• Download PhaseNet repository

git clone https://github.com/wayneweiqiang/PhaseNet.git
cd PhaseNet

• Install to default environment

conda env update -f=env.yml -n base

• Install to "phasenet" virtual envirionment

conda env create -f env.yml
conda activate phasenet

Located in directory: model/190703-214543

• Zhu, Weiqiang, and Gregory C. Beroza. "PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method." arXiv preprint arXiv:1803.03211 (2018).
• Liu, Min, et al. "Rapid characterization of the July 2019 Ridgecrest, California, earthquake sequence from raw seismic data using machine‐learning phase picker." Geophysical Research Letters 47.4 (2020): e2019GL086189.
• Park, Yongsoo, et al. "Machine‐learning‐based analysis of the Guy‐Greenbrier, Arkansas earthquakes: A tale of two sequences." Geophysical Research Letters 47.6 (2020): e2020GL087032.
• Chai, Chengping, et al. "Using a deep neural network and transfer learning to bridge scales for seismic phase picking." Geophysical Research Letters 47.16 (2020): e2020GL088651.
• Tan, Yen Joe, et al. "Machine‐Learning‐Based High‐Resolution Earthquake Catalog Reveals How Complex Fault Structures Were Activated during the 2016–2017 Central Italy Sequence." The Seismic Record 1.1 (2021): 11-19.

See details in the notebook: example_interactive.ipynb

See details in the notebook: example_batch_prediction.ipynb

Earthquake detection workflows can be found in the QuakeFlow project.

• Download a small sample dataset:

wget https://github.com/wayneweiqiang/PhaseNet/releases/download/test_data/test_data.zip
unzip test_data.zip

• Start training from the pre-trained model

python phasenet/train.py  --model_dir=model/190703-214543/ --train_dir=test_data/npz --train_list=test_data/npz.csv  --plot_figure --epochs=10 --batch_size=10

• Check results in the log folder

Please let us know of any bugs found in the code.