Articles | Volume 26, issue 9
https://doi.org/10.5194/nhess-26-4529-2026
https://doi.org/10.5194/nhess-26-4529-2026
Research article
 | 
23 Sep 2026
Research article |  | 23 Sep 2026

Infra-Net: a robust parallel decision-making network for discriminating natural hazards and anthropogenic infrasound events via multi-view feature learning

Hongru Li, Xihai Li, Jihao Liu, Shengjie Luo, and Yun Zhang

Cited articles

Abbaszadeh, M., Soltani, S. M., and Ahmed, A. N.: Optimization of support vector machine parameters in modeling of Iju deposit mineralization and alteration zones using particle swarm optimization algorithm and grid search method, Comput. Geosci., 165, 105140, https://doi.org/10.1016/j.cageo.2022.105140, 2022. 
Ai, L., Wang, J., and Wang, X.: Multi-features fusion diagnosis of tremor based on artificial neural network and D–S evidence theory, Signal. Process., 88, 2927–2935, https://doi.org/10.1016/j.sigpro.2008.06.018, 2008. 
Al, J. A. and Khushaba, R. N.: Deep hand gesture recognition: a wavelet scattering alternative to convolutional networks, in: 2023 IEEE Statistical Signal Processing Workshop (SSP), Hanoi, Vietnam, 2–5 July 2023, 438–442, https://doi.org/10.1109/SSP53291.2023.10208011, 2023. 
Albert, S. and Linville, L.: Benchmarking current and emerging approaches to infrasound signal classification, Seismol. Res. Lett., 91, 921–929, https://doi.org/10.1785/0220190116, 2020. 
Alegria, O. C., Valtierra-Rodriguez, M., P. Amezquita-Sanchez, J., Millan-Almaraz, J. R., Rodriguez, L. M., Moctezuma, A. M., Dominguez-Gonzalez, A., and Cruz-Abeyro, J. A.: Empirical wavelet transform-based detection of anomalies in ULF geomagnetic signals associated to seismic events with a fuzzy logic-based system for automatic diagnosis, in: Wavelet Transform and Some of Its Real-World Applications, edited by: Baleanu, D., InTech, 111–124, https://doi.org/10.5772/61163, 2015. 
Download
Short summary
This study focuses on improving the monitoring of natural disasters like volcanic eruptions and earthquakes using infrasound. We developed a model called Infra-Net to better identify these events. By analyzing sound from multiple angles and combining different perspectives, our system accurately distinguishes natural hazards from human activity. This research provides a more reliable way to detect early warning signs of disasters, helping to improve global safety through more precise monitoring.
Share
Altmetrics
Final-revised paper
Preprint