LoSAR

Construction of Long-Term Seismic Catalog with Deep Learning: A Workflow for Localized Self-Attention RNN (LoSAR)

Usage

1. Train SAR model

1.1 run PAL to generate local training samples
1.2 cut event windows & generate Zarr database

python 1_cut_train-samples.py
python 2_sac2zarr.py

1.3 train SAR model

python 3_train.py

2. Apply LoSAR on continuous data & associate picks

2.1 run LoSAR

python 4_pick_stream.py

2.2 associate picks with PAL associator

python 5_parallel_assoc.py

3. Locate and Relocate LoSAR detections

3.1 HypoINV absolute location
3.2 HypoDD double-difference relocation
3.2.1 two-step relocation: dt.ct and dt.cc
3.2.2 one-step relocation: dt.ct + dt.cc joint inversion

Reference

• Zhou, Y., H. Yue, Q. Kong, & S. Zhou (2019). Hybrid Event Detection and Phase‐Picking Algorithm Using Convolutional and Recurrent Neural Networks. Seismological Research Letters; 90 (3): 1079–1087. doi: 10.1785/0220180319
• Zhou, Y., H. Yue, L. Fang, S. Zhou, L. Zhao, & A. Ghosh (2021). An Earthquake Detection and Location Architecture for Continuous Seismograms: Phase Picking, Association, Location, and Matched Filter (PALM). Seismological Research Letters; 93(1): 413–425. doi: 10.1785/0220210111
• Zhou, Y., A. Ghosh, L. Fang, H. Yue, S. Zhou, & Y. Su (2021). A High-Resolution Seismic Catalog for the 2021 MS6.4/Mw6.1 YangBi Earthquake Sequence, Yunnan, China: Application of AI picker and Matched Filter. Earthquake Science; 34(5): 390-398.doi: 10.29382/eqs-2021-0031