论文标题
直接从观察结果学习4DVAR反演
Learning 4DVAR inversion directly from observations
论文作者
论文摘要
变分数据同化和深度学习共享许多共同的算法方面。前者专注于系统状态估计，后者为学习复杂的关系提供了极大的归纳偏见。在这里，我们使用4DVAR算法的机械约束直接从部分和嘈杂的观测值中设计了一种混合体系结构，直接从部分和嘈杂的观察中学习同化任务。最后，我们在一个实验中表明，所提出的方法能够以有趣的正则属性学习所需的反转，并且它也具有计算兴趣。
Variational data assimilation and deep learning share many algorithmic aspects in common. While the former focuses on system state estimation, the latter provides great inductive biases to learn complex relationships. We here design a hybrid architecture learning the assimilation task directly from partial and noisy observations, using the mechanistic constraint of the 4DVAR algorithm. Finally, we show in an experiment that the proposed method was able to learn the desired inversion with interesting regularizing properties and that it also has computational interests.
