System Identification in Dynamical Sampling

TL;DR

This paper introduces a novel spatiotemporal sampling scheme for system identification in infinite-dimensional processes, enabling the recovery of convolution operators and initial states from sub-lattice samples, with theoretical and numerical validation.

Contribution

It proposes a new sampling approach exploiting spatiotemporal correlation, generalizes finite-dimensional ideas, and provides algorithms and stability analysis for recovering filters and states.

Findings

Successful recovery of filters and initial states from sub-lattice samples

Development of a generalized Prony method for finite impulse response cases

Numerical experiments demonstrating stability and improved methods

Abstract

We consider the problem of spatiotemporal sampling in a discrete infinite dimensional spatially invariant evolutionary process $x^{(n)}=A^nx$ to recover an unknown convolution operator $A$ given by a filter $a \in \ell^1(\mathbb{Z})$ and an unknown initial state $x$ modeled as avector in $\ell^2(\mathbb{Z})$. Traditionally, under appropriate hypotheses, any $x$ can be recovered from its samples on $\mathbb{Z}$ and $A$ can be recovered by the classical techniques of deconvolution. In this paper, we will exploit the spatiotemporal correlation and propose a new spatiotemporal sampling scheme to recover $A$ and $x$ that allows to sample the evolving states $x,Ax, \cdots, A^{N-1}x$ on a sub-lattice of $\mathbb{Z}$, and thus achieve the spatiotemporal trade off. The spatiotemporal trade off is motivated by several industrial applications \cite{Lv09}. Specifically, we show that $\{x(m\mathbb{Z}), Ax(m\mathbb{Z}), \cdots, A^{N-1}x(m\mathbb{Z}): N \geq 2m\}$ contains enough information to recover a typical "low pass filter" $a$ and $x$ almost surely, in which we generalize the idea of the finite dimensional case in \cite{AK14}. In particular, we provide an algorithm based on a generalized Prony method for the case when both $a$ and $x$ are of finite impulse response and an upper bound of their support is known. We also perform the perturbation analysis based on the spectral properties of the operator $A$ and initial state $x$, and verify them by several numerical experiments. Finally, we provide several other numerical methods to stabilize the method and numerical example shows the improvement.