Machine Learning Applications to Reservoir Engineering
Tuesday, 24 September
Room 217 - 219
Technical Session
This session highlights various applications of machine learning methods for reservoir engineering related problems, from optimization of well location and reservoir production, to estimation of petrophysical properties, including automation of history matching and productivity analysis.
-
0830-0855 220783Embed-to-Control-Based Deep-Learning Surrogate for Robust Nonlinearly Constrained Life-Cycle Production Optimization: A Realistic Deepwater Application
-
0855-0920 220964Developing a Novel Machine Learning-based Petrophysical Rock Typing (PRT) Classification: Applied to Heterogenous Carbonate Reservoirs
-
0920-0945 220992Estimating Rock Typing in Uncored Wells Using Machine Learning Techniques for Brazilian Pre-Salt Carbonate Reservoir
-
1015-1040 220847Estimating Petrophysical Properties Directly from Seismic: A Deep Learning Application to Carbonate Field For CO2 Storage Potential
-
1040-1105 220876Efficacy Gain From A Deep Neural Network-based History-matching Workflow
-
1105-1130 220754Deep Learning-driven Acceleration Of Stochastic Gradient Methods For Well Location Optimization Under Uncertainty
-
Alternate 220715Machine-learning Workflow for Fracture Geometry Characterization using High-resolution Distributed Strain Sensing During Well Production