Application of a neural network in well testing

Petroleum well test analysis is a tool for estimating the average properties of the reservoir rock. It is a classic example of an inverse problem. Visual examination of the pressure response of the reservoir to an induced flow rate change at a well allows the experienced analyst to determine the most appropriate model from a library of generalized analytical solutions. Rock properties are determined by finding the model parameters that best fit the observed data. This paper describes a framework in which a modified version of the HaVNet architecture is employed to classify the sequence of features that occur in the test. The network structure is described and the advantages and disadvantages compared to previous approaches are discussed