度学习参数化，该参数化是在CM2.6生成的数据上训练的，CM2.6是一个高分辨率的最先进的耦合气候模型。我们训练一个卷积神经网络的次网格动量强迫使用宏观尺度表面速度从几个选定的子域具有不同的动力学制度。在粗网格的每个位置，而不是预测一个单一的数字为子网格动量强迫，我们预测的平均值和标准偏差的高斯概率分布。这种方法需要训练我们的神经网络来最小化负对数似然损失函数，而不是均方误差，这是深度学习应用于参数化问题的标准。因此，每个估计的条件平均次网格强迫与不确定性估计的标准偏差，这将形成一个随机次网格参数化的基础。离线测试表明，我们的参数化可以很好地推广到全球海洋和二氧化碳水平增加的气候，而无需进一步的培训。然后，我们实施我们学到的随机参数化在一个允许涡流的理想化浅水模型。该实现是稳定的，并改善了流的一些统计。我们的工作证明了将深度学习工具与概率方法相结合，在参数化未解决的海洋动力学方面的潜力。
Coupled climate simulations that span several hundred years cannot be run at a high-enough spatial resolution to resolve mesoscale ocean dynamics. Recently, several studies have considered Deep Learning to parameterize subgrid forcing within macroscale ocean equations using data from ocean-only simulations with idealized geometry. We present a stochastic Deep Learning parameterization that is trained on data generated by CM2.6, a high-resolution state-of-the-art coupled climate model. We train a Convolutional Neural Network for the subgrid momentum forcing using macroscale surface velocities from a few selected subdomains with different dynamical regimes. At each location of the coarse grid, rather than predicting a single number for the subgrid momentum forcing, we predict both the mean and standard deviation of a Gaussian probability distribution. This approach requires training our neural network to minimize a negative log-likelihood loss function rather than the Mean Square Error, which has been the standard in applications of Deep Learning to the problem of parameterizations. Each estimate of the conditional mean subgrid forcing is thus associated with an uncertainty estimate-the standard deviation-which will form the basis for a stochastic subgrid parameterization. Offline tests show that our parameterization generalizes well to the global oceans and a climate with increased CO2 levels without further training. We then implement our learned stochastic parameterization in an eddy-permitting idealized shallow water model. The implementation is stable and improves some statistics of the flow. Our work demonstrates the potential of combining Deep Learning tools with a probabilistic approach in parameterizing unresolved ocean dynamics.