Time-series production forecasting method based on the integration of Bidirectional Gated Recurrent Unit (Bi-GRU) network and Sparrow Search Algorithm (SSA)

Abstract With the gowning demand of improving quality and benefit of unconventional resources, time-series production prediction plays an increasingly essential role in economic investment, stimulation scale and decision making. However, due to the limitations of traditional model-driven methods and data-driven methods, production forecasting is still challenging. In this paper, we propose a novel framework using Bidirectional Gated Recurrent Unit (Bi-GRU) and Sparrow Search Algorithm (SSA) that improves the accuracy of oil rate forecasting. The Bi-GRU could make full use of both past and future information inside production sequences and related features. SSA is employed for hyperparameter tuning of the Bi-GRU model. To validate the feasibility, robustness and efficiency of the proposed method, three cases are carried out from the perspective of an ideal single well from the simulation model, an actual single well under variable production constraints and actual multiple wells. Model performance is compared with traditional decline curve analysis, conventional time series methods and one-way recurrent neural networks. The observations show that the proposed method performs better than the others in terms of accuracy and robustness.

[1]  Fengchao Xiao,et al.  Application of Gated Recurrent Unit (GRU) Neural Network for Smart Batch Production Prediction , 2020 .

[2]  Siddhartha Gupta,et al.  Production Forecasting in Unconventional Resources using Data Mining and Time Series Analysis , 2014 .

[3]  Roland N. Horne,et al.  Deep Learning for Well Data History Analysis , 2019, Day 1 Mon, September 30, 2019.

[4]  Junqiang Wang,et al.  Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model , 2020 .

[5]  Lining Sun,et al.  Rapid Prediction of Respiratory Motion Based on Bidirectional Gated Recurrent Unit Network , 2020, IEEE Access.

[6]  Alan Wee-Chung Liew,et al.  A Novel Improved Particle Swarm Optimization With Long-Short Term Memory Hybrid Model for Stock Indices Forecast , 2021, IEEE Access.

[7]  Yulei Wu,et al.  Attention-based bidirectional GRU networks for efficient HTTPS traffic classification , 2020, Inf. Sci..

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  Torsten Clemens,et al.  Impact of Digitalization on the Way of Working and Skills Development in Hydrocarbon Production Forecasting and Project Decision Analysis , 2020 .

[10]  Bo Shen,et al.  A novel swarm intelligence optimization approach: sparrow search algorithm , 2020 .

[11]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[12]  Xiaolei Liu,et al.  Wind power forecasting – A data-driven method along with gated recurrent neural network , 2021 .

[13]  Aneela Zameer,et al.  Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM , 2020, Chaos, Solitons & Fractals.

[14]  Skipper Seabold,et al.  Statsmodels: Econometric and Statistical Modeling with Python , 2010, SciPy.

[15]  Dan Wang,et al.  Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting , 2019, International Journal of Electrical Power & Energy Systems.

[16]  Jianwei Gu,et al.  Forecasting oil production using ensemble empirical model decomposition based Long Short-Term Memory neural network , 2020, Journal of Petroleum Science and Engineering.

[17]  Bo Liu,et al.  Renewable energy systems optimization by a new multi-objective optimization technique: A residential building , 2020 .

[18]  Gabrial Anandarajah,et al.  Parameter determination for a numerical approach to undeveloped shale gas production estimation: The UK Bowland shale region application , 2018, Journal of Natural Gas Science and Engineering.

[19]  Christopher R. Clarkson,et al.  Production data analysis of unconventional gas wells: Review of theory and best practices , 2013 .

[20]  Abdulaziz Alqasim,et al.  Comparison Study of Asphaltene Precipitation Models Using UTCOMP, CMG/GEM and ECLIPSE Simulators , 2017 .

[21]  Ali Ouni,et al.  Multi-Sequence LSTM-RNN Deep Learning and Metaheuristics for Electric Load Forecasting , 2020, Energies.

[22]  Wenhu Tang,et al.  Wind power forecasting using attention-based gated recurrent unit network , 2020 .

[23]  K. Sepehrnoori,et al.  A Fast EDFM Method for Production Simulation of Complex Fractures in Naturally Fractured Reservoirs , 2018, Day 4 Wed, October 10, 2018.

[24]  Marek Lóderer,et al.  Improving Time Series Prediction via Modification of Dynamic Weighted Majority in Ensemble Learning , 2018, IDEAL.

[25]  J. J. Arps.  Analysis of Decline Curves , 1945 .

[26]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[27]  Nashat T. AL-Jallad,et al.  Short-Term Forecasting for Energy Consumption through Stacking Heterogeneous Ensemble Learning Model , 2018, Energies.

[28]  Zhu Rukai,et al.  Progress, challenges and key issues of unconventional oil and gas development of CNPC , 2020 .

[29]  Lin Lin,et al.  Random forests-based extreme learning machine ensemble for multi-regime time series prediction , 2017, Expert Syst. Appl..

[30]  Taesam Lee,et al.  Deep Learning-Based Maximum Temperature Forecasting Assisted with Meta-Learning for Hyperparameter Optimization , 2020 .

[31]  Kyungbook Lee,et al.  Prediction of Shale-Gas Production at Duvernay Formation Using Deep-Learning Algorithm , 2019, SPE Journal.

[32]  Patrick Keatley,et al.  Energy Storage on a Distribution Network for Self-Consumption of Wind Energy and Market Value , 2020, Energies.

[33]  L. Mattar,et al.  A Systematic and Comprehensive Methodology for Advanced Analysis of Production Data , 2003 .

[34]  Jianhua Z. Huang,et al.  Data-Driven End-To-End Production Prediction of Oil Reservoirs by EnKF-Enhanced Recurrent Neural Networks , 2020 .

[35]  Sara Bouraine,et al.  Particle swarm optimization for solving a scan-matching problem based on the normal distributions transform , 2021, Evolutionary Intelligence.

[36]  Zhiwei He,et al.  An Improved Bidirectional Gated Recurrent Unit Method for Accurate State-of-Charge Estimation , 2021, IEEE Access.

[37]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[38]  Nadeem Javaid,et al.  A survey on hyperparameters optimization algorithms of forecasting models in smart grid , 2020 .

[39]  Hamzeh Alimohammadi,et al.  Multivariate Time Series Modelling Approach for Production Forecasting in Unconventional Resources , 2020 .

[40]  Oluwafemi Olominu,et al.  Application of Time Series Analysis to Predict Reservoir Production Performance , 2014 .

[41]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[42]  J. Sun,et al.  Comparison of Decline Curve Analysis DCA with Recursive Neural Networks RNN for Production Forecast of Multiple Wells , 2018 .

[43]  Shan Huang,et al.  Analytical model for production performance analysis of multi-fractured horizontal well in tight oil reservoirs , 2017 .

[44]  Reza Rezaee,et al.  Production performance of hydraulic fractures in tight gas sands, a numerical simulation approach , 2012 .

[45]  Jun Wang,et al.  Energy market prediction with novel long short-term memory network: Case study of energy futures index volatility , 2020 .

[46]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[47]  Benjamin Badami,et al.  Optimal brain tumor diagnosis based on deep learning and balanced sparrow search algorithm , 2021, Int. J. Imaging Syst. Technol..

[48]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[49]  A. Kostinski,et al.  Is Contact Nucleation Caused by Pressure Perturbation? , 2019, Atmosphere.