Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model

Abstract Oil production forecasting is one of the most critical issues during the exploitation phase of the oilfield. The limitations of traditional approaches make time-series production prediction still challenging. With the development of artificial intelligence, high-performance algorithms make reliable production prediction possible from the data perspective. This study proposes a Long Short-Term Memory (LSTM) neural network based model to infer the production of fractured horizontal wells in a volcanic reservoir, which addresses the limitations of traditional method and shows accurate predictions. The LSTM neural network enables to capture the dependencies of the oil rate time sequence data and incorporate the production constraints. Particle Swarm Optimization algorithm (PSO) is employed to optimize the essential configuration of the LSTM model. For evaluation purpose, two case studies are carried out with the production dynamics from synthetic model and from the Xinjiang oilfield, China. Towards a fair evaluation, the performance of the proposed approach is compared with traditional neural networks, time-series forecasting approaches, and conventional decline curves. The experiment results show that the proposed LSTM model outperforms other approaches.

[1]  T. Niknam.  An Approach Based on Particle Swarm Optimization for Optimal Operation of Distribution Network Considering Distributed Generators , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[2]  Yan-Yan Wang,et al.  A new mathematical model for horizontal wells with variable density perforation completion in bottom water reservoirs , 2017, Petroleum Science.

[3]  Dongxiao Zhang,et al.  Synthetic well logs generation via Recurrent Neural Networks , 2018, Petroleum Exploration and Development.

[4]  Ji Li,et al.  Data Driven Production Forecasting Using Machine Learning , 2016 .

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

[6]  Taher Niknam,et al.  An Efficient Hybrid Evolutionary Algorithm for Cluster Analysis , 2008 .

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

[8]  Xingru Wu,et al.  A numerical simulation study of CO2 injection for enhancing hydrocarbon recovery and sequestration in liquid-rich shales , 2018, Petroleum Science.

[9]  Taher Niknam,et al.  A new fuzzy adaptive hybrid particle swarm optimization algorithm for non-linear, non-smooth and non-convex economic dispatch problem , 2010 .

[10]  Zhangxin Chen,et al.  Performance forecasting for polymer flooding in heavy oil reservoirs , 2018 .

[11]  Lei Zhang,et al.  Hybrid forecasting model based on long short term memory network and deep learning neural network for wind signal , 2019, Applied Energy.

[12]  M. Ye,et al.  Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas , 2018, Journal of Hydrology.

[13]  Ming Zhong,et al.  A Data-Analytics Tutorial: Building Predictive Models for Oil Production in an Unconventional Shale Reservoir , 2018 .

[14]  Palash Panja,et al.  Application of artificial intelligence to forecast hydrocarbon production from shales , 2017 .

[15]  Farhad Qanbari,et al.  A semi-analytical method for forecasting wells completed in low permeability, undersaturated CBM reservoirs , 2015 .

[16]  Bing Han,et al.  A hybrid PSO-SVM-based model for determination of oil recovery factor in the low-permeability reservoir , 2017 .

[17]  Yu-long Zhao,et al.  A simulator for production prediction of multistage fractured horizontal well in shale gas reservoir considering complex fracture geometry , 2019, Journal of Natural Gas Science and Engineering.

[18]  Ming Zhong,et al.  Do Data Mining Methods Matter?: A Wolfcamp Shale Case Study , 2015 .

[19]  Kung-Sik Chan,et al.  Time Series Analysis: With Applications in R , 2010 .

[20]  Amin Shokrollahi,et al.  Evolving artificial neural network and imperialist competitive algorithm for prediction oil flow rate of the reservoir , 2013, Appl. Soft Comput..

[21]  José David Martín-Guerrero,et al.  Predicting service request in support centers based on nonlinear dynamics, ARMA modeling and neural networks , 2008, Expert Syst. Appl..

[22]  Li Li,et al.  Mid-to-long term wind and photovoltaic power generation prediction based on copula function and long short term memory network , 2019, Applied Energy.

[23]  Christine Ehlig-Economides,et al.  Production Optimization Using Machine Learning in Bakken Shale , 2018 .

[24]  Lixin Li,et al.  Deep learning PM2.5 concentrations with bidirectional LSTM RNN , 2019, Air Quality, Atmosphere & Health.

[25]  Taher Niknam,et al.  An efficient hybrid evolutionary optimization algorithm based on PSO and SA for clustering , 2009 .

[26]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[27]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[28]  Shuhua Wang,et al.  Insights to fracture stimulation design in unconventional reservoirs based on machine learning modeling , 2019, Journal of Petroleum Science and Engineering.

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD 2000.

[31]  Han Cao,et al.  Prediction for Tourism Flow based on LSTM Neural Network , 2017, IIKI.

[32]  David S. Fulford,et al.  Machine Learning as a Reliable Technology for Evaluating Time/Rate Performance of Unconventional Wells , 2015 .

[33]  K. Mohammadi,et al.  Comparison of regression, ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent (a case study of Karaj). , 2005 .

[34]  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.

[35]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

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

[37]  Zwe-Lee Gaing,et al.  A particle swarm optimization approach for optimum design of PID controller in AVR system , 2004 .

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

[39]  Christopher R. Clarkson,et al.  History-matching and forecasting tight/shale gas condensate wells using combined analytical, semi-analytical, and empirical methods , 2014 .