Reservoir simulation
The authors propose a deep-learning-based approach enabling near-real-time CO2-plume visualization and rapid data assimilation incorporating multiple geological realizations for predicting future CO2 plume evolution and area-of-review determination.
In this study, forward simulation is executed by a commercial reservoir simulator while external code is developed for backward calculations.
In this study, the authors propose the use of a deep-learning reduced-order surrogate model that can lower computational costs significantly while still maintaining high accuracy for data assimilation or history-matching problems.
-
This paper evaluates learnings from the past 30 years of methods that aim to quantify the uncertainty in the subsurface using multiple realizations, describing major challenges and outlining potential ways to overcome them. -
Schlumberger announced that ConocoPhillips will use its DELFI platform to move its data to the cloud.
-
This paper introduces methods to fully couple reservoir simulation with wellbore flow models in fractured injection wells.
-
The paper presents a model for shale gas production in which CO2 is injected by huff ’n’ puff into a hydraulic fracture surrounded by a shale matrix.
-
This study explores pitfalls experienced when using capacitance/resistance modeling as a plug-and-play technique for waterflood optimization and discusses workarounds and mitigations to improve its reliability.
-
This paper analyzes several configurations of convolutional neural networks suited for predicting upscaled fracture permeabilities and shape factors required to close a dual porosity/dual permeability model.
-
The authors write that simple and straightforward observations on outcrops can be used to build 3D models that mimic geological relationships accurately.
-
This paper presents an integrated work flow to model mechanical properties at sufficiently high resolution to honor accurately rock fabric and its effects on height and complexity and, thus, production.
-
This paper presents a comprehensive comparison of two modeling-based approaches of fluid tracking for condensate allocation and gas usage.
-
The authors develop a representative geostatistically based 3D model that preserves geological elements and eliminates uncertainty of reservoir properties and volumetric estimates for a Libyan field.
