Home

Quick Links

Search

 
Semi-Supervised DeepMachine Learning Assisted Seismic Image Segmentation and Stratigraphic Sequence InterpretationNormal access

Authors: Z. Li, H. Di, H. Maniar and A. Abubakar
Event name: 81st EAGE Conference and Exhibition 2019
Session: Poster: AI/Digitalization for Interpretation - Various Application
Publication date: 03 June 2019
DOI: 10.3997/2214-4609.201901389
Organisations: EAGE
Language: English
Info: Extended abstract, PDF ( 668.78Kb )
Price: € 20

Summary:
Geological / geophysical interpretation of seismic survey commonly requires segmenting a seismic image into different layers/sequences, highlighting certain geobodies, or picking different horizon surfaces, for multiple purposes including, but not limited to, earth model building, velocity model building, stratigraphic analysis, etc. The traditional approach requires the interpreter significant amount of effort to interact with computer and label the data. We demonstrated an innovative workflow for seismic image/sequence/geobody segmentation and horizon picking, where a key aspect is that, it requires much less labels and hence significantly reduce interpreter’s workload.


Back to the article list