Abstract: Embodiments for generating a reservoir performance forecast are provided. The embodiments may be executed by a computer system. In one embodiment, a method includes obtaining inflow performance relationship data generated from a physics-based subsurface-surface coupled simulation model having a surface, a subsurface, and one or more wells fluidly connecting the subsurface to the surface. The inflow performance relationship data comprises performance data for at least one phase of fluid for each well. The method also includes generating a performance forecast for the reservoir using a subsurface simulator and a surface simulator. The subsurface simulator uses the inflow performance relationship data to represent the subsurface during generation of the performance forecast, and the performance forecast satisfies constraints solved by the surface simulator. In one embodiment, a method does not utilize a surface simulator.

Abstract: Embodiments of conservative, sequential fully implicit compositional reservoir simulation are disclosed where 1) pressure, 2) saturation, 3) component balance, and 4) phase equilibrium are computed sequentially to solve for movement of liquid and gas phases over a series of time-steps until convergence to represent fluid flow within the subterranean reservoir. All molecular components in each of the liquid and gas phases are fixed to move with an equivalent phase velocity. Thermodynamic fluxes are accounted for when computing phase equilibrium by computing a difference between fluid volume and pore volume. A hybrid upwinding scheme can be employed to reorder cells based on upwind direction to improve the saturation convergence, especially when phase equilibrium significantly alters the cell properties.

Abstract: Embodiments of generating a field development plan for a hydrocarbon field development are provided herein. One embodiment comprises generating a plurality of training reservoir models of varying values of input channels of a reservoir template; normalizing the varying values of the input channels to generate normalized values of the input channels; constructing a policy neural network and a value neural network that project a state represented by the normalized values of the input channels to a field development action and a value of the state respectively; and training the policy neural network and the value neural network using deep reinforcement learning on the plurality of training reservoir models with a reservoir simulator as an environment such that the policy neural network generates a field development plan. A field development plan may be generated for a target reservoir on the reservoir template using the trained policy network and the reservoir simulator.

Abstract: Computer-implemented systems and methods are provided for optimizing hydrocarbon recovery from subsurface formations, including subsurface formations having bottom water or edgewater. A system and method can be configured to receive data indicative of by-pass oil areas in the subsurface formation from reservoir simulation, identify flow barriers in the subsurface formation based on the by-pass oil areas identified by the reservoir simulation, and predict the lateral extension of the identified flow barriers in the subsurface formation. Infill horizontal wells can be placed at areas of the subsurface formation relative to the flow barriers such that production from a horizontal well in the subsurface formation optimizes hydrocarbon recovery.

Abstract: Computer-implemented systems and methods are provided for optimizing hydrocarbon recovery from subsurface formations, including subsurface formations having bottom water or edgewater. A system and method can be configured to receive data indicative of by-pass oil areas in the subsurface formation from reservoir simulation, identify flow barriers in the subsurface formation based on the by-pass oil areas identified by the reservoir simulation, and predict the lateral extension of the identified flow barriers in the subsurface formation. Infill horizontal wells can be placed at areas of the subsurface formation relative to the flow barriers such that production from a horizontal well in the subsurface formation optimizes hydrocarbon recovery.

Abstract: A method, system and apparatus for real-time reservoir model updating using ensemble Kalman filters is described. The method includes a conforming step for bring bringing static and dynamic state variables into conformance with one another during a time step of the updating. Also, an iterative damping method is used in conjunction with the conformance step to account for nonGaussian and nonlinear features in a system. Also, a re-sampling method is described which reduces the ensemble size of reservoir models which are to be updated.

Abstract: A method, system and apparatus for real-time reservoir model updating using ensemble Kalman filters is described. The method includes a conforming step for bring bringing static and dynamic state variables into conformance with one another during a time step of the updating. Also, an iterative damping method is used in conjunction with the conformance step to account for nonGaussian and nonlinear features in a system. Also, a re-sampling method is described which reduces the ensemble size of reservoir models which are to be updated.