Ranger Uygulamasını Kullanarak Şev Stabilitesi Değerlendirmesi için Rastgele Orman Öneme Dayalı Öznitelik Sıralaması ve Alt Küme Seçimi

Öz

Şevlerin stabilite sorunları geometrik, jeolojik, sismik vb. çeşitli faktörlerden kaynaklanabilir. Şevlerin stabilitesini tahmin etmek için uzun yıllardır limit denge yöntemi, sayısal yöntemler ve istatistiksel yöntemler gibi geleneksel yöntemler başarıyla kullanılmıştır. Öte yandan, şev stabilitesini tahmin etmek için literatürde bulunan veri setlerini kullanılarak pek çok makine öğrenimi (ML) girişiminde de bulunulmuştur. Bu çalışma, Ranger algoritmasını kullanarak şev stabilitesinin değerlendirilmesi için sınıflandırma modelleri oluşturmayı amaçlamaktadır. Model oluşturmak için altı girdi parametresi bulunan (eğim yüksekliği, birim hacim ağırlık, eğim açısı, kohezyon, boşluk suyu basıncı oranı ve iç sürtünme açısı) toplamda 168 şev vakasından oluşan bir veri seti kullanılmıştır. İlk adımda, altı özelliğin rastgele orman (RF) öznitelik önem dereceleri belirlenmiş ve veri setinin değişken sayıları azaltılarak beş farklı tahmin modeli üretilmiştir. Geliştirilen modeller daha sonra performans metrikleri kullanılarak değerlendirilerek ve en iyi tahmin modelini seçmek için sonuçlar karşılaştırılmıştır. Elde edilen bulgulara göre, öznitelik önemine dayalı değişken sıralaması ve alt küme seçimi yaklaşımı (yani RF öznitelik önem derecesi) modellerin performansını etkilediği görülmüştür. RF öznitelik önem puanlarından, çalışılan veri seti için şev stabilitesini en çok etkileyen değişkenin birim hacim ağırlık olduğu görülmüştür. Ayrıca beş değişken ile geliştirilen Ranger modeli (Model IV) %90 değeri ile en yüksek test doğruluğuna ulaşmıştır.

Anahtar Kelimeler

• Öznitelik Sıralaması
• Makine Öğrenimi
• Tahmin Modeli
• Ranger
• Şev Stabilitesi

Random Forest Importance-Based Feature Ranking and Subset Selection for Slope Stability Assessment using the Ranger Implementation

Abstract

Stability problems of slopes can arise from various factors such as geometrical, geological, seismic etc. For many years, conventional methods such as limit equilibrium method, numerical methods, and statistical methods have been successfully utilized to predict the stability of slopes. On the other hand, several machine learning (ML) attempts have been made for predicting slope stability using datasets available in the literature. The present study aims to build classification models for the assessment of the stability of slopes using the Ranger algorithm. A total of 168 cases with six input parameters (slope height, unit weight, slope angle, cohesion, pore water pressure ratio, and internal friction angle) are used to generate models. In the first step, random forest (RF) feature importance scores of the six features are determined and five different prediction models were produced by reducing the feature numbers of the dataset. The developed models are then assessed using performance metrics and results are compared to choose the best prediction model. According to the obtained results, the feature importance-based feature ranking and subset selection approach (i.e., RF feature importance) affect the performance of the models. It is observed that from the RF feature importance scores, the unit weight is found to be the most influencing feature that affects the stability of slopes for the studied dataset. In addition, the Ranger model developed with five features (Model IV) achieves the highest test accuracy with a value of 90%.

Keywords

• Feature Ranking
• Machine Learning
• Prediction Model
• Slope Stability
• Ranger

References

1. Abdalla, J. A., Attom, M. F., & Hawileh, R. (2015). Prediction of minimum factor of safety against slope failure in clayey soils using artificial neural network. Environmental Earth Sciences, 73, 5463-5477.
2. Alpaydin, E. (2020). Introduction to machine learning. MIT press.
3. Cala, M., & Flisiak, J. (2020). Slope stability analysis with FLAC and limit equilibrium methods. In FLAC and numerical modeling in geomechanics (pp. 111-114). CRC Press.
4. Choobbasti, A. J., Farrokhzad, F., & Barari, A. (2009). Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran). Arab J Geosci 2 (4): 311–319.
5. Chakraborty, A., & Goswami, D. (2017). Slope stability prediction using artificial neural network (ANN). Int. J. Eng. Comput. Sci, 6(6), 21845-21848.
6. Demir, S., & Sahin, E. K. (2022). Comparison of tree-based machine learning algorithms for predicting liquefaction potential using canonical correlation forest, rotation forest, and random forest based on CPT data. Soil Dynamics and Earthquake Engineering, 154, 107130.
7. Guyon, I., Gunn, S., Nikravesh, M., & Zadeh, L. A. (Eds.). (2008). Feature extraction: foundations and applications (Vol. 207). Springer.
8. Hoang, N. D., & Bui, D. T. (2017). Slope stability evaluation using radial basis function neural network, least squares support vector machines, and extreme learning machine. In Handbook of neural computation (pp. 333-344). Academic Press.

9. Hoang, N. D., & Pham, A. D. (2016). Hybrid artificial intelligence approach based on metaheuristic and machine learning for slope stability assessment: A multinational data analysis. Expert Systems with Applications, 46, 60-68.
10. Hobeichi, S., Abramowitz, G., Evans, J. P., & Ukkola, A. (2022). Toward a Robust, Impact‐Based, Predictive Drought Metric. Water Resources Research, 58(2), e2021WR031829.
11. Jellali, B., & Frikha, W. (2017). Constrained particle swarm optimization algorithm applied to slope stability. International Journal of Geomechanics, 17(12), 06017022.
12. Kardani, N., Zhou, A., Nazem, M., & Shen, S. L. (2021). Improved prediction of slope stability using a hybrid stacking ensemble method based on finite element analysis and field data. Journal of Rock Mechanics and Geotechnical Engineering, 13(1), 188-201.
13. Krahn, J. (2003). The 2001 RM Hardy Lecture: The limits of limit equilibrium analyses. Canadian Geotechnical Journal, 40(3), 643-660.
14. Li, J., & Wang, F. (2010). Study on the forecasting models of slope stability under data mining. In Earth and Space 2010: Engineering, Science, Construction, and Operations in Challenging Environments (pp. 765-776).
15. Lim, K., Lyamin, A. V., Cassidy, M. J., & Li, A. J. (2016). Three-dimensional slope stability charts for frictional fill materials placed on purely cohesive clay. International Journal of Geomechanics, 16(2), 04015042.
16. Lin, S., Zheng, H., Han, B., Li, Y., Han, C., & Li, W. (2022). Comparative performance of eight ensemble learning approaches for the development of models of slope stability prediction. Acta Geotechnica, 17(4), 1477-1502.
17. Liu, Z., Shao, J., Xu, W., Chen, H., & Zhang, Y. (2014). An extreme learning machine approach for slope stability evaluation and prediction. Natural hazards, 73, 787-804.
18. Liu, G., Ma, J., Hu, T., & Gao, X. (2022). A feature selection method with feature ranking using genetic programming. Connection Science, 34(1), 1146-1168.
19. Lu, P., & Rosenbaum, M. S. (2003). Artificial neural networks and grey systems for the prediction of slope stability. Natural Hazards, 30, 383-398.
20. Moayedi, H., Tien Bui, D., Kalantar, B., & Kok Foong, L. (2019). Machine-learning-based classification approaches toward recognizing slope stability failure. Applied Sciences, 9(21), 4638.
21. Moon, J., Park, S., Rho, S., & Hwang, E. (2022). Robust building energy consumption forecasting using an online learning approach with R ranger. Journal of Building Engineering, 47, 103851.
22. Pham, K., Kim, D., Park, S., & Choi, H. (2021). Ensemble learning-based classification models for slope stability analysis. Catena, 196, 104886.
23. Sah, N. K., Sheorey, P. R., & Upadhyaya, L. N. (1994, February). Maximum likelihood estimation of slope stability. In International journal of rock mechanics and mining sciences & geomechanics abstracts (Vol. 31, No. 1, pp. 47-53). Pergamon.
24. Samui, P. (2008). Slope stability analysis: a support vector machine approach. Environmental Geology, 56, 255-267.
25. Tiyasha, T., Tung, T. M., Bhagat, S. K., Tan, M. L., Jawad, A. H., Mohtar, W. H. M. W., & Yaseen, Z. M. (2021). Functionalization of remote sensing and on-site data for simulating surface water dissolved oxygen: Development of hybrid tree-based artificial intelligence models. Marine pollution bulletin, 170, 112639.
26. Wang, G., Zhao, B., Wu, B., Zhang, C., & Liu, W. (2023). Intelligent prediction of slope stability based on visual exploratory data analysis of 77 in situ cases. International Journal of Mining Science and Technology, 33(1), 47-59.
27. Wang, L., Wu, C., Tang, L., Zhang, W., Lacasse, S., Liu, H., & Gao, L. (2020). Efficient reliability analysis of earth dam slope stability using extreme gradient boosting method. Acta Geotechnica, 15, 3135-3150.
28. Wright, M. N., & Ziegler, A. (2015). ranger: A fast implementation of random forests for high dimensional data in C++ and R. arXiv preprint arXiv:1508.04409.
29. Xiao, S., Guo, W. D., & Zeng, J. (2018). Factor of safety of slope stability from deformation energy. Canadian Geotechnical Journal, 55(2), 296-302.
30. Xiaoming, Y., & Xibing, L. (2011, April). Bayes discriminant analysis method for predicting the stability of open pit slope. In 2011 International Conference on Electric Technology and Civil Engineering (ICETCE) (pp. 147-150). IEEE.
31. Yang, X. L., & Yin, J. H. (2004). Slope stability analysis with nonlinear failure criterion. Journal of Engineering Mechanics, 130(3), 267-273.
32. Yang, Y., Zhou, W., Jiskani, I. M., Lu, X., Wang, Z., & Luan, B. (2023). Slope Stability Prediction Method Based on Intelligent Optimization and Machine Learning Algorithms. Sustainability, 15(2), 1169.
33. Zhou, K. P., & Chen, Z. Q. (2009, December). Stability prediction of tailing dam slope based on neural network pattern recognition. In 2009 Second International Conference on Environmental and Computer Science (pp. 380-383). IEEE.