标题： U-Net 卡尔曼滤波器（UNetKF）：机器学习辅助集合数据同化的示例 显示英文标题

标题： U-Net Kalman Filter (UNetKF): An Example of Machine Learning-assisted Ensemble Data Assimilation

摘要： 机器学习技术在气象和气候科学领域受到了极大的关注。数据同化（DA），即将观测数据和数值模型相结合，有潜力结合机器学习和人工智能（ML/AI）技术。在本文中，我们使用U-Net，一种卷积神经网络（CNN）类型，来预测集合卡尔曼滤波（EnKF）算法的局部集合协方差。使用一个两层的准地转模型，U-Net通过EnKF数据同化实验的数据进行训练。然后将训练好的U-Net用于预测U-Net卡尔曼滤波（UNetKF）实验中的流动依赖的局部误差协方差矩阵，并将其与传统的三维变分（3DVar）、集合三维变分（En3DVar）和EnKF方法进行比较。UNetKF的性能可以达到或超过3DVar、En3DVar或EnKF的性能。我们还证明了训练好的U-Net可以转移到更高分辨率的模型中以实现UNetKF，这再次表现出与3DVar和EnKF相当的性能，尤其是在小集合规模的情况下。 显示英文摘要

摘要： Machine learning techniques have seen a tremendous rise in popularity in weather and climate sciences. Data assimilation (DA), which combines observations and numerical models, has great potential to incorporate machine learning and artificial intelligence (ML/AI) techniques. In this paper, we use U-Net, a type of convolutional neutral network (CNN), to predict the localized ensemble covariances for the Ensemble Kalman Filter (EnKF) algorithm. Using a 2-layer quasi-geostrophic model, U-Nets are trained using data from EnKF DA experiments. The trained U-Nets are then used to predict the flow-dependent localized error covariance matrices in U-Net Kalman Filter (UNetKF) experiments, which are compared to traditional 3-dimensional variational (3DVar), ensemble 3DVar (En3DVar) and EnKF methods. The performance of UNetKF can match or exceed that of 3DVar, En3DVar or EnKF. We also demonstrate that trained U-Nets can be transferred to a higher-resolution model for UNetKF implementation, which again performs competitively to 3DVar and EnKF, particularly for small ensemble sizes.