Automated well productivity estimation and continuous average well pressure monitoring through integration of real-time surface and downhole pressure and temperature measurements

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.