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

2025/10/26 by Sze Chai Leung, Di Zhou, Leung, Sze Chai +3
Computer Science · Engineering · #Computational Engineering #FOS: Computer and information sciences #FOS: Electrical engineering #Finance #Machine Learning (cs.LG) #Systems and Control (eess.SY) #and Science (cs.CE) #cs.CE #cs.LG #cs.SY #eess.SY #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2510.22517

published as Commun. AI Comput. 1, 8 (2026)

arxiv created 2026/06/25 · arxiv updated 2026/08/06

Abstract

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.

Citations

• Deep reinforcement learning of airfoil pitch control in a highly disturbed environment using partial observations
• Environmental Sensor Placement with Convolutional Gaussian Neural Processes
• Algorithms to estimate Shapley value feature attributions
• Explainable AI: A Review of Machine Learning Interpretability Methods
• Optimal Experimental Design for Inverse Problems in the Presence of Observation Correlations
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• Interpreting Interpretations: Organizing Attribution Methods by Criteria
• A layered multiple importance sampling scheme for focused optimal Bayesian experimental design
• Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
• A Unified Approach to Interpreting Model Predictions
• Axiomatic Attribution for Deep Networks
• Temporal Convolutional Networks: A Unified Approach to Action Segmentation
• Sequential Bayesian optimal experimental design via approximate dynamic programming
• Lazier Than Lazy Greedy
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet Large Scale Visual Recognition Challenge
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• On the optimal sensor placement techniques for a bridge structure
• On the statistics of wind gusts
• Numerical solution of the Navier-Stokes equations

Related

• Optimal sensor placement using machine learning
• Measurement Optimization under Uncertainty using Deep Reinforcement Learning
• Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure Measurements
• Human-Interpretable Uncertainty Explanations for Point Cloud Registration
• Physics-informed sensor coverage through structure preserving machine learning