Digital Reservoir Characterization Technology (DIRECT)

Michael Pyrcz

John T. Foster

Carlos Torres-Verdin

Eric Van Oort

The DIRECT Industrial Affiliate Project aims to develop novel technologies, practical workflows, demonstrations and documentation to enable subsurface data analytics and machine learning.

Our goals are to combine best-practice and cutting-edge technology in  reservoir spatiotemporal characterization and modeling , real-time drilling control , production data integration and forecasting , reservoir petrophysical measures and geophysics with emerging technology in big data analytics and machine learning to optimize well trajectory and resource recovery.

Example Projects

Spatial Correlation-based Anomality Detection for Subsurface Data Analytics

Feature Engineering Assisted Well Log Interpretation

Generalized Deep Learning for Flow Forecasting Surrogate Modeling


Jin Kyung Lee - This email address is being protected from spambots. You need JavaScript enabled to view it.

Website URL