Reproducible material for Velocity model building with uncertainty quantification using a multi-modal autoregressive generative network - Harsuko R., Cheng S., Alkhalifah T.

Project structure

This repository is organized as follows:

• 📂 velocitygpt: python library containing routines for VelocityGPT;
• 📂 asset: folder containing logo;
• 📂 data: folder reserved for data;
• 📂 results: folder reserved for storing results;
• 📂 notebooks: set of jupyter notebooks reproducing the experiments in the paper (see below for more details);

Supplementary files

Data for the experiments can be made available upon a reasonable request by sending an email to the main author (mochammad.randycaesario@kaust.edu.sa).

Scripts

The following notebooks are provided:

• 📝 scripts/run_fsq_vel_training.sh: notebook performing training of the FSQ for the velocities;
• 📝 scripts/run_fsq_refl_training.sh: notebook performing training of the FSQ for the reflectivity images;
• 📝 scripts/run_gpt_training.sh: notebook performing training of the GPT;

Getting started 👾 🤖

To ensure reproducibility of the results, we suggest using the environment.yml file when creating an environment.

Simply run:

./install_env.sh

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

Remember to always activate the environment by typing:

conda activate velocitygpt

Disclaimer: All experiments have been carried on a Intel(R) Xeon(R) Platinum 8176 CPU @ 2.10GHz equipped with a single NVIDIA Quadro RTX 8000 GPU. Different environment configurations may be required for different combinations of workstation and GPU.

Cite us