SIGMA: A Physics-Based Benchmark for Gas Chimney Understanding in Seismic Images

TL;DR

SIGMA is a new physics-based seismic dataset designed to improve gas chimney detection and understanding, facilitating research in seismic interpretation and enhancing general seismic analysis.

Contribution

The paper introduces SIGMA, a comprehensive physics-based dataset with labeled gas chimneys and paired images, addressing the lack of labeled data and providing a challenging benchmark for seismic interpretation.

Findings

SIGMA effectively captures diverse geological settings.

Physics-based methods perform well on the dataset.

SIGMA enhances general seismic understanding.

Abstract

Seismic images reconstruct subsurface reflectivity from field recordings, guiding exploration and reservoir monitoring. Gas chimneys are vertical anomalies caused by subsurface fluid migration. Understanding these phenomena is crucial for assessing hydrocarbon potential and avoiding drilling hazards. However, accurate detection is challenging due to strong seismic attenuation and scattering. Traditional physics-based methods are computationally expensive and sensitive to model errors, while deep learning offers efficient alternatives, yet lacks labeled datasets. In this work, we introduce \textbf{SIGMA}, a new physics-based dataset for gas chimney understanding in seismic images, featuring (i) pixel-level gas-chimney mask for detection and (ii) paired degraded and ground-truth image for enhancement. We employed physics-based methods that cover a wide range of geological settings and data acquisition conditions. Comprehensive experiments demonstrate that SIGMA serves as a challenging benchmark for gas chimney interpretation and benefits general seismic understanding.