Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs

2025-11-27 · Feyza Eksen, Stefan Oehmcke, Stefan Lüdtke arxiv

Accurate sensor placement is critical for modeling spatio-temporal systems such as environmental and climate processes. Neural Processes (NPs), particularly Convolutional Conditional Neural Processes (ConvCNPs), provide scalable probabilistic models with uncertainty estimates, making them well-suited for data-driven sensor placement. However, existing approaches rely on total predictive uncertainty, which conflates epistemic and aleatoric components, that may lead to suboptimal sensor selection in ambiguous regions. To address this, we propose expected reduction in epistemic uncertainty as a new acquisition function for sensor placement. To enable this, we extend ConvCNPs with a Mixture Density Networks (MDNs) output head for epistemic uncertainty estimation. Preliminary results suggest that epistemic uncertainty driven sensor placement more effectively reduces model error than approaches based on overall uncertainty.

📄 PDF Abstract BibTeX arXiv:2511.22567

Code (0)

등록된 구현이 없습니다.

Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure Measurements

2025-01-06 · Hanieh Mousavi, Jeff D. Eldredge

This paper presents a novel machine-learning framework for reconstructing low-order gust-encounter flow field and lift coefficients from sparse, noisy surface pressure measurements. Our study thoroughly investigates the …

Computational Efficiency Uncertainty Quantification Variational Inference

TWO-STEP UNCERTAINTY NETWORK FOR TASKDRIVEN SENSOR PLACEMENT

2019-09-25 · Yangyang Sun, Yang Zhang, Hassan Foroosh, Shuo Pang

Optimal sensor placement achieves the minimal cost of sensors while obtaining the prespecified objectives. In this work, we propose a framework for sensor placement to maximize the information gain called Two-step Uncert…

Vocal Bursts Valence Prediction

DEUP: Direct Epistemic Uncertainty Prediction

2021-02-16 · Salem Lahlou, Moksh Jain, Hadi Nekoei, Victor Ion Butoi 외

Epistemic Uncertainty is a measure of the lack of knowledge of a learner which diminishes with more evidence. While existing work focuses on using the variance of the Bayesian posterior due to parameter uncertainty as a …

Active Learning image-classification Image Classification Model Optimization+2

Optimal Coupled Sensor Placement and Path-Planning in Unknown Time-Varying Environments

2025-01-31 · Prakash Poudel, Raghvendra V. Cowlagi

We address path-planning for a mobile agent to navigate in an unknown environment with minimum exposure to a spatially and temporally varying threat field. The threat field is estimated using pointwise noisy measurements…

Computational Efficiency Navigate

Measurement Optimization under Uncertainty using Deep Reinforcement Learning

2023-03-17 · Amin Jabini, Erik A. Johnson

Optimal sensor placement enhances the efficiency of a variety of applications for monitoring dynamical systems. It has been established that deterministic solutions to the sensor placement problem are insufficient due to…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)