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

2026-03-24

AI Summary

Gas chimneys are challenging to detect in seismic images due to strong attenuation and scattering, and the scarcity of high-quality annotated data has hindered the application of deep learning methods. To address this gap, this work introduces SIGMA, the first physics-driven benchmark dataset for gas chimney understanding. Leveraging seismic wave propagation simulations, SIGMA provides synthetic seismic images generated under diverse geological and acquisition conditions, accompanied by pixel-level masks for detection and paired degraded–ground-truth image pairs for enhancement. This dataset fills a critical void in labeled data for chimney interpretation, establishing a challenging benchmark that not only effectively supports gas chimney detection and analysis but also significantly improves model generalization in broader seismic image understanding tasks.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• gas chimney
• seismic image
• fluid migration
• subsurface anomaly
• hydrocarbon exploration

Innovation

• gas chimney
• physics-based dataset
• seismic image enhancement
• pixel-level annotation
• benchmark