Computational Science - ICCS 2021 - 21st International Conference, Krakow, Poland, June 16-18, 2021, Proceedings, Part V
Computational Science - ICCS 2021 - 21st International Conference, Krakow, Poland, June 16-18, 2021, Proceedings, Part V
复制标题
计算科学 - ICCS 2021 - 第 21 届国际会议，波兰克拉科夫，2021 年 6 月 16-18 日，会议记录，第五部分
DOI：
10.1007/978-3-030-77977-1_30
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Amendola M
中科院分区：
文献类型：
--
作者：
Amendola M
数据同化(DA)是一种贝叶斯推理，它将动力系统的状态与仪器在给定时间收集的真实数据结合起来。DA的目标是提高动态系统的精度，使其结果尽可能真实。最流行的DA技术之一是卡尔曼滤波(KF)。当动态系统涉及真实世界的应用程序时，物理系统状态的表示通常会导致大数据问题。对于这些问题，KF结果的计算代价太高，并且要求使用降阶建模技术。在本文中，我们提出了一种新的方法，称为潜在性同化(LA)。它包括在具有非线性编码器功能和非线性译码功能的自动编码器获得的潜在空间中执行KF。在潜在空间中，动态系统用递归神经网络建立的代理模型来表示。具体地，使用长短期记忆(LSTM)网络来训练在潜在空间中模拟动态系统的函数。来自动态模型的数据和来自仪器的真实数据都通过自动编码器进行处理。我们将该方法应用于一个真实的测试用例，结果表明该方法在准确率和效率上都有很好的表现。
Data Assimilation (DA) is a Bayesian inference that combines the state of a dynamical system with real data collected by instruments at a given time. The goal of DA is to improve the accuracy of the dynamic system making its result as real as possible. One of the most popular technique for DA is the Kalman Filter (KF). When the dynamic system refers to a real world application, the representation of the state of a physical system usually leads to a big data problem. For these problems, KF results computationally too expensive and mandates to use of reduced order modeling techniques. In this paper we proposed a new methodology we called Latent Assimilation (LA). It consists in performing the KF in the latent space obtained by an Autoencoder with non-linear encoder functions and non-linear decoder functions. In the latent space, the dynamic system is represented by a surrogate model built by a Recurrent Neural Network. In particular, an Long Short Term Memory (LSTM) network is used to train a function which emulates the dynamic system in the latent space. The data from the dynamic model and the real data coming from the instruments are both processed through the Autoencoder. We apply the methodology to a real test case and we show that the LA has a good performance both in accuracy and in efficiency.