sede-open/synthoseis
Generating seismic data and associated labels to train deep learning networks.
This tool helps geophysicists, seismic interpreters, and exploration geologists create synthetic seismic data. It takes user-defined geological parameters (like layer thickness, faulting, and fluid fills) to generate realistic seismic surveys and corresponding subsurface labels. The output can then be used to train deep learning models that identify features of interest in actual field-acquired seismic data.
115 stars. No commits in the last 6 months.
Use this if you need large, diverse, and accurately labeled synthetic seismic datasets to train deep learning models for subsurface interpretation.
Not ideal if you need to analyze or process existing seismic data rather than generate new synthetic data.
Stars
115
Forks
33
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sede-open/synthoseis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
seisbench/seisbench
SeisBench - A toolbox for machine learning in seismology
petrobras/GeoSlicer
Open source digital rocks software platform for micro-CT, CT, thin sections and borehole image...
thilowrona/seismic_deep_learning
A couple of python scripts to interpret geological structures from geophysical images using deep learning
microsoft/seismic-deeplearning
Deep Learning for Seismic Imaging and Interpretation
RichardScottOZ/mineral-exploration-machine-learning
List of resources for mineral exploration and machine learning, generally with useful code and examples.