Data

Tools

Indexes

Applications

Experiments

Open Source Science

gcs-cam

Derisking geological carbon storage from high-resolution time-lapse seismic to explainable leakage detection

https://github.com/slimgroup/gcs-cam

Science Score: 41.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 6 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org, zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (15.1%) to scientific vocabulary

Keywords

classifier deep-learning geological-carbon-storage seismic-imaging time-lapse
Last synced: 6 months ago · JSON representation ·

Repository

Derisking geological carbon storage from high-resolution time-lapse seismic to explainable leakage detection

Basic Info
Statistics
  • Stars: 9
  • Watchers: 3
  • Forks: 1
  • Open Issues: 0
  • Releases: 2
Topics
classifier deep-learning geological-carbon-storage seismic-imaging time-lapse
Created over 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.md

Derisking geological carbon storage from high-resolution time-lapse seismic to explainable leakage detection

Code to reproduce results in Ziyi Yin, Huseyin Tuna Erdinc, Abhinav Prakash Gahlot, Mathias Louboutin, Felix J. Herrmann, "Derisking geological carbon storage from high-resolution time-lapse seismic to explainable leakage detection". In The Leading Edge in January 2023. DOI: 10.1190/tle42010069.1

Installation

First, install Julia, Python and MiniConda. Next, run the command below to install the required packages.

bash julia -e 'Pkg.add("DrWatson.jl")' julia --project -e 'using Pkg; Pkg.instantiate()' conda env create -f environment.yml source activate gcs-cam python -m ipykernel install --user --name gcs-cam --display-name "Python (gcs-cam)"

Script descriptions

We use the open-source software JUDI.jl for seismic modeling and imaging, which calls the highly optimized propagators of Devito. We used FwiFlow.jl to solve the two-phase flow equations for both the pressure and concentration. The CO2 plume dataset (consisting of regular plumes and leaking plumes) will be downloaded upon running your first example. We used PyTorch library for CAM methods to calculate the CAM images. We thank the authors of these packages for their contributions to the open-source software community.

time-lapse seismic modeling and imaging

GenLinData.jl: script to generate time-lapse linearized data via Born modeling operators.

RTM.jl: script to run reverse-time migration (RTM) on the linearized data.

JRM.jl: script to invert the time-lapse linearized data via joint recovery model (JRM).

The experimental setup (number of sources, receivers, amount of noise etc) can be adjusted according to input keywords.

To generate a dataset for training the deep neural classifier, we provide the clusterless version of the above 3 scripts --- where you can simply run the julia scripts locally and experiments can run on multiple instances in parallel on the cloud. This needs 3 files for registry, credential, and parameter information to be stored in registryinfo.json, credentials.json, params.json files. More information can be found in AzureClusterlessHPC.jl and JUDI4Cloud.jl.

leakage detection with deep neural classifier and class activation mapping

To train the deep neural classifier for leakage detection, open main.ipynb notebook and choose gcs-cam environment as the kernel. It internally uses train.py and test.py modules for training and testing. The notebook contains useful comments for each section.

LICENSE

The software used in this repository can be modified and redistributed according to MIT license.

Disclosure

Some comments in the scripts are generated by ChatGPT 4.

Reference

If you use our software for your research, we appreciate it if you cite us following the bibtex in CITATION.bib.

Authors

This repository is written by Ziyi Yin, Huseyin Tuna Erdinc, Abhinav Prakash Gahlot from the Seismic Laboratory for Imaging and Modeling (SLIM) at the Georgia Institute of Technology.

If you have any question, we welcome your contributions to our software by opening issue or pull request.

SLIM Group @ Georgia Institute of Technology, https://slim.gatech.edu.
SLIM public GitHub account, https://github.com/slimgroup.

Owner

  • Name: SLIM GROUP
  • Login: slimgroup
  • Kind: organization
  • Email: Felix.herrmann@gatech.edu
  • Location: Georgia Institute of Technology, USA

Repositories for software by SLIM group

Citation (CITATION.bib) 

@ARTICLE{yin2022TLEdgc,
  author = {Ziyi Yin and Huseyin Tuna Erdinc and Abhinav Prakash Gahlot and Mathias Louboutin and Felix J. Herrmann},
  title = {Derisking geologic carbon storage from high-resolution time-lapse seismic to explainable leakage detection},
  journal = {The Leading Edge},
  year = {2023},
  month = {01},
  volume = {42},
  number = {1},
  pages = {69–76},
  abstract = {Geological carbon storage represents one of the few truly scalable technologies capable of reducing the {CO$_2$} concentration in the atmosphere. While this technology has the potential to scale, its success hinges on our ability to mitigate its risks. An important aspect of risk mitigation concerns assurances that the injected {CO$_2$} remains within the storage complex. Amongst the different monitoring modalities, seismic imaging stands out with its ability to attain high resolution and high fidelity images. However, these superior features come, unfortunately, at prohibitive costs and time-intensive efforts potentially rendering extensive seismic monitoring undesirable. To overcome this shortcoming, we present a methodology where time-lapse images are created by inverting non-replicated time-lapse monitoring data jointly. By no longer insisting on replication of the surveys to obtain high fidelity time-lapse images and differences, extreme costs and time-consuming labor are averted. To demonstrate our approach, hundreds of noisy time-lapse seismic datasets are simulated that contain imprints of regular {CO$_2$} plumes and irregular plumes that leak. These time-lapse datasets are subsequently inverted to produce time-lapse difference images used to train a deep neural classifier. The testing results show that the classifier is capable of detecting {CO$_2$} leakage automatically on unseen data and with a reasonable accuracy.},
  keywords = {Seismic Imaging, JRM, CCS, classification, CAM, explainability, time-lapse, resolution},
  doi = {10.1190/tle42010069.1},
  note = {(The Leading Edge)},
  software = {https://github.com/slimgroup/GCS-CAM},
  url = {https://slim.gatech.edu/Publications/Public/Journals/TheLeadingEdge/2022/yin2022TLEdgc/paper.html}
}

GitHub Events

Total
  • Watch event: 3
Last Year
  • Watch event: 3

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: 22 minutes
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 3
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • ziyiyin97 (3)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

environment.yml pypi
  • grad-cam ==1.4.6
  • opencv-python ==4.6.0.66
  • pyqt5-sip ==12.11.0
  • pyyaml ==6.0
  • ttach ==0.0.3