QRI Expert Hour -- Efficient Management of Mature Waterfloods Using a Physics-Based, Data-Driven Approach

Recorded On: 11/14/2018


Experts present a powerful new solution that combines the fundamentals of subsurface flow physics with advanced data-driven techniques to quickly build waterflood models based on available geologic, completion and production data. Compared to conventional full-physics model generation workflows for large fields with multiple decades of production history, this new technology’s models are typically built in short time frames, ready for full-field surveillance and optimization. The cloud-based feature provides a flexible platform capable of guiding daily production operations through fast production forecasts and optimization of both existing wells and new drills. The workflow delivers low capital, high impact, short-term recommendations for improved waterflood performance. This directly translates to substantial improvement in capital efficiency and OPEX reduction in mature waterfloods.

Dr. Xiang Zhai

Sr. Data Analyst, Quantum Technologies

Dr. Zhai has a broad range of experience in applied mathematics and physics, including machine learning, data mining, deep learning, artificial intelligence, theoretical and numerical PDEs and ODEs, numerical simulation, and optimization. He has used these tools to quantitatively model and interpret complex petroleum engineering problems and other large-scale dynamic systems. A PhD graduate from Caltech, Dr. Zhai was quickly promoted at QRI to the leader of New Technologies group, a multi-disciplinary R&D group exploring many cutting-edge technologies for the oil and gas industry. Dr. Zhai led the development effort of several major QRI technologies, including SpeedWise® Waterflood Management, a robust waterflood optimization software that combines critical physics with data-driven models. Dr. Zhai also developed SpeedWise Unconventionals®, a technology that uses public and private data to identify opportunities in the unconventional fields, including well spacing optimization, target identification, well performance prediction, and drilling and completion design optimization.  Dr. Zhai is also in charge of QRI's Automated Machine Learning toolbox development, a tool that aims to conduct intelligent, robust and enterprise-level machine learning and data analytics in a fully automated fashion. Dr. Zhai and his team’s technologies have been applied across the world, including the Middle East, East Asian, Mid Asian, North America, and Latin America.

Dr. Feyisayo Olalotiti

Analyst, Quantum Technologies

Dr. Olalotiti has extensive experience in the oil and gas industry as an engineer, an educator, and in research. A PhD graduate from Texas A&M University, Dr. Olalotiti helped design and develop the SpeedWise® Waterflood Management (SWM®) suite for QRI. Previously with PetraNova, he worked on the world’s largest anthropogenic CO2 EOR and storage project. While pursuing his graduate degrees at Texas A&M University, he worked as a teaching assistant for numerous engineering courses. During this time, he was also a Research Assistant on the Model Calibration and Efficient Reservoir Imaging (MCERI) project.  He also held internships with Chevron, where he worked on the RESQML–INTERSECT simulation workflow development, and with Schlumberger, where he developed an efficient unconventional reservoir evaluation engine. Dr. Olalotiti has been honored with several prestigious awards, including the Chevron Fellowship award, the Graduate Fellowship award from the Department of Petroleum Engineering at Texas A&M University, and the ExxonMobil Undergraduate Scholarship award.


Content for this webinar is provided by QRI. By registering, your contact information will be shared with the sponsor.


11/14/2018 at 10:00 AM (EST)   |  60 minutes
11/14/2018 at 10:00 AM (EST)   |  60 minutes
20 Questions