Skip to the content.

Deep Learning in Science and Engineering

Eduardo Gildin, Harold Vance Department of Petroleum Engineering
Development of Proxy Models for Reservoir Simulation by Sparsity Promoting Methods and Machine Learning Techniques

Abstract

Model Order Reduction (MOR) has been used to accelerate large-scale reservoir simulations while preserving the accuracy of the underlying solution. However, changes in reservoir configuration hinder the use of MOR for general applications. Although real-time data can help in devising alternative fixes to MOR, there is still a disconnect with the traditional theoretical first laws principles, whereby conservation laws and phenomenological behavior are used to derive the underlying spatio-temporal evolution equations. In this work, we propose to combine sparsity promoting methods and machine learning techniques to find the governing equation from the spatio-temporal data series from a reservoir simulator. The idea is to connect data with the physical interpretation of the dynamical system. First, we achieve this by identifying the nonlinear ODE system equations of our discretized reservoir system. Second, by using machine learning techniques, we show that the entire system can be represented by the already existing ROMs from very few well locations. Machine Learning provide promising results to approximate the characteristics of the parametric reduced order models.