Lunchbox Geophysics

SAGD dynamic reservoir property characterization using machine learning

Luis E. Cardozo

Luis E. Cardozo
Lead Geophysicist, ConocoPhillips Canada

Wednesday, September 4th, 2019 – 12:00 PM MST
Chevron Canada, Athabasca Room, 2nd Floor, 500 5 Ave SW, Calgary

To attend, please RSVP to
Unless we have exceeded the allowable number of people for the auditorium, we will not be replying to your email.
LunchBox Geophysics is free! Simply bring your own lunch (refreshments provided) and enjoy.


Machine learning applications have drawn much attention across different industries and more recently for seismic reservoir characterization applications. In this presentation, a workflow for estimation of dynamic time-lapse temperature changes (∆T) in a reservoir from seismic using supervised machine learning methods have been proposed to characterize steam assisted gravity drainage (SAGD) recovery processes. The workflow utilizes time lapse (4D) pre-and post-stack seismic data from multiple seismic surveys and additional auxiliary data such as from observation wells, static & dynamic models, and production data. Results were validated with time-lapse thermocouples from the observation wells and demonstrate the feasibility of using machine learning methods for 4D reservoir property change predictions


Luis Cardozo

Lead Geophysics – ConocoPhillips Canada

B.S. in Geology with Honors, MS in Geophysics

With more than 20 years in the Oil Industry, I begun my career with PetroBras in the Venezuelan Heavy Oil Fields. In the early 2000’s I worked for Pemex in the Gulf of Mexico. Since 2006 I been working with ConocoPhillips in Oil Sands mainly focus in 4D.