StorSeismic: An approach to pre-train a neural network to store seismic data features
This repository contains codes and resources to reproduce experiments of StorSeismic in Harsuko and Alkhalifah, 2020.
Instruction
No | Notebook name | Description |
---|---|---|
1 | nb0_1_data_prep_pretrain.ipynb | Create pre-training data |
2 | nb0_2_data_prep_finetune.ipynb | Create fine-tuning data |
3 | nb1_pretraining.ipynb | Pre-training of StorSeismic |
4 | nb2_1_finetuning_denoising.ipynb | Example of fine-tuning task: denoising |
5 | nb2_2_finetuning_velpred.ipynb | Example of fine-tuning task: velocity estimation |
References
Harsuko, R., & Alkhalifah, T. (2022). StorSeismic: A new paradigm in deep learning for seismic processing. ArXiv, abs/2205.00222.
Citation
Citations are very welcomed. This work can be cited using:
@article{Harsuko2022StorSeismicAN,
title={StorSeismic: A new paradigm in deep learning for seismic processing},
author={Randy Harsuko and Tariq Alkhalifah},
journal={ArXiv},
year={2022},
volume={abs/2205.00222}
}