Infrasound Signal Classification Fusion Model Based on Double-Branch and Multi-Scale CNN and LSTM
Open Access
Abstract
The accurate classification of infrasound events is significant in natural disaster warning, verification of nuclear test bans and geophysical research. Current deep learning-based classification methods mostly focus on denoised and filtered signals. To simplify the process, avoid information loss, and address the issues of incomplete feature extraction by single-scale convolution kernels and the potential loss of physical information by single models, this paper directly utilizes raw infrasound signals and proposes two fusion classification models based on multi-scale Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). Experiments were conducted on a typical infrasound signal dataset (comprising four signal types: mountain-associated waves, auroral infrasound waves, volcanic eruptions, and microbaroms). The performances of the two models were compared in terms of accuracy, convergence speed, and stability. The results indicate that both models achieve classification accuracies exceeding 99% with optimal parameter combinations. The dual-branch multi-scale CNN-LSTM model generally outperforms the multi-scale CNN-LSTM model in classification accuracy, while also demonstrating faster convergence speed and better stability. Addressing the class imbalance in the dataset, evaluations using precision, recall, and F1-score further validated the effectiveness of the proposed models. This study demonstrates that the proposed methods can effectively achieve end-to-end classification of raw infrasound signals and are competitive with existing techniques.Keywords
This publication has 25 references indexed in Scilit:
- Infrasound Event Classification Fusion Model Based on Multiscale SE-CNN and BiLSTMApplied Geophysics, 2024
- The influence of volcano topographic changes on infrasound amplitude: lava fountains at Mt. Etna in 2021Bulletin of Volcanology, 2023
- Long range infrasound monitoring of Yasur volcanoJournal of Volcanology and Geothermal Research, 2022
- Construction and application of debris flow infrasound real-time monitoring and warning visualization platformNatural Hazards, 2022
- Infrasound From a Buried Chemical Explosion Recorded on a Balloon in the Lower StratosphereGeophysical Research Letters, 2021
- Using local infrasound arrays to detect plunging snow avalanches along the Milford Road, New Zealand (Aotearoa)Natural Hazards, 2021
- 1001 Rocket Launches for Space Missions and Their Infrasonic SignatureGeophysical Research Letters, 2021
- Infrasound signal classification based on spectral entropy and support vector machineApplied Acoustics, 2016
- A Neurocomputing Approach for Monitoring Plinian Volcanic Eruptions Using InfrasoundProcedia Computer Science, 2012
- Discrimination of infrasound events using parallel neural network classification banksNonlinear Analysis, 2005