Abstract: Defining flow control device configurable positions include executing a reservoir simulator on a reservoir model to obtain a collection of flow control device settings defined in continuous space. For each number of multiple numbers of clusters, a cluster analysis is individually performed on the collection to obtain a set of flow control device configurable positions. The set includes the number of flow control device configurable positions and its corresponding inflow area or diameter. Performing the cluster analysis across the numbers generates multiple sets for the multiple numbers of clusters. The sets of flow control device configurable positions are compared to obtain a selected set of flow control device configurable positions, which is presented in a completion design.

Abstract: A method can include performing a reservoir simulation for injection of carbon dioxide into a reservoir via an injection well: during the performing, accessing a trained machine learning model that outputs hydrate information based on reservoir conditions; and, based on the hydrate information, generating reservoir simulation results that indicate an amount of the carbon dioxide sequestered in the reservoir.

Abstract: A method for calibrating a reservoir model includes receiving a reservoir model of a reservoir. The method also includes simulating ensembles of dynamic cases of the reservoir model to produce simulated dynamic cases. Each dynamic case is different. The dynamic cases each include a plurality of levels. The method also includes performing history matching between the simulated dynamic cases and observed production data to identify a combination of parameters of the reservoir model or values of the parameters. The combination of parameters or values of the parameters result in one or more mismatch values between the simulated dynamic cases and the observed production data being less than a mismatch threshold. The method also includes generating a display based upon the combination of the parameters or the values of the parameters that result in the one or more mismatch values being less than the mismatch threshold.

Abstract: An integrated autonomous operation system that holistically renders the operation in digital form at multiple scales, including reservoir, surface infrastructure, workflows, processes, and the real asset. The system provides an end-to-end digital twin connecting subsurface to production. A subsurface model identifies and monitors water-producing zones for strategic decisions. The models use intelligent AI to provide optimum water injection setpoints. The models provide data to systems that automatically control the chokes and valves to meet the setpoints, thus achieving fully integrated, autonomous operations.

Abstract: A method includes obtaining a reservoir model for a subsurface reservoir, identifying a current state of the subsurface reservoir using the reservoir model, and a computer processor selecting an optimization function from multiple optimization functions according to the current state of the reservoir to obtain a selected optimization function. The method further includes the computer processor calculating valve positions of physical devices using the selected optimization function. The valve positions are implemented.

Abstract: Defining flow control device configurable positions include executing a reservoir simulator on a reservoir model to obtain a collection of flow control device settings defined in continuous space. For each number of multiple numbers of clusters, a cluster analysis is individually performed on the collection to obtain a set of flow control device configurable positions. The set includes the number of flow control device configurable positions and its corresponding inflow area or diameter. Performing the cluster analysis across the numbers generates multiple sets for the multiple numbers of clusters. The sets of flow control device configurable positions are compared to obtain a selected set of flow control device configurable positions, which is presented in a completion design.

Abstract: A method includes obtaining a reservoir model for a subsurface reservoir, identifying a current state of the subsurface reservoir using the reservoir model, and a computer processor selecting an optimization function from multiple optimization functions according to the current state of the reservoir to obtain a selected optimization function. The method further includes the computer processor calculating valve positions of physical devices using the selected optimization function. The valve positions are implemented.