Abstract: This disclosure relates to an inflow control system having an apparatus configured to form or plug openings in a blank pipe. The apparatus includes a housing and a milling sub-system. The housing has a cylindrical wall with an outer surface. The milling sub-system is mounted to a first side of the wall and is configured to mill an opening in the blank pipe. The milling sub-system includes a bit configured to form an opening in the blank pipe and at least one brace attached to a second side of the wall opposite the first side of the wall. The at least one brace is configured to extend radially from the second side of the wall to press the bit to the inner surface of the blank pipe.

Abstract: Methods for training machine learning algorithms for generation of a reservoir digital twin include receiving information obtained from hydrocarbon wells. The information includes porosity logs, petrophysical data, rock typing data, pressure transient test results, vertical production logs, reservoir pressure logs, reservoir saturation logs, production performance, and injection performance. The reservoir saturation logs are normalized in accordance with time. A machine learning algorithm is trained using the reservoir pressure logs, the production performance, and the injection performance to provide variations in reservoir pressure of the hydrocarbon reservoir in accordance with time. The machine learning algorithm is trained to provide variations in reservoir saturation of the hydrocarbon reservoir in accordance with time.

Abstract: A method of removing wellbore water from a production wellbore includes determining a production flow rate. The method also includes determining a target production flow rate of the production fluid and comparing the production flow rate to a flow rate threshold associated with the target production flow rate. The method also includes determining, based on a result of comparing the production flow rate to the flow rate threshold, that the production flow rate satisfies the threshold. The method also includes activating a fluid moving device fluidly coupled to a wellbore string extending from a terranean surface to the water to inject, into the water, at least one of i) a surfactant, ii) a gas, or iii) a foaming agent, allowing the water and the production fluid to emulsify together and thereby allowing a mixture of water and production fluid to flow to the terranean surface of the wellbore.

Abstract: A system and methods for electrolysis of saline solutions are provided. An exemplary method provides simulating temperature gradients of reservoir fluids at different well conditions in a well, wherein the reservoir fluids include oil and water. A total flow rate of the reservoir fluids is quantified based on the simulated temperature gradients, and a water flow rate of water in the reservoir fluids is calculated based on, at least in part, a pulsed neutron log. An oil flow rate is calculated from the total flow rate of the reservoir fluids and the water flow rate.

Abstract: This disclosure relates to an inflow control system having an apparatus configured to form or plug openings in a blank pipe. The apparatus includes a housing and a milling sub-system. The housing has a cylindrical wall with an outer surface. The milling sub-system is mounted to a first side of the wall and is configured to mill an opening in the blank pipe. The milling sub-system includes a bit configured to form an opening in the blank pipe and at least one brace attached to a second side of the wall opposite the first side of the wall. The at least one brace is configured to extend radially from the second side of the wall to press the bit to the inner surface of the blank pipe.

Abstract: The present disclosure describes a method for surveillance of a horizontal well, including: monitoring a first set of measurement data from a pulsed neutron tool and a second set of measurement data from an array tool, wherein: the first set of measurement data indicate a holdup of the second liquid globally inside the horizontal well, and the second set of measurement data show a plurality of velocities measured at a set of corresponding locations inside the horizontal well; and interpolating the first set of measurement data to identify an interface between the first liquid and the second liquid; establish an estimated holdup of the second liquid in the cross-section of the horizontal well; and combining the estimated holdup of the second liquid with velocities measured at locations inside the horizontal well that correspond to the second layer to generate a flow weighted estimate of the second liquid inside the horizontal well.

Abstract: A computer system generates a virtual three-dimensional (3D) model of a hydrocarbon reservoir using a machine learning algorithm. The machine learning algorithm is trained using information obtained from multiple hydrocarbon wells. The virtual 3D model includes a reservoir pressure model of the hydrocarbon reservoir indicating variations in reservoir pressure in accordance with time. A fluid saturation model of the hydrocarbon reservoir indicates variations in reservoir saturation in accordance with time. The computer system executes the machine learning algorithm to determine the variations in the reservoir pressure and the variations in the reservoir saturation with respect to the multiple hydrocarbon wells based on the virtual 3D model. A display device of the computer system generates a graphical representation of the variations in the reservoir pressure and the variations in the reservoir saturation in accordance with time.

Abstract: Methods for training machine learning algorithms for generation of a reservoir digital twin include receiving information obtained from hydrocarbon wells. The information includes porosity logs, petrophysical data, rock typing data, pressure transient test results, vertical production logs, reservoir pressure logs, reservoir saturation logs, production performance, and injection performance. The reservoir saturation logs are normalized in accordance with time. A machine learning algorithm is trained using the reservoir pressure logs, the production performance, and the injection performance to provide variations in reservoir pressure of the hydrocarbon reservoir in accordance with time. The machine learning algorithm is trained to provide variations in reservoir saturation of the hydrocarbon reservoir in accordance with time.