Skip to content

Repository for paper: A Deep‐Learning‐Driven Optimization‐Based Inverse Solver for Accelerating the Marchenko Method

Notifications You must be signed in to change notification settings

DeepWave-KAUST/Inverse-solver-Marchenko-pub

Repository files navigation

Reproducible material for An Optimization-Based Inverse Solver to Accelerate the Marchenko Method - Wang N. and Alkhalifah T.

The repository is organized as follows:

1produce_data

  • Marchenko_imaging.ipynb: Calculating input and output data for NNs

--subroutine: --anglegather.py --imaging.py --marchenko.py

2preprocessing_file

  • data.ipynb: Arrange for training, validation and test data
  • create_mask.ipynb: Calculate time mask

3train_NN_pred

  • 1networking_training.py : The first stage: forward networking training
  • 2inversion.py: The second stage: inversion
  • 3arrange_data.py: Arrange for the total data
  • model.py: The architecture of the U-Net
  • train.py: Training process and validation process

4cal_downgoing

  • 1cal_for_clean_fminus_total.py: De-noising: apply band-pass filter and windowing operator
  • 2cal_for_fplus.py: Calculate f+ by using f-

5arrange_data_for_Marchenko_imaging

  • imaging.py: Carry out Marchenko imaging

data_for_this_test

  • simple_M.npz: Google drive link: https://drive.google.com/file/d/1oUvpIscPw79gwg6blVzMMv7P92tDLGwo/view?usp=drive_link

Environment

To ensure reproducibility of the results, we have provided a environment-latest.yml file. Ensure to have installed Anaconda or Miniconda on your computer.

After that simply run:

./install_env-latest.sh

It will take some time, if at the end you see the word Done! on your terminal you are ready to go!

Cite us

About

Repository for paper: A Deep‐Learning‐Driven Optimization‐Based Inverse Solver for Accelerating the Marchenko Method

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published