Probabilistic logging lithology characterization with random forest probability estimation

Abstract Borehole lithology discrimination is the foundation of formation evaluation and reservoir characterization. Due to the limitation of costing or accuracy, direct discrimination methods such as borehole core and drilling cutting analysis are unable to be deployed to every well, while logging lithology interpretation provides an alternative solution for this. Recently, several machine learning algorithms such as the neural network, support vector machine, decision tree, and random forest have already been employed by researchers for automatic logging lithology interpretation. However, the vast majority of these studies belong to the category of deterministic lithology characterization. In this article, we propose a probability based fuzzy characterization method for more effective logging lithology interpretation. Moreover, to improve the accuracy of lithology probability estimation, we propose the probabilistic random forest algorithm and investigate its advantages referred to 8 existing probability estimation algorithms. Through the comparative experiments on 9 real-world logging lithology interpretation tasks, the feasibility and advantage of the proposed method are confirmed. Application case demonstrates that compared with traditional deterministic lithology characterization methods, probabilistic lithology characterization is able to provide more information about rhythm, heterogeneity, and formation properties, which worths further application and promotion to improve the fineness of formation evaluation and reservoir characterization.

[1]  Mario R. Eden,et al.  Evaluating the Boosting Approach to Machine Learning for Formation Lithology Classification , 2018 .

[2]  Richard E. Neapolitan,et al.  Learning Bayesian networks , 2007, KDD '07.

[3]  Igor Kononenko,et al.  Semi-Naive Bayesian Classifier , 1991, EWSL.

[4]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[5]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[6]  A. W. Schmidt,et al.  The Litho Porosity Cross Plot: A New Concept For Determining Porosity And Lithology From Logging Methods , 1969 .

[7]  M. Rosenblatt.  Remarks on Some Nonparametric Estimates of a Density Function , 1956 .

[8]  David Bosch,et al.  Fuzzy Logic Determination of Lithologies from Well Log Data: Application to the KTB Project Data set (Germany) , 2013, Surveys in Geophysics.

[9]  Jun Li,et al.  The Identification Method of Igneous Rock Lithology Based on Data Mining Technology , 2012 .

[10]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[11]  Naonori Ueda,et al.  Generalization error of ensemble estimators , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[12]  Geoffrey I. Webb,et al.  Not So Naive Bayes: Aggregating One-Dependence Estimators , 2005, Machine Learning.

[13]  Peter Tiño,et al.  Managing Diversity in Regression Ensembles , 2005, J. Mach. Learn. Res..

[14]  Finn Verner Jensen,et al.  Introduction to Bayesian Networks , 2008, Innovations in Bayesian Networks.

[15]  Marley M. B. R. Vellasco,et al.  Neural Net Ensembles for Lithology Recognition , 2003, Multiple Classifier Systems.

[16]  Saurabh Tewari,et al.  Ensemble-based big data analytics of lithofacies for automatic development of petroleum reservoirs , 2019, Comput. Ind. Eng..

[17]  Seyyed Mohsen Salehi,et al.  Automatic Identification of Formation Iithology from Well Log Data: A Machine Learning Approach , 2014 .

[18]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[19]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[20]  Hans B. Helle,et al.  Determination of facies from well logs using modular neural networks , 2002, Petroleum Geoscience.

[21]  R. Fisher.  THE STATISTICAL UTILIZATION OF MULTIPLE MEASUREMENTS , 1938 .

[22]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[23]  Hui-Chuan Chen,et al.  Lithology determination from well logs with fuzzy associative memory neural network , 1997, IEEE Trans. Geosci. Remote. Sens..

[24]  Zhuwen Wang,et al.  A comparison of binary and multiclass support vector machine models for volcanic lithology estimation using geophysical log data from Liaohe Basin, China , 2016 .

[25]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[26]  Geoffrey I. Webb,et al.  A comparative study of Semi-naive Bayes methods in classification learning , 2005 .

[27]  Reza Ebrahimpour,et al.  Mixture of experts: a literature survey , 2014, Artificial Intelligence Review.

[28]  Bieng-Zih Hsieh,et al.  Lithology identification of aquifers from geophysical well logs and fuzzy logic analysis: Shui-Lin Area, Taiwan , 2005, Comput. Geosci..

[29]  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.

[30]  Jiang An-nan,et al.  Studying the lithology identification method from well logs based on DE-SVM , 2009, 2009 Chinese Control and Decision Conference.

[31]  Olivier Peyret,et al.  Automatic Determination of Lithology From Well Logs , 1987 .

[32]  José Reginaldo Hughes Carvalho,et al.  Ensemble of heterogeneous classifiers applied to lithofacies classification using logs from different wells , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[33]  Yujin Zhang,et al.  Application of neural networks to identify lithofacies from well logs , 1999 .

[34]  Charles L. Karr,et al.  Determination of lithology from well logs using a neural network , 1992 .

[35]  Dongmei Zhang,et al.  The Application of Improved BP Neural Network Algorithm in Lithology Recognition , 2008, ISICA.

[36]  L. N. Berry,et al.  Determination of Lithology From Well Logs by Statistical Analysis , 1987 .

[37]  L. Joseph,et al.  Bayesian Statistics: An Introduction , 1989 .

[38]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[39]  Guojian Cheng,et al.  Petroleum Lithology Discrimination Based on PSO-LSSVM Classification Model , 2010, 2010 Second International Conference on Computer Modeling and Simulation.

[40]  Arvin Agah,et al.  Collaborative multi-agent rock facies classification from wireline well log data , 2010, Eng. Appl. Artif. Intell..

[41]  Dong Liu,et al.  Lithology Identification Methods Contrast Based on Support Vector Machines at Different Well Logging Parameters Set , 2010, 2010 International Conference on Computational and Information Sciences.

[42]  Laibin Zhang,et al.  Predicting formation lithology from log data by using a neural network , 2008 .

[43]  Qingyuan Li,et al.  Quantitative evaluation methods for water-flooded layers of conglomerate reservoir based on well logging data , 2010 .

[44]  Michael Luby,et al.  Approximating Probabilistic Inference in Bayesian Belief Networks is NP-Hard , 1993, Artif. Intell..

[45]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[46]  Miguel Bosch,et al.  Lithology discrimination from physical rock properties , 2002 .

[47]  Tom Horrocks,et al.  Evaluation of Automated Lithology Classification Architectures using Highly-Sampled Wireline Logs for Coal Exploration , 2015, Comput. Geosci..

[48]  Heping Pan,et al.  Support vector machine as an alternative method for lithology classification of crystalline rocks , 2017 .

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

[50]  J. Simonoff.  Smoothing Methods in Statistics , 1998 .

[51]  Timothy R. Carr,et al.  Neural network prediction of carbonate lithofacies from well logs, Big Bow and Sand Arroyo Creek fields, Southwest Kansas , 2006, Comput. Geosci..

[52]  Sildomar T. Monteiro,et al.  Rock Recognition From MWD Data: A Comparative Study of Boosting, Neural Networks, and Fuzzy Logic , 2010, IEEE Geoscience and Remote Sensing Letters.

[53]  Patrick M. Wong,et al.  A CRITICAL COMPARISON OF NEURAL NETWORKS AND DISCRIMINANT ANALYSIS IN LITHOFACIES, POROSITY AND PERMEABILITY PREDICTIONS , 1995 .

[54]  R. Tibshirani,et al.  Discriminant Analysis by Gaussian Mixtures , 1996 .

[55]  Ben J. A. Kröse,et al.  Efficient Greedy Learning of Gaussian Mixture Models , 2003, Neural Computation.

[56]  Saumen Maiti,et al.  Neural network modelling and classification of lithofacies using well log data: A case study from KTB borehole site , 2007 .

[57]  O. Serra,et al.  Fundamentals of well-log interpretation , 1984 .

[58]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[59]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[60]  Swapan Chakrabarti,et al.  Comparison of four approaches to a rock facies classification problem , 2007, Comput. Geosci..

[61]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[62]  Marcelo Gattass,et al.  Analysis of Ensemble methods applied to Lithology Classification from Well Logs , 2013 .

[63]  G. Wadge,et al.  Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: an example from the Ocean Drilling Program , 1999 .

[64]  Wen Zhou,et al.  Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances , 2018 .

[65]  Gregory F. Cooper,et al.  The Computational Complexity of Probabilistic Inference Using Bayesian Belief Networks , 1990, Artif. Intell..