Artificial Neural Network for 4D Reservoir Modeling System Design

Authors:

Abstract
In quantitative geological modeling with an artificial neural network approach, time information can be considered as input variable to better describe dynamic evolution patterns of reservoir parameters. Such approach requires independent programming to implements 4D reservoir modeling systems and thus introduces a new research area with great development potential. This paper is dedicated to implement a 4D reservoir modeling system by neural network. It explains the development process with detailed activities vary from determine the execution process and organization structure at one extreme to determine the sequence diagram at the other extreme. Between two extremes besides analyzing essential object class functions, UML modeling language has been used to define the use case model, static structure model and dynamic behavior model. It has practical meaning for further development of eastern oil field in China.