We developed a method using synchrosqueezed transforms (SST) and convolutional neural networks (CNN) to recognize seismic phases from earthquake waveforms. The attention mechanism has added within the CNN to improve the accuracy of seismic phase picking. This approach transforms the 1D seismic signals into a 2D time-frequency representation using a synchrosqueezed transform (SST). We use Stanford Earthquake Dataset (STEAD) to train the proposed method.
Seismic Phase Picking Using Synchrosqueezed Transform and Attention Mechanism
11.10.2023
3916562 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A Method of Human Motion Postures Analysis Using Synchrosqueezed Wavelet Transform
British Library Online Contents | 2017
|Horizon picking in 3D seismic data volumes
British Library Online Contents | 2004
|