Attention-Based Neural Network for Onsite Peak Ground Velocity Earthquake Early Warning
Journal
Seismological Research Letters
Journal Volume
97
Journal Issue
1
Start Page
256
End Page
271
ISSN
0895-0695
1938-2057
Date Issued
2025-08-01
Author(s)
Abstract
To improve on-site earthquake early warning for peak ground velocity (PGV), we leverage a machine learning approach. We propose a novel attention-based transformer architecture to address this challenging problem. A series of comparisons with other methods, including the traditional peak P-wave displacement amplitude approach and long short-term memory neural networks, is conducted. In addition, we demonstrate that the influence of building effects can be mitigated by incorporating station corrections to peak values in the seismograms as additional features during training. Finally, we discuss how the shape of the label can serve as a proxy to indicate the reliability of PGV determination within the first few seconds after the arrival time.
Subjects
Earthquake effects
Learning systems
Long short-term memory
Personnel training
Building effects
Displacement amplitudes
Earthquake early warning
Machine learning approaches
Neural-networks
P waves
Peak ground velocity
Peak values
Short term memory
Station correction
artificial neural network
early warning system
earthquake prediction
machine learning
peak acceleration
seismic velocity
Seismic waves
Publisher
Seismological Society of America (SSA)
Type
journal article