EQpolarity package is a deep-learning-based package for determining earthquake first-motion polarity
Chen Y, Saad OM, Savvaidis A, Zhang F, Chen Y, Huang D, Li H, Zanjani FA, 2024, Deep learning for P-wave first-motion polarity determination and its application in focal mechanism inversion. IEEE Transactions on Geoscience and Remote Sensing, 62, 5917411.
BibTeX:
@article{eqpolarity,
title={Deep learning for P-wave first-motion polarity determination and its application in focal mechanism inversion},
author={Yangkang Chen and Omar M. Saad and Alexandros Savvaidis and Fangxue Zhang and Yunfeng Chen and Dino Huang and Huijian Li and Farzaneh Aziz Zanjani},
journal={IEEE Transactions on Geoscience and Remote Sensing},
year={2024},
volume={62},
number={1},
pages={5917411},
doi={10.1109/TGRS.2024.3407060}
}
Developers of the EQpolarity package, 2021-present
MIT License
First set up the environment and install the dependency packages (tested on CPU machine)
conda create -n eqp python=3.11.7
conda activate eqp
conda install ipython notebook
pip install matplotlib==3.8.0 tensorflow==2.14.0 scikit-learn==1.2.2 seaborn==0.13.2
Or, on machine with a GPU setup, use the following commands
conda create -n eqp python=3.10.14
conda activate eqp
conda install ipython notebook
pip install matplotlib==3.8.0 tensorflow==2.11.0 scikit-learn==1.2.2 seaborn==0.13.2
conda install -c anaconda cudnn==8.2.1
Make sure LD_LIBRARY_PATH includes ~/anaconda3/envs/eqp/lib (libcudnn.so.8)
Then install eqpolarity using the latest version
git clone https://github.com/chenyk1990/eqpolarity
cd eqpolarity
pip install -v -e .
Or using Pypi
pip install eqpolarity
Or using pip directly from Github
pip install git+https://github.com/chenyk1990/eqpolarity
https://github.com/chenyk1990/eqpolarity/tree/main/data/TexasData
The development team welcomes voluntary contributions from any open-source enthusiast.
If you want to make contribution to this project, feel free to contact the development team.
Regarding any questions, bugs, developments, or collaborations, please contact
Yangkang Chen
chenyk2016@gmail.com
The gallery figures of the eqpolarity package can be found at https://github.com/chenyk1990/gallery/tree/main/eqpolarity
Each figure in the gallery directory corresponds to a DEMO script in the "demo" directory. These gallery figures are also presented below.
DEMO1 The following figures show an example confusion matrix comparison before/after transfer learning. Generated by demos/test_texas_transferlearning.py
DEMO2 The following figures show an example of plotting waveforms and polarity labels for the Texas dataset. Generated by demos/test_plot_waveforms_and_polarity.py
