Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leung, Sze Chai, Zhou, Di, Bae, H. Jane
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911566200307712
author Leung, Sze Chai
Zhou, Di
Bae, H. Jane
author_facet Leung, Sze Chai
Zhou, Di
Bae, H. Jane
contents Optimal sensor placement (OSP) is critical for efficient, accurate monitoring, control, and inference in complex physical systems. We propose a machine-learning-based feature attribution (FA) framework to identify OSP for target predictions. FA quantifies input contributions to a model output; however, it struggles with highly correlated input data often encountered in practical applications for OSP. To address this, we propose a Correlation-Assisted Attribution Framework (CAAF), which introduces a clustering step on the candidate sensor locations before performing FA to reduce redundancy and enhance generalizability. We first illustrate the core principles of the proposed framework through a series of validation cases, then demonstrate its effectiveness in realistic dynamical systems such as structural health monitoring, airfoil lift prediction, and wall-normal velocity estimation for turbulent channel flow. The results show that the CAAF outperforms alternative approaches that typically struggle due to the presence of nonlinear dynamics, chaotic behavior, and multi-scale interactions, and enables the effective application of FA for identifying OSP in real-world environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22517
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)
Leung, Sze Chai
Zhou, Di
Bae, H. Jane
Computational Engineering, Finance, and Science
Machine Learning
Systems and Control
Optimal sensor placement (OSP) is critical for efficient, accurate monitoring, control, and inference in complex physical systems. We propose a machine-learning-based feature attribution (FA) framework to identify OSP for target predictions. FA quantifies input contributions to a model output; however, it struggles with highly correlated input data often encountered in practical applications for OSP. To address this, we propose a Correlation-Assisted Attribution Framework (CAAF), which introduces a clustering step on the candidate sensor locations before performing FA to reduce redundancy and enhance generalizability. We first illustrate the core principles of the proposed framework through a series of validation cases, then demonstrate its effectiveness in realistic dynamical systems such as structural health monitoring, airfoil lift prediction, and wall-normal velocity estimation for turbulent channel flow. The results show that the CAAF outperforms alternative approaches that typically struggle due to the presence of nonlinear dynamics, chaotic behavior, and multi-scale interactions, and enables the effective application of FA for identifying OSP in real-world environments.
title Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)
topic Computational Engineering, Finance, and Science
Machine Learning
Systems and Control
url https://arxiv.org/abs/2510.22517