README.md

Demo code for:

Interpretable unsupervised learning framework for multi-dimensional erratic and random noise attenuation

Description

MANet is an unsupervised-learning-based deep learning framework for 2D and 3D seismic random and erratic noise attenuation. This paper visualizes outputs and weights at different levels to study the interpretability of the network denoising process.

---

Reference

If you find this package useful, please do not forget to cite the following paper.

Yang, L., Fomel, S., Wang, S., Chen, X., Sun, Y., and Chen, Y. (2024). Interpretable unsupervised learning framework for multi-dimensional erratic and random noise attenuation, IEEE TGRS, In press.

BibTeX:

@article{YangDe2024,
  title={Interpretable unsupervised learning framework for multi-dimensional erratic and random noise attenuation},
  author={Liuqing Yang and Sergey Fomel and Shoudong Wang and Xiaohong Chen and Yaoguang Sun and Yangkang Chen},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  year={2024},
  pages={in press},
}

---

License

GNU General Public License, Version 3
(http://www.gnu.org/copyleft/gpl.html)  

---

Dependence Packages

• Tensforflow-gpu: 1.9.0
• numpy: 1.15.4
• Keras: 2.2.5
• GPU: GeForce RTX 1050 Ti

---

Contact

If you have any suggestions or questions, please contact me:
Liuqing Yang 
yangliuqingqin@163.com