pyseisdl is a python package for different dictionary learning methods and their applications in seismology. DL has a variety of applications in seismology, including but not limited to seismic denoising, seismic reconstruction, seismic diffraction separation, constrained LSRTM, constrained FWI, etc.
Chen, Y. (2020). Fast dictionary learning for noise attenuation of multidimensional seismic data. Geophysical Journal International, 222(3), 1717-1727.
Wang, H., Chen, W., Zhang, Q., Liu, X., Zu, S., & Chen, Y. (2020). Fast dictionary learning for high-dimensional seismic reconstruction. IEEE Transactions on Geoscience and Remote Sensing, 59(8), 7098-7108.
BibTeX:
@article{chen2020sgk,
title={Fast dictionary learning for noise attenuation of multidimensional seismic data},
author={Yangkang Chen},
journal={Geophysical Journal International},
volume={222},
number={3},
issue={3},
pages={1717-1727},
year={2020}
}
@article{wang2021sgk,
title={Fast dictionary learning for high-dimensional seismic reconstruction},
author={Hang Wang and Wei Chen and Quan Zhang and Xingye Liu and Shaohuan Zu and Yangkang Chen},
journal={IEEE Transactions on Geoscience and Remote Sensing},
volume={59},
number={8},
issue={8},
pages={7098-7108},
doi={10.1109/TGRS.2020.3030740},
year={2021}
}
The pyseisdl developing team, 2021-present
GNU General Public License, Version 3
(http://www.gnu.org/copyleft/gpl.html)
Using the latest version
git clone https://github.com/chenyk1990/pyseisdl
cd pyseisdl
pip install -v -e .
or using Pypi
pip install pyseisdl
The "demo" directory contains all runable scripts to demonstrate different applications of pyseisdl.
The gallery figures of the pydrr package can be found at https://github.com/chenyk1990/gallery/tree/main/pyseisdl Each figure in the gallery directory corresponds to a DEMO script in the "demo" directory with the exactly the same file name.
- scipy
- numpy
- matplotlib
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, collaborations, please contact
Yangkang Chen
[email protected]