Reservoir: Data-Driven and Reduced Order Models in Reservoir Simulation

Speaker: Hector Klie
Speaker Hector Klie
Dr. Hector Klie holds the position of Staff Reservoir Engineer at Reservoir Performance Analysis, Geosciences & Reservoir Engineering Technology, at ConocoPhillips Company. He currently leads technical initiatives to develop data mining and surrogate modeling solutions for modeling, uncertainty quantification, forecasting and optimal control of reservoir assets and drilling operations. Dr. ...

Dr. Hector Klie holds the position of Staff Reservoir Engineer at Reservoir Performance Analysis, Geosciences & Reservoir Engineering Technology, at ConocoPhillips Company. He currently leads technical initiatives to develop data mining and surrogate modeling solutions for modeling, uncertainty quantification, forecasting and optimal control of reservoir assets and drilling operations. Dr. Klie completed a Ph.D. in Computational Science and Engineering at the Department. of Computational and Applied Mathematics at Rice University in 1996 and a Master’s Degree in Computer Science at the Simon Bolivar University, Venezuela, 1991. Before joining ConocoPhillips in March of 2008, Dr. Klie was Associate Director and Senior Research Associate at the Center for Subsurface Modeling in The University of Texas at Austin. He also spent 14 years working for PDVSA-Intevep, the research and technological branch of the Venezuelan oil industry. His current interest aims at the development of efficient simulation, history matching, optimization, control and reservoir management workflows for unconventional resources based on data mining, machine learning, surrogate modeling and high performance computing technologies.

Full Description

Real-time reservoir management, optimization and uncertainty assessment requires an effective assimilation of all available data into multiple reservoir models to be able to generate accurate forecasts and ultimately, fast and reliable decisions.  As more data becomes available, more ambitious reservoir simulation problems can be addressed and innovative opportunities for understanding the reservoir behavior are now at our disposal. In particular, the extraction of knowledge and physical insights from vast amounts of data is providing powerful mechanisms to tailor the generation of non-intrusive reduced order models and specialized analytics to capture solution trends that may not be otherwise amenable to assimilate into current complex simulation systems. This presentation will provide a panoramic view of a few promising advances that have been taking place in data mining and machine learning to enable the development of non-intrusive data-driven surrogate models. Provided that there is a representative set of training reservoir scenarios, input parameters, and outputs can be projected into a much lower dimension that retains the main features contained in the simulation system. Once the complexity of the simulation is reduced, predictions can be efficiently carried out with the aid of neural or kernel models. Cases will be shown to illustrate the enormous potentials that this class of data-driven surrogate models offer to tackle current and forthcoming reservoir engineering challenges within the Oil& Gas business.  

Organizer Miles Palke

When?

Thu, May. 22, 2014
11:30 a.m. - 1 p.m. America/Chicago

How Much?

A $5 donation for the SPE-GCS Scholarship Fund has automatically been added to the registration fee. Use OptOut in the Discount Code field if you do not wish to donate at this time.
Event has ended

Where?

Sullivan’s Steakhouse
4608 Westheimer Rd
Houston, TX 77027
United States

Refund Policy: You must notify the SPE-GCS office of your intent to cancel at least 24 hours prior to the event date to receive a refund. For all refund inquiries, email spe-gcs@spe.org. View our Terms & Conditions for more information.