Comparative Performance Analysis of Ensemble Learning Algorithms for Rock Classification

Öz

Knowing the physical and mechanical properties of rocks is important for engineering studies. Because determining the properties and type of rocks affects the safety of engineering structures. Therefore, this study is important in terms of minimizing possible errors in engineering studies. Moreover, Automatic detection of rock types reduces the workload of engineers. In this study, the types of rocks were determined by using some physical and mechanical properties of rocks measured in the laboratory. Rep tree algorithm and ensemble learning algorithms were used in the study. The success of ensemble learning algorithms in classification was compared. As a result, it was understood that ensemble learning algorithms increase success. When the logitboost algorithm was used together with the rep tree algorithm, the Tp rate increased to 0.82. Precision Recall values were 0.80, MCC and AUC were 0.95, kappa was 0.80. In addition, the FP rate decreased to 0.04. The most successful algorithm in rock classification was the Logistboost algorithm. The highest performance metrics were obtained in the classification made with the Logistboost algorithm. In addition, 4 different metric types were calculated to determine the error rates of the algorithms. Logistboost algorithm classified with the lowest error rate.

Anahtar Kelimeler

• Clasification
• Ensemble learning algorithms
• Machine learning
• Rep tree
• Rock

Kaynakça

1. Nahhas, T., Py, X., & Sadiki, N. (2019). Experimental investigation of basalt rocks as storage material for high-temperature concentrated solar power plants. Renewable and Sustainable Energy Reviews, 110, 226-235.
2. Fegade, V., Ramachandran, M., Madhu, S., Vimala, C., Malar, R. K., & Rajeshwari, R. (2022, May). A review on basalt fibre reinforced polymeric composite materials. In AIP Conference Proceedings 2393(1). AIP Publishing.
3. Aldeeky, H., Al Hattamleh, O., & Rababah, S. (2020). Assessing the uniaxial compressive strength and tangent Young’s modulus of basalt rock using the Leeb rebound hardness test. Materiales de Construcción, 70(340), e230-e230.
4. Mustapaevich, D. K. (2021). Geological-Geochemical and Mineralogical Properties of Basalt Rocks of Karakalpakstan. International Journal on Integrated Education, 4(10), 205-208.
5. Sadique, M. R., Zaid, M., & Alam, M. M. (2022). Rock tunnel performance under blast loading through finite element analysis. Geotechnical and Geological Engineering, 40(1), 35-56.
6. Zaid, M. (2021). Three-dimensional finite element analysis of urban rock tunnel under static loading condition: effect of the rock weathering. Geomechanics and Engineering, 25(2), 99-109.
7. Zhao, D., He, Q., Ji, Q., Wang, F., Tu, H., & Shen, Z. (2023). Similar model test of a mudstone-interbedded–sandstone-bedding rock tunnel. Tunnelling and Underground Space Technology, 140, 105299.
8. Shoeb, M., Khan, S. A., Alam, T., Ali, M. A., Gupta, N. K., Ansari, M. M., ... & Dobrota, D. (2023). Dynamic stability analysis of metro tunnel in layered weathered sandstone. Ain Shams Engineering Journal, 102258.

9. Abdulsamad, F., Revil, A., Ghorbani, A., Toy, V., Kirilova, M., Coperey, A., ... & Ravanel, L. (2019). Complex conductivity of graphitic schists and sandstones. Journal of Geophysical Research: Solid Earth, 124(8), 8223-8249.
10. Nayak, S. K., Satapathy, A., & Mantry, S. (2022). Use of waste marble and granite dust in structural applications: A review. Journal of Building Engineering, 46, 103742.
11. Kang, F., Jia, T., Li, Y., Deng, J., & Huang, X. (2021). Experimental study on the physical and mechanical variations of hot granite under different cooling treatments. Renewable Energy, 179, 1316-1328.
12. Skierszkan, E. K., Dockrey, J. W., Mayer, K. U., Bondici, V. F., McBeth, J. M., & Beckie, R. D. (2020). Geochemical Controls on Uranium Release from Neutral-pH Rock Drainage Produced by Weathering of Granite, Gneiss, and Schist. Minerals, 10(12), 1104.
13. Barham, W. S., Rabab’ah, S. R., Aldeeky, H. H., & Al Hattamleh, O. H. (2020). Mechanical and physical based artificial neural network models for the prediction of the unconfined compressive strength of rock. Geotechnical and Geological Engineering, 38, 4779-4792.
14. Xu, H., Zhou, J., G. Asteris, P., Jahed Armaghani, D., & Tahir, M. M. (2019). Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate. Applied sciences, 9(18), 3715.
15. Garzanti, E. (2019). Petrographic classification of sand and sandstone. Earth-science reviews, 192, 545-563.
16. Bressan, T. S., de Souza, M. K., Girelli, T. J., & Junior, F. C. (2020). Evaluation of machine learning methods for lithology classification using geophysical data. Computers & Geosciences, 139, 104475.
17. Sertçelik, İ., Kurtuluş, C., Sertçelik, F., Pekşen, E., & Aşçı, M. (2018). Investigation into relations between physical and electrical properties of rocks and concretes. Journal of Geophysics and Engineering, 15(1), 142-152.
18. ASTM Standard 1984Standard test method for unconfined compressive strength of intact corespecimens soil and rock building stones Annual Book of ASTM Standards 4.08
19. ASTM Standard 2001Standard Practice for Preparing Rock Core Specimens and Determining Dimensional and Shape Tolerances (Philadelphia, PA: American Society for Testing and Materials) D4543
20. ISRM 2007 The Complete ISRM Suggested Methods for Rock Characterization Testing and Monitoring:1974–2006 ed R Ulusay and J A Hudson (Ankara: Kozan Ofset Press)
21. Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140.
22. Freund, Y., & Schapire, R. E. (1996, July). Experiments with a new boosting algorithm. In Icml 96, 148-156.
23. Friedman, J., Hastie T., & Tibshirani, R. (2000) Additive Logistic Regression: a Statistical View of Boosting, Annals of Statistics, 28, 337-407.