Robotized petrophysics: Machine learning and thermal profiling for automated mapping of lithotypes in unconventionals

Abstract We present a method for predicting rock types. The method is based on continuous high-resolution thermal logging along full-size core samples and being applied for rocks from a major unconventional formation. The method utilizes spatial spectral decomposition and machine learning approaches allowing automatic classification of the core samples over lithological groups within an isolated stratigraphic depth interval of a wellbore. The core samples are basically classified to the particular lithotypes by means of spectral representation of profiles of thermal properties obtained by a modern contactless method.

[1]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[2]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[3]  Baouche Rafik Baouche Rafik,et al.  Prediction of permeability and porosity from well log data using the nonparametric regression with multivariate analysis and neural network, Hassi R’Mel Field, Algeria , 2017 .

[4]  Vikram Jayaram,et al.  Active Learning Algorithms in Seismic Facies Classification , 2013 .

[5]  I. D. Gates,et al.  On the Capability of Support Vector Machines to Classify Lithology from Well Logs , 2010 .

[6]  Mohammad Ali Sebtosheikh,et al.  Support vector machine method, a new technique for lithology prediction in an Iranian heterogeneous carbonate reservoir using petrophysical well logs , 2015, Carbonates and Evaporites.

[7]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[8]  Jane Labadin,et al.  Ensemble machine learning: An untapped modeling paradigm for petroleum reservoir characterization , 2017 .

[9]  G. Beardsmore,et al.  ISRM Suggested Methods for Determining Thermal Properties of Rocks from Laboratory Tests at Atmospheric Pressure , 2016, Rock Mechanics and Rock Engineering.

[10]  H. Tang,et al.  Improved Carbonate Reservoir Facies Classification Using Artificial Neural Network Method , 2008 .

[11]  Application of nearest neighbour method for sedimentation environment study , 2015 .

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

[13]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[14]  Larry W. Lake,et al.  Seismic Facies Identification and Classification Using Simple Statistics , 2008 .

[15]  Vikram Jayaram,et al.  Lithofacies classification in Barnett Shale using proximal support vector machines , 2014 .

[16]  D. Grana,et al.  Petro-Elastic Facies Classification in the Marcellus Shale by Applying Expectation Maximization to Measured Well Logs , 2014 .