Application of Gated Recurrent Unit (GRU) Neural Network for Smart Batch Production Prediction

Xuechen Li,Shicheng Zhang,Fei Wang,Xinfang Ma,Fengchao Xiao

doi:10.3390/en13226121

Abstract

Production prediction plays an important role in decision making, development planning, and economic evaluation during the exploration and development period. However, applying traditional methods for production forecasting of newly developed wells in the conglomerate reservoir is restricted by limited historical data, complex fracture propagation, and frequent operational changes. This study proposed a Gated Recurrent Unit (GRU) neural network-based model to achieve batch production forecasting in M conglomerate reservoir of China, which tackles the limitations of traditional decline curve analysis and conventional time-series prediction methods. The model is trained by four features of production rate, tubing pressure (TP), choke size (CS), and shut-in period (SI) from 70 multistage hydraulic fractured horizontal wells. Firstly, a comprehensive data preprocessing is implemented, including excluding unfit wells, data screening, feature selection, partitioning data set, z-score normalization, and format conversion. Then, the four-feature model is compared with the model considering production only, and it is found that with frequent oilfield operations changes, the four-feature model could accurately capture the complex variance pattern of production rate. Further, Random Forest (RF) is employed to optimize the prediction results of GRU. For a fair evaluation, the performance of the proposed model is compared with that of simple Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) neural network. The results show that the proposed approach outperforms the others in prediction accuracy and generalization ability. It is worth mentioning that under the guidance of continuous learning, the GRU model can be updated as soon as more wells become available.

Highlights

Production prediction plays an important role in decision making, development planning, and economic evaluation during the exploration and development period
history window (HW), the long‐term production rate can be obtained according to the proposed well-block Gated Recurrent Unit (GRU) model
Continuous learning refers to the PartIterative scheme, as depicted in Figure 8c, in which the HW will be updated as time goes on to make full use of production data

Summary

Introduction

Production prediction plays an important role in decision making, development planning, and economic evaluation during the exploration and development period. In unconventional reservoirs, accurate production estimation helps evaluate oil and gas potential and, at the same time, guides fracturing operation reasonably [1,2,3]. There are several commonly used methods for future production prediction. Reservoir numerical simulation is a common method for production rate forecasting because of its reliable physical background [4,5]. It is time-consuming and demands many reservoir features, such as rock mechanical parameters and fluid property parameters [6]. In conglomerate reservoirs, it is difficult to build a robust numerical model due to the effect of gravel as well as the complicated fracture propagation mechanism

Objectives

Methods

Results

Conclusion