Data‐Driven Equation Discovery of Ocean Mesoscale Closures
Data‐Driven Equation Discovery of Ocean Mesoscale Closures
复制标题
DOI：
10.1029/2020gl088376
复制
发表时间：
2020-07
影响因子：
5.2
通讯作者：
L. Zanna;T. Bolton
中科院分区：
文献类型：
--
作者：
L. Zanna;T. Bolton
气候模型的分辨率受到计算成本的限制。因此，我们必须依靠参数化来表示在模型所能解析的尺度之下发生的过程。在此，我们聚焦于海洋中尺度涡旋的参数化，并采用机器学习（ML），即相关向量机（RVMs）和卷积神经网络（CNNs），从数据中推导出计算高效的参数化，这些参数化是可解释的和/或包含物理原理的。特别是，我们展示了RVM算法在揭示具有嵌入守恒定律的涡旋参数化的闭式方程方面的有效性。当在一个理想化的海洋模型中实施时，所有的参数化都改善了粗分辨率模拟的统计数据。CNN比RVM更稳定，因此它在重现高分辨率模拟方面的能力高于其他方案；然而，RVM方案是可解释的。这项工作展示了用于海洋气候模型的具有新的物理感知且可解释的机器学习湍流参数化的潜力。
The resolution of climate models is limited by computational cost. Therefore, we must rely on parameterizations to represent processes occurring below the scale resolved by the models. Here, we focus on parameterizations of ocean mesoscale eddies and employ machine learning (ML), namely, relevance vector machines (RVMs) and convolutional neural networks (CNNs), to derive computationally efficient parameterizations from data, which are interpretable and/or encapsulate physics. In particular, we demonstrate the usefulness of the RVM algorithm to reveal closed‐form equations for eddy parameterizations with embedded conservation laws. When implemented in an idealized ocean model, all parameterizations improve the statistics of the coarse‐resolution simulation. The CNN is more stable than the RVM such that its skill in reproducing the high‐resolution simulation is higher than the other schemes; however, the RVM scheme is interpretable. This work shows the potential for new physics‐aware interpretable ML turbulence parameterizations for use in ocean climate models.