Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning
Дискриминация сейсмических волн с помощью машинного обучения: применение для раннего предупреждения о землетрясениях
2018-05-11
SCID: 54.1/hmp8th52
Discuss with AI
Earthquake early warningGenerative adversarial networkP-wave detectionRandom Forest classifierSeismic wave discrimination
Figures from the paper
Abstract (AI)
Abstract Performance of earthquake early warning systems suffers from false alerts caused by local impulsive noise from natural or anthropogenic sources. To mitigate this problem, we train a generative adversarial network (GAN) to learn the characteristics of first‐arrival earthquake P waves, using 300,000 waveforms recorded in southern California and Japan. We apply the GAN critic as an automatic feature extractor and train a Random Forest classifier with about 700,000 earthquake and noise waveforms. We show that the discriminator can recognize 99.2% of the earthquake P waves and 98.4% of the noise signals. This state‐of‐the‐art performance is expected to reduce significantly the number of false triggers from local impulsive noise. Our study demonstrates that GANs can discover a compact and effective representation of seismic waves, which has the potential for wide applications in seismology.
Key Findings
1
A GAN was trained on 300,000 seismic waveforms from southern California and Japan to learn characteristics of first-arrival earthquake P waves.
2
The GAN discriminator was used as an automatic feature extractor, combined with a Random Forest classifier trained on approximately 700,000 earthquake and noise waveforms.
3
The approach achieved state-of-the-art discrimination performance and is expected to substantially reduce false earthquake early-warning triggers caused by local impulsive noise.
4
The resulting system recognized 99.2% of earthquake P waves and 98.4% of noise signals.
5
The study demonstrates that GANs can learn compact, effective seismic-wave representations with potential applications across seismology.
Research Object
First-arrival earthquake P waves and local impulsive noise signals recorded in southern California and Japan
Research Subject
Discrimination and recognition performance between earthquake P waves and noise signals for reducing false alerts in earthquake early warning systems
Publication Details
Publication Date
2018-05-11
Journal
Publisher
ISSN
Cited by
305
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest