Hybrid Reservoir Modeling and Evaluation Merging Physics and Data-Driven Technology
Monday, 23 September
Room 220 - 222
Technical Session
This session is focused on integration of advanced machine learning technologies into existing workflows for reservoir modeling and evaluation. Highlights includes using data analytics to analyze large datasets and extract meaningful insights and using hybrid approaches for well performance analysis, completion design, connectivity analysis, and enhancement of reservoir modeling and simulation.
-
1400-1425 220875Analyzing Impact Of Fracturing Revolution On Shale Oil Well Performance In Permian Basin: A Review From Over 10,000 Wells
-
1425-1450 220989A New Algorithm For Automated ISIP Interpretation
-
1450-1515 220933Physics-Informed Machine Learning Approach For Closed-Loop Reservoir Management Using RGNet
-
1545-1610 220978Transfer Learning In Flow Surrogate Model With Physics-guided Neural Network
-
1610-1635 220906Application Of Artificial Intelligence To Model Stresses And Failure Parameters In Anisotropic Formations
-
1635-1700 221029Fast Evaluation Of Reservoir Connectivity By Use Of A Newdeep Learning Approach - Attention-guided Fusion Model
-
Alternate 220982Physics Informed Production Forecast Using Long Short-Term Memory With Attention
-
Alternate 220838Enhanced 3d Pore Segmentation And Multi-model Pore-scale Simulation By Deep Learning
-
Alternate 221028Enhancing Reservoir Model History Matching With Ai Surrogate And Ensemble Iterative Algorithms
-(1200x628-px).png)