Deep Diffusion Models for Seismic Processing
PyTorch implementation of Deep Diffusion Models for Seismic Processing.
Overview
Seismic data processing involves techniques to deal with undesired effects that occur during acquisition and pre-processing. These effects mainly comprise coherent artefacts such as multiples, non-coherent signals such as electrical noise, and loss of signal information at the receivers that leads to incomplete traces. In this work, we introduce diffusion models for three seismic applications: demultiple, denoising and interpolation.
Testing Code on Demultiples
Download Pretrained Model (model_test.pt). Run inference on:
visualization.ipynb
Training Code
Before starting the training you should specify in the run.py: the mode, the dataset folder and the image size. Then:
python run.py
Note that you might need to installl thrid party libraries.
Acknowledgement
We acknowledge the code from lucidrains & Janspiry