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.
-
The optimization algorithm used in this work is a hybrid genetic algorithm (HGA), which is the combination of GAs with artificial neural networks (ANNs) and evolution strategies (ESs). -
Computational advances in reservoir simulation have made possible the simulation of thousands of reservoir cases in a practical time frame. This enables exhaustive exploration of subsurface uncertainty and development/depletion options.
-
This paper describes how seismic reservoir integration, advanced production analysis, and accurate nanoscale and 3D full-field simulations may address profitability issues and help oil companies to be more efficient in developing unconventional portfolios.
-
With the easy conventional oil in Argentina having been produced, one remaining way to find new oil in existing fields is to convert fields from primary or secondary production to secondary or tertiary production, respectively.
-
Because the uncertainty analysis is complex and time consuming, in this paper, a stochastic representation of the computer model, called an emulator, was constructed to quantify the reduction in the parameter input space.
-
Reservoir-simulation-model inputs are numerous, and uncertainty is pervasive—before, during, and after development. With the pressure to deliver results quickly, how do we find the right balance?
-
In upstream oil and gas, cloud computing is very immature because the industry has always been challenged by storage and computational capability. However, high-performance cloud computing may create an opportunity for smaller companies lacking infrastructure for scientific applications.
-
Permanent downhole gauges (PDGs) can provide a continuous record of flow rate and pressure, which provides extensive information about the reservoir. In this work, a machine-learning framework based on PDG data was extended to two applications: multiwell testing and flow-rate reconstruction.
-
With the recent drop in oil prices, operators are shifting to optimization of existing assets with minimal costs. For mature floods (water, chemical, and CO2), one low-cost optimization strategy is the intelligent adjustment of well-rate targets.
-
In this paper, the authors introduce a novel semianalytic approach to compute the sensitivity of the bottomhole pressure (BHP) data with respect to gridblock properties.
