The oil and gas industry is increasingly striving to “produce in context” rather than “produce at all costs”, with the help of machine learning and AI. This workshop will move beyond the buzzword and demonstrate where machine learning can be applied to upstream activity to improve performance, optimize processes and inform new business models. It will walk you through practical examples of how tools and models are being utilized to uncover and solve business problems. Join this workshop to familiarize yourself with machine learning techniques to identify patterns and
improve your analysis of performance.
Jaijith Sreekantan, Senior Data Scientist, Schlumberger
Jay Parashar, Principal Data Scientist - Advanced Analytics, Schlumberger
Jay Parashar is a Principal Data Scientist – Advanced Analytics at Schlumberger. He comes from an Informational Technology background with over 20 years of experience across various domains and industries. He has worked for diverse industries and delivered applications ranging from complex algorithmic modules, to high traffic websites and application integration. He is passionate about Data Science and building high productivity applications that fulfills business goals.
At Schlumberger, he is part of the Advanced Analytics team involved in building predictive models covering Operation Efficiency, People Productivity, Asset Analytics, PHM, Sales and Operation Planning and Supply Chain Optimization to name a few.
With the possibilities becoming endless for predictive analytics to improve performance, reduce downtime and minimize risks, engineers must understand the fundamentals of this process to leverage its potential. Building predictive models requires knowledge of your datasets, the context in which it will be applied and your IT capabilities. This session will take you through the model building processes to understand what’s required for data cleansing, algorithm selection, pattern identification, breakage predictions, tool optimization and successful integration into current processes. This workshop will draw on use cases to demonstrate how analytics can identify key drivers for performance change, learning what they look like, predicting how machinery and tools will behave and finally implementing methodology to react quicker to such changes.
Keith Modesitt, Subsurface & Wells Data Science Lead , BP
For over 25 years, Mr. Modesitt has turned data into a competitive advantage for the oil & gas, transportation, utility, chemical and mining industries. Since 1999, he’s been an accredited instructor for turning earth science data into continuous actionable insight using the latest analytical technologies. Currently, he is the BP Subsurface & Wells Data Science Lead and Data Science Community of Practice Lead. He is responsible for operationalizing data science by embedding data science into how BP operates to improve safety, reduce risk and increase competitiveness.
Meena Thandavarayan, Enterprise Architect - Data and Analytics , BP
Meena Thandavarayan is an adaptive and creative Information Management leader passionate about delivering human-centered experiences. His focus is on designing and delivering data driven business solutions to enable organizations derive value from their data assets – Information Products, Machine Learning and Artificial Intelligence.
In his role at BP, Meena is responsible for the defining the strategy and architecture of BP’s operational and analytical environments working closely with Business, IT and Industry leading product vendors. Prior to BP, Meena was a practice lead for AI and Automation with Infosys delivering Fluid and transformational AI and Data science platforms for fortune 500 clients.
Meena is a connector, design thinker and an active speaker in international conferences. His passion is coaching, giving back to the community. He spends his weekends helping Middle and High school kids with SAT preparation, Programming and Junior Achievement.
Rob Klenner, Principal Geoscientist, Energy & Environmental Research Center
Rob Klenner is a Principal Geoscientist at the EERC, where he leads geological evaluations for CO2 enhanced oil recovery (EOR), CO2 storage, and unconventional hydrocarbon recovery projects and geomodeling and simulation efforts. He holds M.S. and B.S. degrees in Geology from UND.
Prior to his current position at the EERC, Mr. Klenner served as a Senior Geoscientist with Baker Hughes, a GE Company, where he was the reservoir analytics leader, creating subsurface machine learning solutions and services. Prior to that, he served as Lead Geoscientist with GE Global Research, where he was a key member of the team that initiated the reservoir program at the Oil and Gas Technology Center. He also served as a Geoscientist at the EERC and a Geophysicist Intern at The Geysers, the world’s largest geothermal field, for Calpine Corporation.
Mr. Klenner’s principal areas of interest and expertise include reservoir modeling, petrophysics, unconventional resources, petroleum geology, geothermal energy, machine learning, and commercialization of research and development. He has authored or coauthored publications in the fields of CO2 storage, EOR, geothermal energy, and machine learning solutions for upstream oil and gas.
Christopher Olsen, Data Scientist, ConocoPhillips
Dr. Christopher Olsen has been working as a Data Scientist at ConocoPhillips for the past 2 years and before that as a Petrophysicist also for ConocoPhillips for 2 years. Before moving into the oil and gas industry, he previously worked for 7 years in aerospace at the Ad Astra Rocket Company developing advanced plasma propulsion rockets, spaceflight hardware, and conducting zero-gravity experiments to fast track flight hardware. He received his doctorate and master’s degrees in Experimental Physics from Rice University in Houston Texas, and undergraduate degrees in Physics and Geology from Brigham Young University in Provo Utah.
Reza Khaninezhad, Senior Data Scientist, Apache
Dr. Reza Khaninezhad is a Senior Data Scientist at Apache Corporation. He has a Ph.D. in Electrical Engineering (Minor in Data Sciences and Operations) from University of Southern California and is a researcher, practitioner and educator as well as machine learning developer with over 6 years of practical experience developing and deploying some of the state-of-the-art industrial level artificial intelligence systems. He has authored more than 30 journal and conference papers focused on geo-statistical imaging and stochastic inverse modeling and holds three pending international and U.S. domestic patent applications in computer vision and deep learning. He also serves as technical editor in some of the prominent remote-sensing and imaging as well as petroleum engineering journals.
As Principal Data Scientist at Panton Inc, he built and deployed a fully automated object recognition system for aerial imaging using convolutional deep learning models. He has also developed several virtual reality products ranging from stereo-3D mapping to real-time human tracking systems. As a Senior Data Scientist at Apache Corporation, he is involved in development of augmented and artificial intelligence systems that automate, accelerate and guide subject matter experts’ decision-making workflows. He is also responsible for building efficient pipelines for deploying machine learning solutions. Automation and integration of disparate workflows as well as knowledge extraction from uncommon patterns in data are the main motivator for his current hobby of building automated algorithmic trading recommender systems.