A new reduced-order adaptive filter for state estimation in high-dimensional systems (Q1371657)

A simple reduced-order adaptive filter, optimal in the sense of minimum prediction error, is proposed for estimating the state of high-dimensional systems in which the process and observation noise statistics are unknown. Implementation of this filter requires only the integration of two difference equations -- the filtering equation and the associated adjoint equation; no solution of either an algebraic Riccati equation or a Lyapunov equation is needed. The paper gives also an overview of other reduction methods and two applications of the suggested method to a quasi-geostrophic ocean model.