Hybrid Physics-based Data-driven Methods – the future for Petroleum Engineering? – Technical Webinar
Data-driven methods are widely and successfully used in social sciences, an area where no discernible physics exist, but a plethora of observations exist. As a result there has been a drive to implement such approaches into our industry.
However, in petroleum engineering, reservoir characterization and flow in porous media, we are actually faced with the opposite scenario: limited observations with ambiguous interpretation (example well log or seismic data) and relatively well know physics and equations. Over the last 50 years, we have seen the establishment of physics-based approaches, with numerical simulation at the core of it.
We are seeing the emergence of hybrid approaches: data-driven but physics compliant. In this talk, we contend that these methods may provide a best-of-both worlds, and we provide two specific examples of such hybrid methods. First, we introduce a novel method for zonal production allocation, which allows for the inclusion of physics at the well (well log, relative permeabilities etc) and observations (surveillance, completion events etc). We demonstrate through project examples how this approach significantly improves production allocation, and therefore reservoir management decisions. Secondly, we discuss the integration of the published Remaining Oil Compliant Mapping algorithm with machine learning methods for the purpose of ‘locate-the-remaining-oil’ activities, and determining behind casing and infill drilling opportunities. Drilling results from recent projects are examined, and the accuracy of the method evaluated.
Mr. Babak Moradi,
Reservoir Engineer & Data Scientist at Three60 Energy Group
Babak Moradi has over 13 years of experience reservoir engineering. He has been involved in studies of more than 20 mature fields located in the Middle East, South East Asia, Australia, North Sea, and Africa. Babak is an expert in machine learning and programming, he has developed several software packages relating to petroleum engineering. He is the author of 40 scientific publications in areas of enhanced oil recovery, CO2 sequestration, fluid properties modelling, hybrid workflows, and has published a textbook on fluid flow in the wellbore. His strong background in mathematics and programming helps him to turn data into knowledge.
Click Here for LinkedIn Meet & Greet!