Application of the long short-term memory networks for well-testing data interpretation in tight reservoirs

Abstract Conventional interpretation of the well-testing data cannot effectively detect the real formation response from the noise to characterize the reservoir. Machine learning techniques provide a new data interpretation approach to discover the relationships between production rates and pressure responses of the well. In this study, the long short-term memory networks (LSTMNs) are explored to analyze the field permanent downhole gauge (PDG) data for better reservoir characterization and modelling. Unlike the conventional recurrent neural networks (RNNs), LSTMNs are designed to learn the long-term dependencies among the sequential data sets. More specifically, an approximate analytical model is firstly proposed to describe the flow rate and pressure behavior in a tight reservoir with natural fractures. The synthetic flow rate and pressure data with noise generated by the analytical model are then used to train the LSTMNs. Prediction accuracy of the LSTMNs is first validated by using the field data sets collected from Montney Formation, and their applicability for reservoirs with different types of boundaries are tested by the synthetic flow rate and pressure data sets generated from the analytical models. The field cases have proved that this data mining technique is able to capture the well shut-in operations in Montney liquid-rich tight reservoirs, where the well bottomhole pressure can be accurately predicted when feeding the model with both gas rate and condensate rate. In addition, the LSTMNs are able to learn the pressure behavior from the noisy data sets and do not require a denoising procedure when predicting the pressure response for a given flow rate. In summary, this work first uses the LSTMNs to interpret well-testing data in naturally fractured tight reservoirs. The LSTMNs not only shows a great tolerance to the noise of datasets, but also can capture the pressure responses characterized by well shut-in, boundary effects, and stress-sensitive fractures. It is proved that this data-driven model can discover the patterns and relationships between the flow rate and pressure through the data mining process, while not requiring the prior knowledge of physical model or mathematical assumptions.

[1]  Roland N. Horne,et al.  Recurrent Neural Networks for Permanent Downhole Gauge Data Analysis , 2017 .

[2]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[3]  Hassan Hassanzadeh,et al.  Shape factor in the drawdown solution for well testing of dual-porosity systems , 2009 .

[4]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

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

[6]  Jitendra Kikani,et al.  Perturbation Analysis of Stress-Sensitive Reservoirs (includes associated papers 25281 and 25292 ) , 1991 .

[7]  Shengnan Chen,et al.  Approximate Analytical-Pressure Studies on Dual-Porosity Reservoirs With Stress-Sensitive Permeability , 2015 .

[8]  H. Kazemi,et al.  NUMERICAL SIMULATION OF WATER-OIL FLOW IN NATURALLY FRACTURED RESERVOIRS , 1976 .

[9]  G. I. Barenblatt,et al.  Basic concepts in the theory of seepage of homogeneous liquids in fissured rocks [strata] , 1960 .

[10]  Iraj Ershaghi,et al.  A Robust Neural Network Model for Pattern Recognition of Pressure Transient Test Data , 1993 .

[11]  Alaa El. Sagheer,et al.  Time series forecasting of petroleum production using deep LSTM recurrent networks , 2019, Neurocomputing.

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

[13]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[14]  Iraj Ershaghi,et al.  Complexities of Using Neural Network in Well Test Analysis of Faulted Reservoirs , 1993 .

[15]  J. E. Warren,et al.  The Behavior of Naturally Fractured Reservoirs , 1963 .

[16]  Roland N. Horne,et al.  Interpreting Pressure and Flow-Rate Data From Permanent Downhole Gauges by Use of Data-Mining Approaches , 2013 .

[17]  Humberto L. Najurieta,et al.  A Theory for Pressure Transient Analysis in Naturally Fractured Reservoirs , 1980 .

[18]  T. Nanba.  Numerical Simulation of Pressure Transients in Naturally Fractured Reservoirs With Unsteady-State Matrix-to-Fracture Flow , 1991 .

[19]  Iraj Ershaghi,et al.  A New Approach to Reservoir Characterization Using Deep Learning Neural Networks , 2016 .

[20]  O. A. Pedrosa.  Pressure Transient Response in Stress-Sensitive Formations , 1986 .

[22]  Walter K. Sawyer,et al.  Transient Flow In Naturally Fractured Reservoirs And Its Application To Devonian Gas Shales , 1980 .

[23]  A. U. Al-Kaabi,et al.  Author's reply to discussion of using artificial neural nets to identify the well-test interpretation model , 1993 .

[24]  Roland N. Horne,et al.  Applying Machine-Learning Techniques To Interpret Flow-Rate, Pressure, and Temperature Data From Permanent Downhole Gauges , 2019, SPE Reservoir Evaluation & Engineering.

[25]  Norbert Jankowski,et al.  Survey of Neural Transfer Functions , 1999 .

[26]  Jing Peng,et al.  An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories , 1990, Neural Computation.

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