SPE Online Education
Hybrid Digital Twin: The Challenges in Combining Data-Driven and Physics-based Modeling for Digital Twin Creation
While the aviation, aerospace, and renewable energy industries have experienced enormous benefits over the past decade, the adoption of data-driven and/or physics-based reduced-order models as a digital twin is still in its infancy in the oil and gas (O&G) industry.
Benefits captured across these other industries include: improved quality and speed of decision-making, greater asset utilization, condition-based monitoring and prognostication, enhanced operational-efficiency and improvements in preventive maintenance. However, many challenges exist in our industry with respect to the generation and adoption of data science principles for the creation of a digital twin.
We tend to rely more on physics-based models. Moreover, key gaps exist in the understanding of basic principles concerning how and when to use different data-analytics tools to create a virtual representation from data, and then combining it with trusted physic-based modeling; thereby, allowing the assimilation of data-driven models into physics-based models.
Advances in hardware and software technologies have enabled the development of the information and computational infrastructure, which in turn gives industries the opportunity to explore and take advantage of the exciting possibilities for digital twins to analyze physical assets efficiently and effectively. The challenge of creating these entities, either through physics-based methods, data-driven modelling or combining them to form a “hybrid digital twin,” is of real interest to both academic and industry research and is the main motivation for this webinar.
Dr. Egidio (Ed) Marotta
Chief Advisor, Landmark
Dr. Marotta presently holds the position of Chief Advisor – Digital Twin & Optimization for Landmark, a division of Halliburton. Also, Ed has held faculty positions as an Assistant Professor at Clemson University (1997) and Associate Teaching & Research Professor at Texas A&M (2003), all within the Mechanical Engineer Department.
A Chief Advisor at Landmark with over 25 years of academic and industry experience in the development of physics-based models, and now data-driven models, with the end goal of analyzing systems with a Systems Engineering philosophy. Ed is experienced in helping customers realize value from modeling and simulation, analysis led design, and the incorporation of digital twins for asset health monitoring and prognostication.
Most recently, he held the position of the Systems Analysis, Analytics & Modeling Manager. Ed worked across multiple Product Lines to develop best practices and synergies to assemble models and conduct validation testing on key technologies as they are inserted into larger, multi-disciplinary, "System of Systems" (SoS) platforms. In addition, Ed has held the position as Technical Manager for the Multi-Physics Simulation Group within the North America Technology Center, FMC Technologies Inc. In the latter group, he was responsible for developing a Center of Excellence for modeling and simulation of multi-physics phenomena for Surface and Subsea applications.
Ed has published over 100 Journal, Conference, and Magazine papers/articles within the areas of Thermo-Fluid Sciences, Avionics, and Oil & Gas. He presently holds the position of ABS Adjunct Professor with the ME (Subsea Engineering Program).
Ed received a B.S. in Chemistry from the University of Albany (SUNY) and a M.S. and Ph.D. in Mechanical Engineering with specialization in Thermo-Fluid Sciences from Texas A&M University. He holds the grade of Fellow in the American Society of Mechanical Engineers (ASME) and Associate Fellow in the American Institute of Aeronautics and Astronautics (AIAA). Ed is an OTC member for both ASME and SPE subcommittees.
Dr. Srinath Madasu
Technical Advisor, Landmark
Dr. Madasu has worked as Technical Advisor at Landmark since March 2017. He did his Ph.D. from Drexel University, Philadelphia in Chemical Engineering in 2002. Srinath finished Post-Doctoral Research in Chemical engineering from The Pennsylvania State University, State College. He worked at Halliburton for more than 7 years after working at Maya Heat Transfer Technologies, Montreal as CFD and Heat Transfer Application Developer for 5 years. He received a MVP award in 2013 from Halliburton.
His main interests are Machine Learning, Optimization, Robotics and Physics based Modeling. He developed real time machine learning and optimization model for drilling, artificial lift methods such as Gas lift and automated production history matching. He has seven issued patents, five SPE papers and nine journal publications.
SPE Webinars are FREE to members courtesy of the