Lithofacies Classification From Well Log Data Using Neural Networks, Interval Neutrosophic Sets And Quantification Of Uncertainty

This paper proposes a novel approach to the question of lithofacies classification based on an assessment of the uncertainty in the classification results. The proposed approach has multiple neural networks (NN), and interval neutrosophic sets (INS) are used to classify the input well log data into outputs of multiple classes of lithofacies. A pair of n-class neural networks are used to predict n-degree of truth memberships and n-degree of false memberships. Indeterminacy memberships or uncertainties in the predictions are estimated using a multidimensional interpolation method. These three memberships form the INS used to support the confidence in results of multiclass classification. Based on the experimental data, our approach improves the classification performance as compared to an existing technique applied only to the truth membership. In addition, our approach has the capability to provide a measure of uncertainty in the problem of multiclass classification.
{"references":["P. Smets, Uncertainty Management in Information Systems: From Needs\nto Solutions. Kluwer Academic Publishers, 1997, ch. Imperfect\ninformation: Imprecision-Uncertainty, pp. 225-254.","M. Duckham, \"Uncertainty and geographic information: Computational\nand critical convergence,\" in Representation in a Digital Geography.\nNew York: John Wiley, 2002.","P. F. Fisher, Geographical Information Systems: Principles, Techniques,\nManagement and Applications, 2nd ed. Chichester: John Wiley, 2005,\nvol. 1, ch. Models of uncertainty in spatial data, pp. 69-83.","C. C. Fung, K. W. Wong, and H. Eren, \"Modular Artificial Neural\nNetwork for Prediction of Petrophysical Properties From Well Log\nData,\" in IEEE Transactions on Instrumentation and Measurement,\nvol. 46, no. 6, 1997, pp. 1259-1263.","H. Crocker, C. C. Fung, and K. W. Wong, \"The STAG Oilfield Formation\nEvaluation: A Neural Network Approach,\" Australian Petroleum Production\nand Exploration Association APPEA99 Journal, vol. 39, part1, pp.\n451-460, 1999.","K. W. Wong and T. D. Gedeon, \"Fuzzy Rule Interpolation for Multidimensional\nInput Space with Petroleum Engineering Application,\"\nin Proceedings of Joint 9th IFSA World Congress and 20th NAFIPS\nInternational Conference, Vancouver, Canada, July 2001, pp. 2470-\n2475.","K. W. Wong, Y. S. Ong, T. D. Gedeon, and C. C. Fung, \"Reservoir\nCharacterization Using Support Vector Machines,\" in Proceedings of\nthe 2005 International Conference on Computational Intelligence for\nModelling, Control and Automation, vol. 2, November 2005, pp. 354-\n359.","G. Ou, Y. L. Murphey, and L. A. Feldkamp, \"Multiclass Pattern Classification\nUsing Neural Networks,\" in Proceeding of the 17th International\nConference on Pattern Recognition (ICPR), 2004, pp. 585-588.","H. Wang, D. Madiraju, Y.-Q. Zhang, and R. Sunderraman, \"Interval\nneutrosophic sets,\" International Journal of Applied Mathematics and\nStatistics, vol. 3, pp. 1-18, March 2005.\n[10] R. Erenshteyn, P. Laskov, D. M. Saxe, and R. A. Foulds, \"Distributed\nOutput Encoding for Multi-Class Pattern Recognition,\" in Proceeding\nof the 10th International Conference on Image Analysis and Processing\n(ICIAP), 1999, pp. 229-234.\n[11] T. G. Dietterich and G. Bakiri, \"Solving Multiclass Learning Problems\nvia Error-Correcting Output Codes,\" Journal of Artificial Intelligence\nResearch, vol. 2, pp. 263-286, 1995.\n[12] K. Crammer and Y. Singer, \"On the Learnability and Design of Output\nCodes for Multiclass Problems,\" Machine Learning, vol. 47, no. 2-3,\npp. 201-233, 2002.\n[13] P. Kraipeerapun, C. C. Fung, and W. Brown, \"Assessment of Uncertainty\nin Mineral Prospectivity Prediction Using Interval Neutrosophic\nSet,\" in Proceedings of the International Conference on Computational\nIntelligence and Security, ser. Lecture Notes in Artificial Intelligence,\nno. 3802. Xi-an, China: Springer Verlag, 2005, pp. 1074-1079.\n[14] P. Kraipeerapun, C. C. Fung, W. Brown, and K. W. Wong, \"Mineral\nProspectivity Prediction using Interval Neutrosophic Sets,\" in IASTED\nInternational Conference on Artificial Intelligence and Applications,\nInnsbruck, Austria, February 2006, pp. 235-239.\n[15] H. Wang, F. Smarandache, Y.-Q. Zhang, and R. Sunderraman, Interval\nNeutrosophic Sets and Logic: Theory and Applications in Computing,\nser. Neutrosophic Book Series, No.5. http://arxiv.org/abs/cs/0505014,\nMay 2005."]}