Common-azimuth seismic data fault analysis using residual UNet
- 19 March 2020
- journal article
- research article
- Published by Society of Exploration Geophysicists in Interpretation
- Vol. 8 (3) , SM25-SM37
Abstract
Seismic fault interpretation is one of the key steps for seismic structure interpretation, which is a time-consuming task and strongly depends on the experience of the interpreter. Aiming to automate fault interpretation, we have considered it as an image segmentation issue and adopt a solution using a residual UNet (ResUNet), which introduces residual units to UNet. Using the ResUNet model, we develop a fault-versus-azimuth analysis based on offset vector tile data, which, as common-azimuth seismic data, provide more detailed and useful information for interpreting seismic faults. To avoid manual efforts for picking training labels and the inaccuracy introduced by different interpreters, we use synthetic seismic data with a random number of faults with different locations and throws as the training and validation data sets. ResUNet is finally trained using only synthetic data and tested on field data. Field data applications show that the proposed fault-detection algorithm using ResUNet can predict seismic faults more accurately than coherence- and UNet-based approaches. Moreover, geologic fault interpretation results computed using common-azimuth data exhibit higher lateral resolution than those computed using poststack seismic data.Keywords
Funding Information
- National Science and Technology Major Project (2016ZX05024-001-007, 2017ZX05069)
- National Natural Science Foundation of China (41904102, 41604106)
- SINOPEC Key Laboratory of Geophysics
- Fundamental Research Funds for the Central Universities (xjh012019030, xjj2018260, xxj022019006)
- China Postdoctoral Science Foundation (2016M600780, 2019M653584)
- National Postdoctoral Program for Innovative Talents (BX20190279)
- National Science and Technology Major Project (2016ZX05024-001-007, 2017ZX05069)
- National Natural Science Foundation of China (41904102, 41604106)
- SINOPEC Key Laboratory of Geophysics
- Fundamental Research Funds for the Central Universities (xjh012019030, xjj2018260, xxj022019006)
- China Postdoctoral Science Foundation (2016M600780, 2019M653584)
- National Postdoctoral Program for Innovative Talents (BX20190279)
This publication has 36 references indexed in Scilit:
- Multi-attribute ant-tracking and neural network for fault detection: a case study of an Iranian oilfieldJournal of Geophysics and Engineering, 2013
- Azimuthal anisotropy in the Chile Ridge subduction region retrieved from ambient noiseLithosphere, 2011
- New fault attribute based on robust directional schemeGeophysics, 2007
- Interpreting seismic data in the presence of azimuthal anisotropy; or azimuthal anisotropy in the presence of the seismic interpretationThe Leading Edge, 2002
- Eigenstructure-based coherence computations as an aid to 3-D structural and stratigraphic mappingGeophysics, 1999
- Coherency calculations in the presence of structural dipGeophysics, 1999
- 3-D seismic attributes using a semblance-based coherency algorithmGeophysics, 1998
- 3-D seismic discontinuity for faults and stratigraphic features: The coherence cubeThe Leading Edge, 1995
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987
- Velocity spectra-digital computer derivation and applications of velocity functionsGeophysics, 1969