A Deep-Learning-Based LSTM Approach for Multiphase Rate Transient Analysis in Tight and Ultratight Reservoir

Abstract

This paper developed a long short-term memory (LSTM)-based deep learning for rate transient analysis in tight and ultratight (shale) reservoirs and proposed a workflow to quantitatively evaluate fracture parameters. The proxy model is based on a deep-learning algorithm of LSTM and is combined with a semi-analytical (base) model for multiphase water and hydrocarbon flow in the hydraulically fractured reservoirs. To rigorously consider the multiphase flow mechanism in the semi-analytical model, LSTM and attention mechanism are introduced to forecast the key relationship of average saturation and pressure for semi-analytical model by training and predicting the time-dependent pressure and saturation series. We generated thousands of numerical simulation cases of wells in hydraulically fractured reservoirs, which provide production data and static reservoir data to train the deep-learning-based proxy model. Model verification and comparison show that the proxy model can effectively predict pressure-dependent average saturation relationships with high accuracy. The numerical validation confirms the superiority of the proposed deep-learning-based model over the semi-analytical model in accuracy with an error of less than 10% in estimating reservoir and fracture parameters and in calculation efficiency with the speed two orders of magnitude faster. The LSTM approach for rate transient analysis provides a more reliable method for evaluating reservoir performance, which can lead to improved production planning and resource allocation.