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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Seismic Phase Picking Using Synchrosqueezed Transform and Attention Mechanism


    Contributors:
    Chen, Zejie (author) / Du, Yao (author) / Liu, Qian (author)


    Publication date :

    2023-10-11


    Size :

    3916562 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Method of Human Motion Postures Analysis Using Synchrosqueezed Wavelet Transform

    Man, Weishi / Zhu, Zongyao / Zhang, Zhiyu et al. | British Library Online Contents | 2017




    Horizon picking in 3D seismic data volumes

    Faraklioti, M. / Petrou, M. | British Library Online Contents | 2004


    Order picking method and mechanism

    THEOBALD DANIEL | European Patent Office | 2018

    Free access