SIGMA: A Physics-Based Benchmark for Gas Chimney Understanding in Seismic Images
2026-03-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created SIGMA, a new dataset to help detect gas chimneys, which are features in underground images caused by fluid movements and important for oil exploration. Traditional methods to detect these are slow and error-prone, while deep learning needs good labeled data, which was lacking. SIGMA provides detailed labels and pairs of noisy and clear images to improve detection and image quality. Their experiments show that SIGMA is a useful and challenging resource for studying gas chimneys and improving seismic image analysis.
seismic imaginggas chimneyssubsurface reflectivitydeep learningpixel-level maskimage enhancementhydrocarbon explorationseismic attenuationphysics-based modelingdataset
Authors
Bao Truong, Quang Nguyen, Baoru Huang, Jinpei Han, Van Nguyen, Ngan Le, Minh-Tan Pham, Doan Huy Hien, Anh Nguyen
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.