Uncertainty in Automated Well Log Correlation Using Stochastic Dynamic Time Warping
Paper Ref: SPWLA-2022-0071 (click for full abstract)
Author: Mustafa A. Al Ibrahim, EXPEC Advanced Research Center, Saudi Aramco
Speaker: Mustafa A. Al Ibrahim
Presenter Bio: Mustafa A. Al Ibrahim is a research geoscientist at the EXPEC Advanced Research Center, Saudi Aramco. He has a background in Energy Engineering (Stanford University), Geology (Colorado School of Mines, University of Calgary), and Geophysics (University of Calgary). His work focuses on the development of new technologies for quantitative geologic analysis with focus on algorithm and software development. His current work focuses on the development of machine learning algorithms focused on the automated analysis of geologic data.
Abstract:
Well log correlation is used extensively to generate subsurface cross-sections from the sparse well data. This is commonly done by a subject matter expert such as stratigraphers and exploration geophysicists. Several methodologies exist for automating the procedure with varying success. Dynamic time warping (DTW) is a signal processing technique where one signal is locally stretched and squeezed to maximize similarity between a reference second signal. This is done by calculating a similarity cost matrix that is traversed to minimize the cumulative distance. The technique produces reasonable results when applied to the well correlation problem. The produced correlation, however, is deterministic, and thus, it does not allow for studying the associated uncertainty. This study presents an extension of the traditional dynamic time warping to allow the generation of multiple realizations of correlations. To accomplish this, the cost matrix is traversed deterministically or probabilistically based on a local correlation metric, e.g., the local correlation coefficient. The resultant realizations show stability in the correlation markers where the signals are similar and instability where they are not. The methodology is applied on two adjacent wells. Multiple well log types (gamma ray, sonic, and resistivity) are used to construct the similarity cost matrix between the two wells. The cost matrix is traversed multiple times to produce multiple realizations. The produced realizations are geologically acceptable. By generating large number of realizations, the uncertainty in the solutions is quantified. While the application presented here relates to well log correlation, the presented stochastic dynamic time warping methodology can be applied on other types of signals and data such as seismic, chemostratigraphy data, and realtime drilling measurements
(Houston --->Saudi Arabia Time)
There are two identical sessions:
Wednesday, April 19th Early Morning Session: Houston (CST) 1am – 2am ===> Morning Session: Saudi Arabia (GMT+3) 9:00am-10:00am
Wednesday, April 19th Morning Session: Houston (CST) 8am – 9am ===> Afternoon Session: Saudi Arabia (GMT+3) 4:00pm-5:00pm
REGISTRATION FEE: FREE to current members and Non-Members are $25.00
PRE-REGISTRATION REQUIRED
How to Register:
-> Log In -> Click on the "Register Myself" tab -> Add this event to your cart -> Check out (complete payment) -> Find a receipt in your email inbox for your records
Almost there - a few additional steps to complete your registration
-> Locate an email from webinar_registration in you inbox
-> Follow the instructions in the email to complete your registration in GoToWebinar which will generate a unique link and add the event to your calendar
-> You must have a link to access this class, without the link you will not be able to join
-> Being proactive will allow you easy access