De Groot-Bril’s (dGB) ChimneyCube technique uses neural network technology to detect gas-charged sediment over a reservoir. Claimed as commercial ‘first’ the service exclusively offered by dGB uses a seismic object detection method jointly developed by dGB and Statoil. A worldwide patent has been applied for and dGB believes the method has the potential to become the ‘next generation’ seismic interpretation system.
Work performed on 3D seismic data cubes for drilling hazard detection led to the realization that high-amplitude reflections, pockmarks, mud-volcanoes and other geological features were connected in space via hydrocarbon migration paths - seismic ‘chimneys’. Statoil workers realized that emerging neural-net techniques could be applied to automatic locating of such anomalies.
Initial results obtained with a ‘supervised Multi-Layer-Perceptron’ classification network were described as ‘stunning’. Migration paths could be followed down to the source, distinguishing charged and dry structures.
Click here to comment on this article © Oil IT Journal - all rights reserved.
If your browser does not work with the MailTo button, send mail to firstname.lastname@example.org with PDM_V_3.3_9910_17 as the subject.
© Oil IT Journal - all rights reserved.