Bayesian Convolutional Neural Networks for Uncertainty-Aware Classification of Infrasound Events
Sensors · 05.08.2026 · 26 (15) · 4955
DOI: 10.3390/s26154955 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.08.2026. Verfasst von Hao Yin und 8 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Chemistry for NBC Hazards Protection, Beijing 102205, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate classification of infrasound signals is essential for nuclear-test verification, natural-hazard warning, and geophysical monitoring. Conventional convolutional neural networks (CNN) applied to this task tend to overfit small, class-imbalanced datasets and cannot quantify predictive uncertainty. To address these limitations, we introduce a Bayesian CNN framework that treats network weights as probability distributions and performs inference by variational approximation. LeNet-5, AlexNet, and 4Conv3Fc network serve as baselines and are converted into Bayes LeNet-5, Bayes AlexNet, and Bayes 4Conv3Fc. The short-time Fourier transform (STFT) provides time–frequency spectrograms as model input. On a highly imbalanced dataset comprising nuclear tests, chemical explosions, volcanic eruptions, rocket launches, earthquakes, and lightning, Bayes 4Conv3Fc reaches an overall accuracy of 99.14% without any data augmentation. Relative to the deterministic baselines, precision, recall, and F1-score increase by up to 6.91, 7.12, and 7.20 percentage points, respectively, and Cohen’s Kappa coefficient by up to 8.86 percentage points. Against class-weighted cross-entropy, a standard imbalance-handling baseline, the Bayesian models yield consistently lower Brier scores, indicating that the gains stem from principled uncertainty modelling rather than loss re-weighting alone.. This study quantifies both epistemic and aleatoric uncertainty in an infrasound signal classification model, and the calibration analysis validates that these uncertainty estimates are reliable, providing a basis for evaluating prediction reliability and diagnosing potential failure modes, thereby contributing to improved model interpretability. Coupled with an event-level data partitioning strategy, the evaluation faithfully reflects the model’s generalization to unseen events and offers a promising direction toward uncertainty-aware infrasound monitoring.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Chemistry for NBC Hazards Protection, Beijing 102205, China.
Zitieren
APA
Yin, H., Zhang, K., Lu, Y., Chang, Y., Wu, Y., Yang, F., Li, X., Xu, J., & Pang, X. (2026). Bayesian Convolutional Neural Networks for Uncertainty-Aware Classification of Infrasound Events. Sensors, 26(15), 4955. https://doi.org/10.3390/s26154955
Vancouver
Yin H, Zhang K, Lu Y, Chang Y, Wu Y, Yang F, et al. Bayesian Convolutional Neural Networks for Uncertainty-Aware Classification of Infrasound Events. Sensors. 2026;26(15):4955. doi:10.3390/s26154955
BibTeX
@article{Yin2026,
author = {Yin, Hao and Zhang, Kai and Lu, Yu and Chang, Yunfen and Wu, Yunhui and Yang, Fan and Li, Xuexu and Xu, Jiaoheng and Pang, Xinliang},
title = {Bayesian Convolutional Neural Networks for Uncertainty-Aware Classification of Infrasound Events},
journal = {Sensors},
year = {2026},
volume = {26},
number = {15},
pages = {4955},
doi = {10.3390/s26154955}
}
EUVIMED