The CREWES Data Science Initiative will host, on June 24th, at 5:30pm (MT), the last webinar of a series of four focused on applied machine learning to seismic inversion. This is the final presentation linked to the Geophysics in the Cloud competition.

Geophysics in the Cloud was a competition with the goal to perform seismic inversion of rock attributes from seismic data with the use of well logs. It used open data (3D Poseidon from Australia) and the competitors needed to perform inversions for P-Impedance, S-Impedance, and Density. Well logs with DTC, DTS and RHOB are used for training and evaluation (two blin wells). After the data analysis, pre-processing, and feature engineering (presented during labs 15 and 16), now comes the modelling part. There are a large number of solutions to choose from. Using long-short term memory (LSTM) algorithms proved to be a fine solution for the problem, as this type of model considers neighbours points to predict the impedances and density of the current depth.

Shang Huang is an MSc student at CREWES (University of Calgary) under the supervision of Dr. Daniel Trad. Paulina Woźniakowska is a Ph.D. candidate at the University of Calgary under the supervision of Dr. David Eaton and she is part of the Microseismic Industry Consortium also at the University of Calgary. Both Shang and Paulina are machine learning specialists and are presenting their solutions using a combination of LSTM and CNN models for the competition modelling.

Shang Huang's LinkedIn: [ Ссылка ]
Paulina Woźniakowska's LinkedIn: [ Ссылка ]

To learn more, visit our website:
[ Ссылка ]...

Follow us on Twitter: [ Ссылка ]
Follow us on LinkedIn: [ Ссылка ]

Stay tuned for the next events at our MeetUp group: [ Ссылка ]

свернуть