SeisMark: A Large-Scale Open Benchmark for Robust 3D Seismic Fault Detection
Minjun Park, Joseph Stitt, Robert Clapp, Ilan Naiman, Artem Goncharuk, Kevin Smith
Abstract
We introduce SeisMark, a large-scale open benchmark designed to bridge the gap between verifiable ground truth and realistic texture in 3D seismic fault detection. Using a novel pipeline merging procedural geology with diffusion-based synthesis, we produce domain-realistic (survey-specific) textured volumes that expose significant brittleness in existing models masked by simplified physics data. Experiments demonstrate that SeisMark acts as a rigorous discriminator, distinguishing robust modern architecture from legacy model that suffers performance collapse under realistic domain shifts. We release this benchmark to the community to serve as a verifiable standard for developing trustworthy, deployment-ready AI for safety-critical subsurface applications.
BibTeX
@inproceedings{
park2026seismark,
title={SeisMark: A Large-Scale Open Benchmark for Robust 3D Seismic Fault Detection},
author={Min Jun Park and Joseph Stitt and Robert Graham Clapp and Ilan Naiman and Artem Goncharuk and Kevin F. Smith},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=trSx4NouPD}
}