Physics-Informed Learning for Robust Acoustic Localization with Calibrated Uncertainty

2026-08-09

AI Summary

In complex outdoor acoustic environments, conventional sound source localization methods suffer significant performance degradation due to multipath propagation, near-field effects, and non-ideal transmission conditions. This work proposes a physics-guided learning framework that integrates physically informed acoustic features, a hyperbolic solver, and deep learning, enabling end-to-end training to correct implausible solutions arising under non-ideal conditions. The approach preserves the median accuracy of classical solvers while substantially reducing worst-case errors and providing geometry-aware uncertainty estimates. Experimental results demonstrate robust localization performance on both real-world and simulated outdoor microphone array data, supporting scalable, automated wildlife monitoring applications.

Abstract

Recent advances in Passive Acoustic Monitoring (PAM) offer an opportunity to obtain ecological spatial point-process data at unprecedented scale. However, realizing this opportunity necessitates the development of accurate and scalable localization methods. In real-world outdoor soundscapes, however, the assumptions underlying classical localization methods such as hyperbolic and score-based localization are routinely violated by multipath dominance, near-field effects, and complex propagation. Under these conditions, classical localization methods become brittle, with extreme errors possible even in small detection arrays. Rather than statistically replacing the underlying physics, we propose a method to refine it and increase robustness outside of ideal operating conditions: a learned model operating on physics-informed acoustic features corrects a fast hyperbolic solver where it produces implausible solutions, substantially reducing catastrophic worst-case errors while matching its median accuracy on field data. We further provide calibrated, geometry-aware uncertainty estimates suitable for propagation into downstream spatial models. Evaluating on distributed microphone arrays in real and simulated outdoor environments, we demonstrate that the proposed method yields robust, uncertainty-aware localization, providing a step toward scalable automated wildlife monitoring in complex acoustic environments.

Problem

• acoustic localization
• multipath propagation
• near-field effects
• uncertainty calibration
• passive acoustic monitoring

Innovation

• physics-informed learning
• acoustic localization
• uncertainty calibration
• multipath robustness
• passive acoustic monitoring