Rice University & DeepCast Co.
Dr. Hector Klie is an experienced computational and data scientist focused on developing physics-informed AI solutions for multiple engineering and geoscientific applications in Oil & Gas. Dr. Klie is co-founder and Chief Executive Officer of DeepCast.ai since June 2017. He is currently appointed as an Adjunct Professor of the Dept. of Computational and Applied Mathematics at Rice University. Prior to his role at DeepCast.ai, he was Director of Enterprise Data Solutions and Data Science Technical Lead at Sanchez Oil & Gas Corporation (2016-2017), Staff Reservoir Engineer and Lead Data Scientist at ConocoPhillips (2008-2016) and Associate Director and Senior Research Associate at the Center for Subsurface Modeling in The University of Texas at Austin (2003-2008) and, Research Scientist at PDVSA-Intevep (1989-2003). He has published over 80 papers in the areas of sparse linear solvers, production forecasting, field optimization, uncertainty quantification, high-performance computing, reduced-order modeling, and machine learning. Dr. Klie has patented 5 inventions in the areas of data analytics for automated drilling and parallel physics-based solvers. He has chaired and co-organized several technical events at the SPE, SIAM, SEG, and IEEE. He is currently an Associate Editor of the Computational Geosciences Journal. Dr. Klie completed his Ph.D. in Computational Science and Engineering at the Dept. of Computational and Applied Mathematics at Rice University, 1997, and a Master’s Degree in Computer Science at Simon Bolivar University, Venezuela, 1991.
Numerical simulation in porous media relies on the discrete representation of equations that have been derived from conservation laws and constitutive relations. In many practical applications, the scope of these equations can be insufficient to realistically describe the dynamics of flow in complex porous media induced by sudden changes in boundary conditions and force terms (e.g., wells, aquifers). Nevertheless, the increasing affordability for collecting and storing large volumes of data is enabling possibilities to gain new insights and discover elusive physical relations missing from existing simulation models. In this presentation, we introduce a framework of combined physics-based and data-driven models, namely Physics-AI (or PhysAI) models, to reconstruct and predict the dynamics of fluid flow in diverse unconventional field scenarios. These models are designed to learn and identify spatiotemporal relationships from monitoring data as well as providing explainable interpretations in the form of differential equations if needed. Hence, the proposed approach differs from other well-known data-driven approaches that strictly rely on black-box solutions. Capabilities of PhysAI models are evaluated for reliably predicting state data (e.g., pressure and saturation) as well as for forecasting multi-well production data on multiphase and couple flow/geomechanics applications involving both synthetic and modest field data requirements. A stochastic optimization approach is coupled with the resulting PhysAI model for generating optimal in-fill, drawdown, and completion design recommendations in different unconventional fields.