Permeability prediction using hybrid techniques of continuous restricted Boltzmann machine, particle swarm optimization and support vector regression

Abstract How to obtain reliable permeability data is universally considered as one of the critical work that guides geologists to explore oil-gas accumulation zones underground. Many significant researches related to permeability prediction have revealed that permeability can be directly calculated from logging data under usage of some complex non-linear equations. In this way, the key of permeability prediction is how to establish relational expression between permeability and logging data. Support vector regression is one of the best mathematical models using to explain complex mapping relationship between independent and dependent variables, and thus it can be viewed as an ideal approach to predict permeability. However, such model cannot be effective when different kinds of input data have high correlation or network parameters are not evaluated well. Then other two mathematical models, continuous restricted Boltzmann machine and particle swarm optimization, are referred to use to support the application of SVR. CRBM is functional to make a new data separation from the raw data, and network parameters can be optimized after PSO process. Therefore a new data-driven permeability prediction model CRBM-PSO-SVR is provided in this article. Data source used for method validation derives from five coring wells of the IARA oilfield, Santos Basin, Brazil. In two self-designed experiments, the accuracy rates of new method are respectively 67.34% and 76.67%, both of which are higher than those of other comparison methods. Experiment results well demonstrate the effectiveness of new method in permeability prediction when only logging data is available.

[1]  Walter Rose,et al.  Some Theoretical Considerations Related To The Quantitative Evaluation Of The Physical Characteristics Of Reservoir Rock From Electrical Log Data , 1950 .

[2]  Zhenhua Rui,et al.  Assessing the combined influence of fluid-rock interactions on reservoir properties and injectivity during CO2 storage in saline aquifers , 2018, Energy.

[3]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[4]  A. Timur,et al.  An Investigation Of Permeability, Porosity, & Residual Water Saturation Relationships For Sandstone Reservoirs , 1968 .

[5]  Lawrence W. Martz,et al.  Numerical definition of drainage network and subcatchment areas from digital elevation models , 1992 .

[6]  Kholoud Ghareeb Al-Nayadi,et al.  Water Saturation from NMR, Resistivity and Oil Base Core in a Heterogeneous Middle East Carbonate Reservoir , 2006 .

[7]  R. Vanderbei.  LOQO:an interior point code for quadratic programming , 1999 .

[8]  I. D. Gates,et al.  Support vector regression to predict porosity and permeability: Effect of sample size , 2012, Comput. Geosci..

[9]  Nii O. Attoh-Okine,et al.  Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance , 1999 .

[10]  George V. Chilingar,et al.  Relationship Between Porosity, Permeability, and Grain-Size Distribution of Sands and Sandstones , 1964 .

[11]  Cong Lu,et al.  Numerical investigation of hydraulic fracture propagation in a layered reservoir using the cohesive zone method , 2017 .

[12]  Teik C. Lim,et al.  Evaluation of vehicle interior sound quality using a continuous restricted Boltzmann machine-based DBN , 2017 .

[13]  Nikolai S. Rubanov.  The layer-wise method and the backpropagation hybrid approach to learning a feedforward neural network , 2000, IEEE Trans. Neural Networks Learn. Syst..

[14]  Hua Wang,et al.  The porosity and permeability prediction methods for carbonate reservoirs with extremely limited logging data: Stepwise regression vs. N-way analysis of variance , 2017 .

[15]  Andreas Christmann,et al.  Bouligand Derivatives and Robustness of Support Vector Machines for Regression , 2007, J. Mach. Learn. Res..

[16]  Ioan Cristian Trelea,et al.  The particle swarm optimization algorithm: convergence analysis and parameter selection , 2003, Inf. Process. Lett..

[17]  Tayfun Babadagli,et al.  A Review of Permeability-Prediction Methods for Carbonate Reservoirs Using Well-Log Data , 2004 .

[18]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[19]  G. R. Pickett,et al.  A Review of Current Techniques for Determination of Water Saturation From Logs , 1966 .

[20]  Zhenhua Rui,et al.  Influence of gravel on the propagation pattern of hydraulic fracture in the glutenite reservoir , 2018, Journal of Petroleum Science and Engineering.

[21]  R. Khanna,et al.  Support Vector Regression , 2015 .

[22]  Yuhui Shi,et al.  Particle swarm optimization: developments, applications and resources , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[23]  Tom Manzocchi,et al.  Faults in conventional flow simulation models: a consideration of representational assumptions and geological uncertainties , 2008, Petroleum Geoscience.

[24]  Ian D. Gates,et al.  A support vector machine algorithm to classify lithofacies and model permeability in heterogeneous reservoirs , 2010 .

[25]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[26]  Alan F. Murray,et al.  Continuous restricted Boltzmann machine with an implementable training algorithm , 2003 .

[27]  Timothy S. Collett,et al.  A review of well-log analysis techniques used to assess gas-hydrate-bearing reservoirs , 2013 .

[28]  Chi-Jie Lu.  Hybridizing nonlinear independent component analysis and support vector regression with particle swarm optimization for stock index forecasting , 2012, Neural Computing and Applications.

[29]  S. Bryant,et al.  Permeability Prediction from Geologic Models , 1993 .

[30]  Zehui Huang,et al.  Permeability prediction with artificial neural network modeling in the Venture gas field, offshore eastern Canada , 1996 .

[31]  Hossein Memarian,et al.  Uncertainty assessment of porosity and permeability by clustering algorithm and fuzzy arithmetic , 2018 .

[32]  Jinfeng Yi,et al.  Efficient distance metric learning by adaptive sampling and mini-batch stochastic gradient descent (SGD) , 2013, Machine Learning.

[33]  Charles Flaum,et al.  Wettability, Saturation, and Viscosity From NMR Measurements , 2003 .

[34]  G C Borgia,et al.  Estimates of permeability and irreducible water saturation by means of a new robust computation of fractional power average relaxation times. , 1998, Magnetic resonance imaging.

[35]  A. E. Omar.  Effect of brine composition and clay content on the permeability damage of sandstone cores , 1990 .

[36]  Peter S. Mozley,et al.  The effect of carbonate cementation on permeability heterogeneity in fluvial aquifers: An outcrop analog study , 2006 .

[37]  Chanh Cao Minh,et al.  Predicting Effective Permeability to Oil in Sandstone and Carbonate Reservoirs From Well-Logging Data , 2011 .

[38]  Ali Elkamel,et al.  Reservoir permeability prediction by neural networks combined with hybrid genetic algorithm and particle swarm optimization , 2013 .

[39]  Mark D. Zoback,et al.  Experimental investigation of matrix permeability of gas shales , 2014 .

[40]  Jianchun Guo,et al.  Composite linear flow model for multi-fractured horizontal wells in heterogeneous shale reservoir , 2017 .

[41]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[42]  Kinji Magara,et al.  ESTIMATION OF IRREDUCIBLE WATER SATURATION AND EFFECTIVE PORE SIZE OF MUDSTONES , 1982 .

[43]  G. Eberli,et al.  The Velocity-Deviation Log: A Tool to Predict Pore Type and Permeability Trends in Carbonate Drill Holes from Sonic and Porosity or Density Logs , 1999 .

[44]  Hanqiao Jiang,et al.  Optimization of well placement by combination of a modified particle swarm optimization algorithm and quality map method , 2014, Computational Geosciences.

[45]  Razvan Pascanu,et al.  Learning Algorithms for the Classification Restricted Boltzmann Machine , 2012, J. Mach. Learn. Res..

[46]  Li-Rong Dai,et al.  Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[47]  Chun-Xia Zhang,et al.  Learning ensemble classifiers via restricted Boltzmann machines , 2014, Pattern Recognit. Lett..

[48]  Zhiyuan Ge,et al.  Salt-structural styles and kinematic evolution of the Jequitinhonha deepwater fold belt, central Brazil passive margin , 2012 .

[49]  Christoph Clauser,et al.  Permeability prediction based on fractal pore‐space geometry , 1999 .

[50]  M. Hall,et al.  Lacustrine carbonate reservoirs from Early Cretaceous rift lakes of Western Gondwana: Pre-Salt coquinas of Brazil and West Africa , 2015 .

[51]  Samy Bengio,et al.  SVMTorch: Support Vector Machines for Large-Scale Regression Problems , 2001, J. Mach. Learn. Res..

[52]  Paul W. J. Glover,et al.  Permeability prediction from MICP and NMR data using an electrokinetic approach , 2006 .

[53]  Shashi Mathur,et al.  Optimal design of an in-situ bioremediation system using support vector machine and particle swarm optimization. , 2013, Journal of contaminant hydrology.

[54]  Xiaoqing Wang,et al.  A quantitative framework for evaluating unconventional well development , 2018, Journal of Petroleum Science and Engineering.

[55]  S. Cuddy,et al.  Litho-Facies and Permeability Prediction from Electrical Logs using Fuzzy Logic , 2000 .

[56]  Gang Chen,et al.  A realistic and integrated model for evaluating oil sands development with Steam Assisted Gravity Drainage technology in Canada , 2018 .

[57]  Kwok-wing Chau,et al.  Data-driven input variable selection for rainfall-runoff modeling using binary-coded particle swarm optimization and Extreme Learning Machines , 2015 .