Saved in:
Bibliographic Details
Main Authors: Liu, Yichen, Xiao, Wei, Chu, Tianguang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.08592
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908950423666688
author Liu, Yichen
Xiao, Wei
Chu, Tianguang
author_facet Liu, Yichen
Xiao, Wei
Chu, Tianguang
contents Reservoir observers provide a data-driven approach to the inference of unmeasured variables from observed ones for nonlinear dynamical systems. While previous studies have demonstrated wide applicability, their performance may vary considerably with different input variables, even compromising reliability in the worst cases. To enhance the performance of inference, we integrate residual calibration and attention mechanism into the reservoir observer design. The residual calibration module leverages information from the estimation residuals to refine the observer output, and the attention mechanism exploits the temporal dependencies of the data to enrich the representation of reservoir internal dynamics. Experiments on typical chaotic systems demonstrate that our method substantially improves inference accuracy, especially for the worst cases resulting from the traditional reservoir observers. We also invoke the notion of transfer entropy to explain the reason for the input-dependent observation discrepancy and the effectiveness of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08592
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reservoir observer enhanced with residual calibration and attention mechanism
Liu, Yichen
Xiao, Wei
Chu, Tianguang
Machine Learning
Chaotic Dynamics
Reservoir observers provide a data-driven approach to the inference of unmeasured variables from observed ones for nonlinear dynamical systems. While previous studies have demonstrated wide applicability, their performance may vary considerably with different input variables, even compromising reliability in the worst cases. To enhance the performance of inference, we integrate residual calibration and attention mechanism into the reservoir observer design. The residual calibration module leverages information from the estimation residuals to refine the observer output, and the attention mechanism exploits the temporal dependencies of the data to enrich the representation of reservoir internal dynamics. Experiments on typical chaotic systems demonstrate that our method substantially improves inference accuracy, especially for the worst cases resulting from the traditional reservoir observers. We also invoke the notion of transfer entropy to explain the reason for the input-dependent observation discrepancy and the effectiveness of the proposed method.
title Reservoir observer enhanced with residual calibration and attention mechanism
topic Machine Learning
Chaotic Dynamics
url https://arxiv.org/abs/2604.08592