A Recurrent Neural Network-Based Solvent Chamber Estimation Framework During Warm Solvent Injection in Heterogeneous Reservoirs

Abstract

Abstract Warm solvent injection (WSI), injecting low-temperature solvent into formations to reduce the viscosity of heavy oil, is a clean technology for heavy oil production while reducing greenhouse gas emissions and water usage. The success of WSI operation depends on the uniform development of solvent chambers in reservoirs. However, reservoir heterogeneity stemming from shale barriers plays a detrimental role in the conformance of solvent chamber development and oil production rate. In this work, we develop a novel recurrent neural network (RNN)-based framework with the capability of efficiently tracking and estimating the solvent chamber positions in heterogeneous reservoirs based on only production time-series data. The developed estimation model utilizes the "sequence-to-sequence" mapping methodology to correlate observed production time-series sequence and solvent chamber edge sequence via a long short-term memory (LSTM) algorithm. The developed RNN-based workflow is tested via several cases, and the results are promising. The predicted dynamic solvent chamber locations match the corresponding true locations with a high coefficient of determination and a low mean squared error. The major benefits of this workflow include reducing time for numerical simulations and saving overall monitoring and tracking costs for conventional techniques. The present work would provide a good illustration of the capability of practical integration of machine learning methods in solving engineering problems.