Graduate Research Assistant at University of OKlahoma, United States
Ashutosh Sharma is an experienced doctoral candidate in Petroleum Engineering with a solid foundation in data science and energy systems. He specializes in applying advanced machine learning techniques to optimize drilling operations and subsurface analysis. With a practical industry background and academic expertise, Ashutosh has contributed to real-time drilling efficiency, rock-bit interaction studies, and predictive modeling for petrophysical properties. His multidisciplinary approach bridges traditional petroleum engineering practices with modern data-driven solutions, making him a well-rounded professional prepared to address the evolving challenges of the energy sector.
Profile
Orcid
Education
Ashutosh is pursuing a Ph.D. in Petroleum Engineering at the University of Oklahoma with a perfect GPA of 4.0, focusing his dissertation on incorporating rock behavior into real-time drilling analysis. Complementing this, he is also earning an M.S. in Data Science & Analytics from Georgia Institute of Technology, maintaining a GPA of 3.9. He holds a prior M.S. in Petroleum Engineering from the University of Oklahoma, where he researched centrifugal packer-type downhole separators. His academic foundation was established with a B.S. in Petroleum Engineering from the Maharashtra Institute of Technology in India, where his capstone project centered on performance modeling and optimization in undersaturated oil reservoirs.
Experience
Ashutosh’s diverse work experience spans both academic research and hands-on industry roles. Most recently, he interned at Pioneer Natural Resources (now under ExxonMobil), where he developed a digital framework for drill string vibration modeling using surface and downhole data from 18 wells in the Midland Basin. Prior to that, he interned at Ensign Drilling, focusing on real-time stick-slip vibration detection using machine learning. Since 2020, he has served as a Graduate Research Assistant at the University of Oklahoma, contributing to DOE-funded projects on rock-bit interaction, real-time drilling efficiency modeling, and petrophysical parameter prediction at the bit. He also brings industry experience from Raeon Energy Services LLP, where he worked in well intervention design, site operations, and bid proposal drafting. Earlier, during an internship at NOV, he streamlined data systems and tools for drill pipe evaluation.
Research Interest
Ashutosh’s research interests lie at the intersection of petroleum engineering and data analytics, focusing on real-time drilling analysis, rock-bit interaction modeling, machine learning applications in drilling optimization, and subsurface prediction. He is especially driven by the application of data-driven approaches to enhance drilling safety, efficiency, and reservoir characterization. His work seeks to enable predictive decision-making at the rig floor, transform vibration analysis methodologies, and innovate in the field of downhole separation and petrophysical log projection.
Award
Ashutosh has been recognized for both his academic achievements and professional contributions. He received the SPE General Scholarship in the Ph.D. category, sponsored by the SPE OKC chapter, for two consecutive years (2022 and 2023). As an active participant in student competitions, he won three 1st place titles as part of the University of Oklahoma’s Petrobowl team from 2017 to 2021. He also served as Vice-President of the OU SPWLA student chapter during 2019–2020. Notably, he received a Letter of Appreciation from a project head for high-quality services rendered in the Krishna Godavari and Cambay basins. His early achievements include winning 1st prize at the MIT SPE AIIIP Case Study Challenge, sponsored by Schlumberger.
Publication
Ashutosh’s scholarly work reflects a consistent focus on machine learning applications in petroleum systems. His notable journal articles include:
Evaluating PDC bit-rock interaction models to investigate torsional vibrations in Geothermal drilling (Geothermics, Elsevier, 2024; cited by 18 articles),
Real-time lithology prediction at the bit using machine learning (Geosciences, MDPI, 2024; cited by 9 articles),
Predicting separation efficiency of a downhole separator using machine learning (Energies, MDPI, 2024; cited by 7 articles).
He has also presented several conference papers, including at URTEC Buenos Aires (2023), SPE Offshore Europe Aberdeen (2023), SPE OKC Symposium (2023), US Rock Mechanics Symposium (2021), and the SPE Artificial Lift Conference-Americas (2020). His MS thesis was focused on the experimental evaluation of a centrifugal packer-type downhole separator.
Conclusion
Ashutosh Sharma’s multidisciplinary skill set, merging petroleum engineering fundamentals with cutting-edge data analytics, positions him uniquely in the energy industry. Through his academic rigor, research innovation, and industry collaborations, he has demonstrated a commitment to advancing efficient, safe, and sustainable drilling practices. As he completes his Ph.D. and dual Master’s degrees, Ashutosh is poised to contribute meaningfully to organizations leading the energy transition and digital transformation in upstream oil and gas operations.