Well Log Data Analytics    

Presented by Chris Dyt, Geoscience Data Analytics team, ARRC WA

Data Analytics techniques and Machine Learning are currently extremely popular in a range of fields, and petroleum exploration and production is no exception. However, their benefits and limitations are generally poorly understood by geologists.

This talk will introduce in a very non technical way the concepts behind various techniques. The disc ussion will focus on the importance of identifying the exact problem that needs to be solved,
understanding the meaning behind the data and selecting the correct method of solution.

We will provide three examples where different approaches have been applied to the interpretation
of well logs. The three different approaches range from heavily user involved techniques, completely
unsupervised classification of the logs and a mix of data analytics and expert rule based classification.
The final system will be discussed in more detail as it stresses the importance of understanding the
physics behind the problem that is being solved.

About the presenter

Chris Dyt: Chris Dyt is an applied mathematician with 20 years’ experience working in petroleum geology. Chris’ PhD in Astrophysics left him desiring to use his mathematics on a more practical application and was lucky enough to join the University of Adelaide and develop a stratigraphic forward modelling code Sedsim. In 2000 CSIRO acquired the software and Chris joined as well. In the following years Chris has been fortunate enough to work across a broad range of modelling projects and is currently working in the Geoscience Data Analytics team based at ARRC WA.

Tell your colleagues about this event with the flyer!