Abstract: A computer-implemented method for determining flow information of a well producing fluid from a subsurface formation comprising. The method comprises obtaining at least one first production measurement from the well. The method comprises obtaining, with a sensor, a first measurement generated by the fluid flowing through a device. The method comprises inputting the first measurement and the at least one first production measurement into a virtual flow meter. The method comprises determining, via the virtual flow meter, a multi-phase flow rate of the fluid based on the first measurement and the at least one first production measurement.

Abstract: A method for configuring a learning machine to predict a flow rate of at least one phase of a fluid. The method comprises determining a feature set for the learning machine, the feature set including information derived from a signal generated by a flow of the fluid interacting with a fluidic oscillator in a wellbore. The method comprises configuring the learning machine with the feature set including information derived from the signal.

Abstract: Some implementations relate to a computer-implemented method for creating digital acoustic sensing (DAS) related training data for a learning machine. The method may include moving a first optimal microseismic event location to a first perturbed microseismic event location in each of a plurality of first images. The method also may include modifying first shear waves and first compressional waves in each of the first images based on one or more signal travel times between the first perturbed microseismic event location and a fiber optic cable to form a plurality of training images configured to train a learning machine.