State Estimation Using Sparse DEIM and Recurrent Neural Networks

TL;DR

This paper introduces an equation-free RNN-based framework for state estimation in dynamical systems using sparse observations, overcoming limitations of traditional data assimilation methods and achieving near-optimal accuracy.

Contribution

It proposes a novel RNN-based approach to estimate the kernel vector in S-DEIM without requiring system equations, improving accuracy and convergence.

Findings

RNN-based S-DEIM reduces estimation error by 42-58% compared to Q-DEIM.

Method effective on complex systems like Lorenz-96, Kuramoto-Sivashinsky, and Rayleigh-Benard convection.

Reservoir computing networks suffice for satisfactory state estimation.

Abstract

Sparse Discrete Empirical Interpolation Method (S-DEIM) was recently proposed for state estimation in dynamical systems when only a sparse subset of the state variables can be observed. The S-DEIM estimate involves a kernel vector whose optimal value is inferred through a data assimilation algorithm. This data assimilation step suffers from two drawbacks: (i) It requires the knowledge of the governing equations of the dynamical system, and (ii) It is not generally guaranteed to converge to the optimal kernel vector. To address these issues, here we introduce an equation-free S-DEIM framework that estimates the optimal kernel vector from sparse observational time series using recurrent neural networks (RNNs). We show that the recurrent architecture is necessary since the kernel vector cannot be estimated from instantaneous observations. But RNNs, which incorporate the past history of the observations in the learning process, lead to nearly optimal estimations. We demonstrate the efficacy of our method on three numerical examples with increasing degree of spatiotemporal complexity: a conceptual model of atmospheric flow known as the Lorenz-96 system, the Kuramoto-Sivashinsky equation, and the Rayleigh-Benard convection. In each case, the resulting S-DEIM estimates are satisfactory even when a relatively simple RNN architecture, namely the reservoir computing network, is used. More specifically, our RNN-based S-DEIM state estimations reduce the relative error between 42% and 58% when compared to Q-DEIM which ignores the kernel vector by setting it equal to zero.