Engineering Commons^™

Development Of Reduced Order Models Using Reservoir Simulation And Physics Informed Machine Learning Techniques, Mark V. Behl Jr

LSU Master's Theses

Reservoir simulation is the industry standard for prediction and characterization of processes in the subsurface. However, simulation is computationally expensive and time consuming. This study explores reduced order models (ROMs) as an appropriate alternative. ROMs that use neural networks effectively capture nonlinear dependencies, and only require available operational data as inputs. Neural networks are a black box and difficult to interpret, however. Physics informed neural networks (PINNs) provide a potential solution to these shortcomings, but have not yet been applied extensively in petroleum engineering.

A mature black-oil simulation model from Volve public data release was used to generate training data …

Geoaware - A Simulation-Based Framework For Synthetic Trajectory Generation From Mobility Patterns, Jameson D. Morgan

Browse all Theses and Dissertations

Recent advances in location acquisition services have resulted in vast amounts of trajectory data; providing valuable insight into human mobility. The field of trajectory data mining has exploded as a result, with literature detailing algorithms for (pre)processing, map matching, pattern mining, and the like. Unfortunately, obtaining trajectory data for the design and evaluation of such algorithms is problematic due to privacy, ethical, dataset size, researcher access, and sampling frequency concerns. Synthetic trajectories provide a solution to such a problem as they are cheap to produce and are derived from a fully controllable generation procedure. Citing deficiencies in modern synthetic trajectory …