Reproducible material for Guided Diffusion Posterior Sampling for Elastic Parameter Inversion with Angle-Stack Seismic Data - Dixit A., Brandolin F., Alkhalifah T.

Project structure

This repository is organized as follows:

• 📂 diffavoinv: python library containing routines for DPS based AVO Inversion and editing;
• 📂 asset: folder containing logo;
• 📂 data: folder containing test data of 2D Otway synthetic data and Poseidon Field angle-stack seismic (note: right now contains only the test data, no trained weight and/or datasets, because of GitHub memory issues)
• 📂 notebooks: set of jupyter notebooks reproducing the experiments in the paper (see below for more details);
• 📂 scripts: set of python scripts used to run multiple experiments ...

Notebooks

The following notebooks are provided:

• 📙 AVOUQ_synth_otway.ipynb: notebook performing uncertaninty quantification on synthetic otway model;
• 📙 avo_inversion_guided_ddim.ipynb: notebook performing DPS based AVO Inversion and editing;
• 📙 dataset_avo.ipynb: notebook performing training data and unconditional samples visulization;
• 📙 field_avo_inversion_guided_ddim_UQ.ipynb: notebook performing DPS based avo inversion on field data and uncertanity quantification;

Note: to run the notebook, please download the trained model weights from the checkpoints folder

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 diffseisavo

After that you can simply install your package:

pip install .

or in developer mode

pip install -e .

Disclaimer: All experiments have been carried on a Intel(R) Xeon(R) CPU @ 2.10GHz equipped with a single NVIDIA GEForce RTX 3090 GPU. Different environment configurations may be required for different combinations of workstation and GPU.

Cite us

DW0127 - Dixit A., Brandolin F., Alkhalifah T. (2026) Guided Diffusion Posterior Sampling for Elastic Parameter Inversion with Angle-Stack Seismic Data.