Abstract: Continuous gross rate of each of a plurality of wells is estimated. Information provided by sensors configured with each of a plurality of electrical submersible pumps is received. Information associated with a respective model of each of the plurality of electrical submersible pumps is accessed. Utilizing at least one of artificial intelligence and machine learning, the information provided by sensors and the information associated with the respective model of each of the plurality of electrical submersible pumps is processed to estimate a first gross rate of each of the plurality of wells. A second gross rate of each of the plurality of wells is estimated via a pipeline simulation that applies a physics-based model. A continuous gross rate for each of the plurality of wells is estimated as a function the first gross rate and the second gross rate.

Abstract: Embodiments described herein include a system for dynamic real-time water-cut monitoring that includes a plurality of sensors for sensing pressure across a pipe that includes logic that causes the system to determine whether to use a direct approach for determining water-cut. In some embodiments, in response to determining not to use the direct approach, the logic causes the system to determine an initial guess for water-cut, estimate at least one dynamic pressure loss across the distance, estimate at least one potential energy pressure loss across the distance, estimate a value for water-cut from the at least one dynamic pressure loss and the at least one potential energy pressure loss, determine whether the initial guess is within a predetermined threshold of the value for water-cut, and in response to determining that the initial guess is within the predetermined threshold of the value for water-cut, output the value for water-cut.

Abstract: Systems and methods for generating pressure data from at least two pressure sensors, storing one or more parameters indicative of water cut in a neural network model, receiving pressure data from at least the two pressure sensors respectively indicative of the pressure at two points of a well bore, determining a pressure drop between the two points, generating an input water cut estimate, estimating a dynamic pressure loss to initiate an iterative process, estimating a potential energy loss, inverse modeling a water cut estimate, comparing the water cut estimate to the input water cut estimate to generate a water cut ?, utilizing the water cut estimate as the input water cut estimate for the iterative process when the water cut ? exceeds a threshold, and continuing the iterative process until the water cut ? is below the threshold.

Abstract: Embodiments described herein include a system for dynamic real-time water-cut monitoring that includes a plurality of sensors for sensing pressure across a pipe that includes logic that causes the system to determine whether to use a direct approach for determining water-cut. In some embodiments, in response to determining not to use the direct approach, the logic causes the system to determine an initial guess for water-cut, estimate at least one dynamic pressure loss across the distance, estimate at least one potential energy pressure loss across the distance, estimate a value for water-cut from the at least one dynamic pressure loss and the at least one potential energy pressure loss, determine whether the initial guess is within a predetermined threshold of the value for water-cut, and in response to determining that the initial guess is within the predetermined threshold of the value for water-cut, output the value for water-cut.

Abstract: Systems and methods for generating pressure data from at least two pressure sensors, storing one or more parameters indicative of water cut in a neural network model, receiving pressure data from at least the two pressure sensors respectively indicative of the pressure at two points of a well bore, determining a pressure drop between the two points, generating an input water cut estimate, estimating a dynamic pressure loss to initiate an iterative process, estimating a potential energy loss, inverse modeling a water cut estimate, comparing the water cut estimate to the input water cut estimate to generate a water cut ?, utilizing the water cut estimate as the input water cut estimate for the iterative process when the water cut ? exceeds a threshold, and continuing the iterative process until the water cut ? is below the threshold.

Abstract: Systems and methods for intelligent estimation of productivity index and reservoir pressure values using pressure sensors, a neural network model comprising historical flow rate data of at least a well bore, and a data processor. The pressure sensors generate pressure data associated with a well bore's surface point and a downhole point. The data processor, communicatively coupled to the two pressure sensors and the neural network model, is operable to receive the pressure data from the sensors respectively indicative of pressure at each of the two points, estimate a real-time productivity index value in real-time based on the pressure data from the pressure sensors and the historical flowrate data of the neural network model, and estimate a reservoir pressure value of the well bore at a flowing condition, a reservoir pressure value of the well bore at a shut-in condition, or both, based on the real-time productivity index.