Assessing the Impact of Expert Labelling of Training Data on the Quality of Automatic Classification of Lithological Groups Using Artificial Neural Networks

[1] NAC Kazatomprom JSC, “Kazatomprom,” 2020. [Online]. Available: https://www.kazatomprom.kz/en [Accessed: Mar. 02, 2020].Search in Google Scholar

[2] GRK LLP, “Technical instruction for geophysical survey in wells at reservoir infiltration deposits of uranium,” unpublished.Search in Google Scholar

[3] E. N. Amirgaliev, S. Kh. Iskakov, Ya. I. Kuchin, and R. I. Muhamediev, “Machine learning methods for rock recognition problems in uranium deposits,” in Proc. of the National Academy of Sciences of Kazakhstan 3, 2013, pp. 82–88.Search in Google Scholar

[4] N. Giang, et al. “Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey,” Artificial Intelligence Review 52.1, pp. 77–124, 2019. https://doi.org/10.1007/s10462-018-09679-z10.1007/s10462-018-09679-zSearch in Google Scholar

[5] R. Muhamedyev, “Machine learning methods: An overview,” CMNT 19, no. 6, pp. 14–29, 2015.Search in Google Scholar

[6] M. van der Baan, et al. “Neural networks in geophysical applications,” Geophysics 65(4), pp. 1032–1047, 2000. https://doi.org/10.1190/1.144479710.1190/1.1444797Search in Google Scholar

[7] J. L. Baldwin, R. M. Bateman, and C. L. Wheatley, “Application of a neural network to the problem of mineral identification from well logs,” The Log Analyst, vol. 3, pp. 279–293, 1990.Search in Google Scholar

[8] B. Benaouda, G. Wadge, R. B. Whitmarsh, R. G. Rothwell, and C. MacLeod, “Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs - an example from the Ocean Drilling Program.” Geophysical Journal International, vol. 136, no. 2, pp. 477–491, 1999. https://doi.org/10.1046/j.1365-246X.1999.00746.x10.1046/j.1365-246X.1999.00746.xSearch in Google Scholar

[9] M. M. Saggaf, and Ed. L. Nebrija, “Estimation of missing logs by regularized neural networks.” AAPG Bulletin, vol. 87, no. 8, pp. 1377–1389, 2003. https://doi.org/10.1306/0311030103010.1306/03110301030Search in Google Scholar

[10] V. A. Tenenev, B. A. Yakimovich, M. A. Senilov, and N. B. Paklin, “Intellectual systems for interpretation of well logging,” Shtnyi intelekt vol. 3, p. 338, 2002.Search in Google Scholar

[11] Y. Klaus, and T. Sven, “Computational Neural Networks for Geophysical Data Processing,” Elsevier Science, 2001.Search in Google Scholar

[12] M. Borsaru, B. Zhou, T. Aizawa, H. Karashima, and T. Hashimoto, “Automated lithology prediction from PGNAA and other geophysical logs,” Applied Radiation and Isotopes, vol. 64, no. 2, pp. 272–282, 2006. https://doi.org/10.1016/j.apradiso.2005.07.01210.1016/j.apradiso.2005.07.01216140021Search in Google Scholar

[13] S. J. Rogers, H. C. Chen, D. C. Kopaska-Merkel, and J. H. Fang, “Predicting permeability from porosity using artificial neural networks,” AAPG Bulletin, vol. 12, no. 12, pp. 1786–1797, 1995. https://doi.org/10.1306/7834DEFE-1721-11D7-8645000102C1865D10.1306/7834DEFE-1721-11D7-8645000102C1865DSearch in Google Scholar

[14] L. Kapur, L. Lake, K. Sepehrnoori, D. Herrick, and C. Kalkomey, “Facies prediction from core and log data using artificial neural network technology,” in 39th Society of Professional Well Log Analysts Annual Logging Symposium, 1998.Search in Google Scholar

[15] S. P. Aleshin, A. L. Lyakhov, “Neural network assessment of the mineral resource base of a region according to geophysical monitoring data,” New technologies, vol. 1, no. 31, pp. 39–43, 2001.Search in Google Scholar

[16] S. J. Rogers, J. H. Fang, C. L. Karr, D. A. Stanley, “Determination of lithology from well logs using a neural network,” AAPG Bulletin, vol. 76, no. 5, pp. 731–739, 1992. https://doi.org/10.1306/BDFF88BC-1718-11D7-8645000102C1865D10.1306/BDFF88BC-1718-11D7-8645000102C1865DSearch in Google Scholar

[17] D. V. Kostikov, “Instrumental tools for interpretation of well logging based on converted logging data using a multilayer neural network,” Ph.D. dissertation, p. 189, 2007.Search in Google Scholar

[18] R. Muhamediyev, E. Amirgaliev, S. Iskakov, Y. Kuchin, and E. Muhamedyeva, “Integration of Results of Recognition Algorithms at the Uranium Deposits,” Journal of ACIII, vol. 18, no. 3, pp. 347–352, 2014.Search in Google Scholar

[19] E. N. Amirgaliev, S. Kh. Iskakov, Ya. I. Kuchin, and R. I. Muhamediev, “Integration of recognition algorithms of lithological types,” Informatics problems. Siberian Branch of the Russian Academy of Sciences vol. 4, no. 21, pp. 11–20, 2013.Search in Google Scholar

[20] E. N. Amirgaliev, S. Kh. Iskakov, Ya. I. Kuchin, R. I. Muhamediev, “Machine learning methods for rock recognition problems in uranium deposits,” in Proc. of the National Academy of Sciences of Kazakhstan 3, 2013, pp. 82–88.Search in Google Scholar

[21] “Development of methods of data boreholes interpretation by using artificial neural network (On request of Geotehnoserviss ltd),” unpublished.Search in Google Scholar

[22] Y. I. Kuchin, R. I. Muhamedyev, E. L. Muhamedyeva, P. Gricenko, Zh. Nurushev, and K. Yakunin, “The analysis of the data of geophysical research of boreholes by means of artificial neural networks,” Computer Modelling and New Technologies, vol. 15, no. 4, pp. 35–40, 2011.Search in Google Scholar

[23] R. I. Muhamedyev, Y. I. Kuchin, and E. L. Muhamedyeva, “Geophysical research of boreholes: Artificial neural networks data analysis,” in IEEE 6th International Conference on Soft Computing and Intelligent Systems, and the 13th International Symposium on Advanced Intelligence Systems, 2012, pp. 825–829. https://doi.org/10.1109/SCIS-ISIS.2012.650518310.1109/SCIS-ISIS.2012.6505183Search in Google Scholar

[24] E. Amirgaliev, Z. Isabaev, S. Iskakov, Y. Kuchin, R. Muhamediyev, E. Muhamedyeva, K. Yakunin, “Recognition of rocks at uranium deposits by using a few methods of machine learning,” Soft Computing in Machine Learning, pp. 33–40, 2014. https://doi.org/10.1007/978-3-319-05533-6_410.1007/978-3-319-05533-6_4Search in Google Scholar

[25] R. I. Muhamedyev, et al., “Comparative analysis of classification algorithms,” in IEEE 9th International Conference on Application of Information and Communication Technologies (AICT), 2015, pp. 96–101. https://doi.org/10.1109/ICAICT.2015.733852510.1109/ICAICT.2015.7338525Search in Google Scholar

[26] R. Muhamediyev, E. Amirgaliev, S. Iskakov, Y. Kuchin, and E. Muhamedyeva, “Integration of Results of Recognition Algorithms at the Uranium Deposits,” JACIII, vol. 8, no. 3, pp. 347–352, 2014.Search in Google Scholar

[27] R. Muhamedyev, S. Iskakov, P. Gricenko, K. Yakunin, and Y. Kuchin, “Integration of results from Recognition Algorithms and its realization at the uranium production process,” in 8th IEEE International Conference AICT, 2014, pp. 188–191.Search in Google Scholar

[28] Y. Kuchin, R. Mukhamediev, and K. Yakunin, “One method of generating synthetic data to assess the upper limit of machine learning algorithms performance,” Cogent Engineering, p. 1718821, 2020. https://doi.org/10.1080/23311916.2020.171882110.1080/23311916.2020.1718821Search in Google Scholar

[29] Keras Team, “Keras: Deep Learning for humans,” [Online]. Available: https://github.com/keras-team/keras [Accessed: Mar. 02, 2020].Search in Google Scholar

[30] M. Ribeiro, S. Singh, and C. Guestrin, “Local Interpretable Model-Agnostic Explanations (LIME): An Introduction A technique to explain the predictions of any machine learning classifier,” 2019.Search in Google Scholar

[31] M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should i trust you? Explaining the predictions of any classifier,” in Proc. of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 1135–1144.10.1145/2939672.2939778Search in Google Scholar

[32] L. Hulstaert, “Understanding Model Predictions with LIME. Learn about Lime and how it works along with the potential pitfalls that come with using it,” [Online]. Available: https://www.datacamp.com/community/tutorials/understanding-modelpredictions-lime [Accessed: Mar. 02, 2020].Search in Google Scholar

[33] M. Ribeiro, “Lime,” [Online]. Available: https://github.com/marcotcr/lime [Accessed: Mar. 02, 2020].Search in Google Scholar

[34] M. Ribeiro, S. Singh, and C. Guestrin, “Local Interpretable Model-Agnostic Explanations (LIME): An Introduction,” [Online]. Available: https://www.oreilly.com/learning/introduction-to-local-interpretablemodel-agnostic-explanations-lime [Accessed: Mar. 02, 2020].Search in Google Scholar

[35] W. Koehrsen, “A Complete Machine Learning Walk-Through in Python: Part Three Interpreting a machine learning model and presenting results,” [Online]. Available: https://towardsdatascience.com/a-completemachine-learning-walk-through-in-python-part-three-388834e8804b [Accessed: Mar. 02, 2020].Search in Google Scholar

[36] S. M. Lundberg, S. I. Lee, “A unified approach to interpreting model predictions,” Advances in neural information processing systems, pp. 4765–4774, 2017.Search in Google Scholar

[37] S. Lundberg, “SHAP (SHapley Additive exPlanations),” [Online]. Available: https://github.com/slundberg/shap [Accessed: Mar. 02, 2020].Search in Google Scholar

[38] Mangalathu, Sujith, Seong-Hoon Hwang, and Jong-Su Jeon. “Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach,” Engineering Structures 219, pp. 110927, 2020. https://doi.org/10.1016/j.engstruct.2020.11092710.1016/j.engstruct.2020.110927Search in Google Scholar

[39] A. B. Parsa, et al. “Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis,” Accident Analysis & Prevention, vol. 136, pp. 105405, 2020. https://doi.org/10.1016/j.aap.2019.10540510.1016/j.aap.2019.10540531864931Search in Google Scholar

[40] R. Muhamedyev, et al. “The use of machine learning “black boxes” explanation systems to improve the quality of school education.” Cogent Engineering, vol. 7.1, pp. 1769349, 2020. https://doi.org/10.1080/23311916.2020.176934910.1080/23311916.2020.1769349Search in Google Scholar

[41] García, María Vega, and José L. Aznarte. “Shapley additive explanations for NO2 forecasting,” Ecological Informatics vol. 56, pp. 101039, 2020. https://doi.org/10.1016/j.ecoinf.2019.10103910.1016/j.ecoinf.2019.101039Search in Google Scholar

[42] Rodríguez-Pérez, Raquel, and Jürgen Bajorath. “Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values,” Journal of Medicinal Chemistry vol. 63, no. 16, pp. 8761−8777, 2020. https://doi.org/10.1021/acs.jmedchem.9b0110110.1021/acs.jmedchem.9b0110131512867Search in Google Scholar