Data Imputation of Well Logs using Regression Models - Geophysics in the Cloud Competition

Luping Qu, Marcelo Guarido, Daniel O. Trad, David J. Emery

The CREWES Data Science Initiative presents the first lab of a series of four, focused on the solutions for seismic inversion using machine learning. 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 blind wells). However, the provided logs contain a large amount of missing data.

Luping Qu is a PhD student at CREWES and she took part in the competition. She will present her solution, in Matlab, on how to use other logs (such as gamma-ray) combined with regression models to predict and 'recover' the missing DTC, DTS, and RHOB to train the inversion machine learning model. Luping will do a hands-on demonstration during the learning lab and will use the same dataset provided in the competition.