神经网络参数化的可解释离线-在线训练：小数据机制下的1D重力波-QBO试验台
Explainable Offline-Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave-QBO Testbed in the Small-data Regime
AI总结：
本研究利用一维QBO-GW试验台，对比大数据与小数据机制下神经网络离线训练效果，发现仅两层在线再训练即可产生真实QBO，并通过傅里叶分析揭示其机制，为气候参数化提供通用策略。
摘要：
训练神经网络（NN）作为次网格尺度参数化存在不同策略。在此，我们使用准两年振荡（QBO）和重力波（GW）参数化的一维模型作为试验台。一个12层卷积神经网络，用于预测给定风廓线的重力波强迫，当在大数据机制（100年）下离线训练时，一旦与一维模型耦合，便能产生真实的QBO。相反，在小数据机制（18个月）下离线训练该神经网络，则产生不真实的QBO。然而，仅使用集合卡尔曼反演和仅时间平均的QBO统计量，对该神经网络的仅两层进行在线再训练，所得参数化能产生真实的QBO。对这三个神经网络核的傅里叶分析揭示了再训练为何及如何起作用，并表明这些神经网络主要学习低通、高通以及带通滤波器的组合，这与重力波传播/耗散中局部和非局部动力学的重要性一致。这些发现/策略普遍适用于其他气候过程的数据驱动参数化。
英文摘要：
There are different strategies for training neural networks (NNs) as subgrid-scale parameterizations. Here, we use a 1D model of the quasi-biennial oscillation (QBO) and gravity wave (GW) parameterizations as testbeds. A 12-layer convolutional NN that predicts GW forcings for given wind profiles, when trained offline in a big-data regime (100-years), produces realistic QBOs once coupled to the 1D model. In contrast, offline training of this NN in a small-data regime (18-months) yields unrealistic QBOs. However, online re-training of just two layers of this NN using ensemble Kalman inversion and only time-averaged QBO statistics leads to parameterizations that yield realistic QBOs. Fourier analysis of these three NNs' kernels suggests why/how re-training works and reveals that these NNs primarily learn low-pass, high-pass, and a combination of band-pass filters, consistent with the importance of both local and non-local dynamics in GW propagation/dissipation. These findings/strategies apply to data-driven parameterizations of other climate processes generally.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
