Flooding system optimization: Advantages of a hybrid approach to developing neural network filtration models

Background. Currently, neural networks are increasingly used for processing and forecasting the dynamics of well performance. However, there are a number of limitations in their application for flooding system optimization. Objective. To develop models that can correctly reproduce the impact of the reservoir pressure maintenance system on the operation of production wells. The article considers the problem of modeling the reaction of producing wells to the changes in water injection modes in injection wells using neural network modeling methods. Results. We propose the approaches to the creation and training of physics-informed neural networks for modeling responses in oil production to regime changes in the reservoir pressure maintenance system. The results of testing the training and predictive abilities of PINN (physics-informed neural network) models are presented, and a comparison is made with the results of forecasting on the classical LSTM neural network. Conclusions. With hybrid training of models based on actual data, PINN models make it possible to offset the limitations of classical neural networks.