PhaseNet: A Deep-neural Network Seismic Arrival-time Picking Method
Jun 12,2025
This paper introduces PhaseNet, a deep neural network designed for seismic arrival-time picking. PhaseNet uses three-component seismic waveforms as input and outputs probability distributions for P-wave arrivals, S-wave arrivals, and noise. Trained on a large dataset of manually labeled P and S arrival times, PhaseNet achieves higher accuracy and recall rates compared to traditional methods like STA/LTA. The model demonstrates robust performance across different instrument types and signal-to-noise ratios, and it can be applied to continuous data for earthquake detection. The study highlights PhaseNet's potential to improve earthquake monitoring and S-wave velocity modeling.
*https://doi: 10.1093/gji/ggy423
BLOG
CONTACT
Tel: 0086-0551-65327898 / 65327899
Fax: 0086-0551-65327899
E-mail: hfgwe@hfgwe.com
Add: 9th Floor, Building A, G3, Phase II, Innovation Industry Park,No. 2800 Innovation Avenue, High-tech Zone, Hefei city,Anhui Province, China
Mobile website
Hefei Guowei Electronics Co., Ltd.
Subscribe Us
We will contact you within one working day. Please pay attention to your email.
CopyRight:Hefei Guowei Electronics Co., Ltd. Powered by 300.cn SEO