Machine Learning Applications in Subsurface Energy Resource Management

Dr. Srikanta Mishra is Senior Research Leader and Technical Director for Geo-energy Resource Modeling and Analytics at Battelle Memorial Institute, the world’s largest independent contract R&D organization. He is nationally and internationally recognized for his expertise in developing and communicating physics-based and data-driven predictive models for subsurface resource management. Dr. Mishra currently serves as the Technical Lead of the SMART (Science Informed Machine Learning for Accelerating Real-time Decisions for Subsurface applications) initiative, organized by the US Department of Energy and involving multiple national laboratories and universities. He was a recipient of the Society of Petroleum Engineers (SPE) Distinguished Member Award in 2021, and also served as a Global Distinguished Lecturer on Big Data Analytics for SPE during 2018–19 and received the 2022 SPE Data Science and Engineering Analytics Award.

Part 1: Reservoir Characterization 1. Machine Learning in Geophysical Imaging Modalities for Unconventional Plays 2. Machine Learning for Discovering, Understanding and Extracting Geothermal Energy (Velimir Vesselinov, Los Alamos National Laboratory) 3. Enhancing Our Understanding of the Subsurface With Ml/ai Applied to Well and Seismic Data Part 2: Drilling Operations 4. Overview of Ml/ai Applications in Drilling 5. Using Machine Learning to Improve Drilling Operations in Unconventional and Tight Rocks Part 3: Production Data Analysis 6. Application of Physics-informed Neural Networks in the Analysis of Production Data From Unconventional Reservoirs 7. Machine Learning Assisted Decline Curve and Pressure/rate Transient Analysis in Unconventional Plays (Dmachine Learning Case Studies for Performance Forecasting of Oil and Gas Reservoirs 8. Role of Analytics in Extracting Data-driven Models From Reservoir Surveillance Part 4: Reservoir Modeling 9. Deep-learning and Reduced-order Model Based Proxies for History Matching and Uncertainty Quantification 10. Hybrid Machine Learning and Physics-informed Reservoir Modeling for Unconventionals 11. New Machine Learning and Deep Learning Approaches for Field Development and Production Optimization 12. Physics-embedded Machine Learning for Modeling and Optimization of Oil and Gas Assets 13. Reservoir Modeling Using Fast Predictive Machine Learning Algorithms for Geological Carbon Storage 14. Top-down Reservoir Modeling