Time series forecasting of oil production in Enhanced Oil Recovery system based on a novel CNN-GRU neural network

Chen, Guangxu; Tian, Hailong; Xiao, Ting; Xu, Tianfu; Lei, Hongwu

doi:10.1016/j.geoen.2023.212528

Cited by 10 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rise of artificial intelligence, neural network models for TSF have been proposed and widely used. Neural networks are able to break the limitations of numerical simulation methods and have the advantage of massively parallel processing for fast history fitting and prediction [15]. Sagheer and Kotb [16] proposed a deep long short-term memory (DLSTM) architecture to overcome the time-consuming and complex limitations of traditional prediction methods, and DLSTM outperformed statistical ARIMA [17] (an auto-regressive integrated moving average statistical algorithm), NEA [18] (a nonlinear extension model based on the Arps decline model), and HONN [19] (a cumulative oil production prediction method based on higher-order neural networks) in experiments.…”

Section: Introductionmentioning

confidence: 99%

A Time Series Forecasting Approach Based on Meta-Learning for Petroleum Production under Few-Shot Samples

Xu,

2024

Energies

View full text Add to dashboard Cite

Accurate prediction of crude petroleum production in oil fields plays a crucial role in analyzing reservoir dynamics, formulating measures to increase production, and selecting ways to improve recovery factors. Current prediction methods mainly include reservoir engineering methods, numerical simulation methods, and deep learning methods, and the required prerequisite is a large amount of historical data. However, when the data used to train the model are insufficient, the prediction effect will be reduced dramatically. In this paper, a time series-related meta-learning (TsrML) method is proposed that can be applied to the prediction of petroleum time series containing small samples and can address the limitations of traditional deep learning methods for the few-shot problem, thereby supporting the development of production measures. The approach involves an architecture divided into meta-learner and base-learner, which learns initialization parameters from 89 time series datasets. It can be quickly adapted to achieve excellent and accurate predictions with small samples in the oil field. Three case studies were performed using time series from two actual oil fields. For objective evaluation, the proposed method is compared with several traditional methods. Compared to traditional deep learning methods, RMSE is decreased by 0.1766 on average, and MAPE is decreased by 4.8013 on average. The empirical results show that the proposed method outperforms the traditional deep learning methods.

show abstract