Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini

Utku Köktan

doi:10.54365/adyumbd.1817408

EN TR

Estimation of the Safety Factor of Retaining Walls Using a Bayesian Optimization Supported XGBoost Model

Abstract

In this study, 1880 distinct scenarios were generated for rectangular cantilever retaining walls constructed in cohesionless soil backfill from combinations of six input parameters such as internal friction angle and unit weight of the backfill soil, width, height, and unit weight of the wall, and horizontal seismic acceleration coefficient. Subsequently, safety factors against sliding, overturning, and bearing capacity failure were calculated for each scenario based on the Mononobe-Okabe method. The minimum among these safety factors was accepted as the output value for the respective scenario, thereby creating a dataset, and a Bayesian optimization-supported XGBoost (XGBoost-BO) model was developed to predict this minimum safety factor. The model's predictive performance was evaluated using statistical metrics such as R2, VAF, RMSE, MAE, and MSE, in addition to performance curves, residual analysis, and associated histogram and Q-Q plots. The developed model demonstrated high success, achieving R2:0.9921 and RMSE:0.0129, and the decision-making mechanism was explained in detail by interpreting the influence of the inputs on the output via SHAP analysis.

Keywords

Retaining walls , Bayesian optimization , XGBoost algorithm , SHAP analysis

Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini

Öz

Bu çalışmada, kohezyonsuz zemin ortamında inşa edilen dikdörtgen kesitli konsol istinat duvarları için dolgu zeminine ait içsel sürtünme açısı ve birim hacim ağırlık, duvara ait genişlik, yükseklik ve birim hacim ağırlık ile yatay deprem ivme katsayısının kombinasyonlarından 1880 farklı senaryo oluşturulmuştur. Ardından her bir senaryo için Mononobe-Okabe yöntemine dayalı hesaplamalar gerçekleştirilerek kayma, devrilme ve taşıma gücüne karşı güvenlik sayıları elde edilmiştir. Bu güvenlik sayılarının en küçüğü, ilgili senaryonun çıktı değeri kabul edilerek bir veri seti oluşturulmuş ve minimum güvenlik sayısını tahmin edebilen Bayesian optimizasyon destekli XGBoost (XGBoost-BO) modeli geliştirilmiştir. Modelin tahmin performansı R2, VAF, RMSE, MAE ve MSE gibi istatistiksel metrikler ve performans eğrilerine ilaveten yapılan artık analizi ve buna bağlı oluşturulan histogram ve Q-Q grafikleri üzerinden değerlendirilmiştir. Geliştirilen model, R2:0.9921 ve RMSE:0.0129 ile yüksek başarı sergilemiş ve ayrıca SHAP analizi ile girdilerin çıktı üzerindeki etkileri yorumlanarak karar mekanizması detaylıca açıklanmıştır.

Anahtar Kelimeler

İstinat duvarları , Bayesian optimizasyonu , XGBoost algoritması , SHAP analizi

Kaynakça

Köktan U. Konsol İstinat duvarlarının dinamik davranışının yapay zeka yöntemleriyle belirlenmesi. [Doktora Tezi]. Samsun, Türkiye: Ondokuz Mayıs Üniversitesi; 2024.
Kramer SL. Geotechnical earthquake engineering. Pearson Education India; 1996.
Okabe S. General theory of earth pressures, j. Japan soc. Civil Engineering 1926; 12(1).
Mononobe N. On determination of earth pressure during earthquake. In: Proc. World Engrg. Congress, Tokyo, Japan; 1929.
Coulomb C. An attempt to apply the rules of maxima and minima to several problems of stability related to architecture. Mémoires de l’Académie Royale des Sciences 1776; 7: 343-382.
TBDY: Türkiye bina deprem yönetmeliği. Afet ve Acil Durum Yönetimi Başkanlığı, 2018.
Cakir T. Evaluation of the effect of earthquake frequency content on seismic behavior of cantilever retaining wall including soil–structure interaction. Soil Dynamics and Earthquake Engineering 2013; 45: 96-111.
Richards Jr R, Elms DG. Seismic behavior of gravity retaining walls. Journal of the Geotechnical Engineering Division 1979; 105(4): 449-464.
Nadim F, Whitman RV. Seismically induced movement of retaining walls. Journal of Geotechnical Engineering 1983; 109(7): 915-931.
Steedman R, Zeng X. The influence of phase on the calculation of pseudo-static earth pressure on a retaining wall. Geotechnique 1990; 40(1): 103-112.

Baghbani A, Choudhury T, Costa S, Reiner J. Application of artificial intelligence in geotechnical engineering: A state-of-the-art review. Earth-Science Reviews 2022; 228: 103991.
Ghaleini EN, Koopialipoor M, Momenzadeh M, Sarafraz ME, Mohamad ET, Gordan B. A combination of artificial bee colony and neural network for approximating the safety factor of retaining walls. Engineering with Computers 2019; 35(2): 647-658.
Chen H, Asteris PG, Jahed Armaghani D, Gordan B, Pham BT. Assessing dynamic conditions of the retaining wall: Developing two hybrid intelligent models. Applied Sciences 2019; 9(6): 1042.
Gordan B, Koopialipoor M, Clementking A, Tootoonchi H, Tonnizam Mohamad E. Estimating and optimizing safety factors of retaining wall through neural network and bee colony techniques. Engineering with Computers 2019; 35(3): 945-954.
Özturk TE. Artificial neural networks approach for earthquake deformation determination of geosynthetic reinforced retaining walls. International Journal of Intelligent Systems and Applications in Engineering 2014; 2(1): 1-9.
Xu C, Gordan B, Koopialipoor M, Armaghani DJ, Tahir M, Zhang X. Improving performance of retaining walls under dynamic conditions developing an optimized ann based on ant colony optimization technique. IEEE Access 2019; 7: 94692-94700.
Yang H, Koopialipoor M, Armaghani DJ, Gordan B, Khorami M, Tahir M. Intelligent design of retaining wall structures under dynamic conditions. Steel and Composite Structures, An International Journal 2019; 31(6): 629-640.
Koopialipoor M, Murlidhar BR, Hedayat A, Armaghani DJ, Gordan B, Mohamad ET. The use of new intelligent techniques in designing retaining walls. Engineering with Computers 2020; 36(1): 283-294.
Mishra P, Samui P, Mahmoudi E. Probabilistic design of retaining wall using machine learning methods. Applied Sciences 2021; 11(12): 5411.
Mustafa R, Samui P, Kumari S. Probabilistic analysis of gravity retaining wall using anfis-based optimization techniques. Innovative Infrastructure Solutions 2022; 7(6): 366.
Mustafa R, Samui P, Kumari S. Reliability analysis of gravity retaining wall using hybrid anfis. Infrastructures 2022; 7(9): 121.
Mustafa R, Samui P, Kumari S. Seismic performance of gravity retaining walls under quasi-static approach using probabilistic analysis. Transportation Infrastructure Geotechnology 2023; 11(2): 1-38.
Mustafa R, Samui P, Kumari S, Mohamad ET, Bhatawdekar RM. Probabilistic analysis of gravity retaining wall against bearing failure. Asian Journal of Civil Engineering 2023: 1-21.
Kumar A, Burman A. Reliability analysis of gravity retaining wall under seismic conditions using a novel hybrid paradigm of elm and improved grey wolf optimizer. Modeling Earth Systems and Environment 2025; 11(3): 214.
Azad SK, Akış E. Cost efficient design of mechanically stabilized earth walls using adaptive dimensional search algorithm. Teknik Dergi 2020; 31(4): 10167-10188.
Bekdaş G, Cakiroglu C, Kim S, Geem ZW. Optimal dimensioning of retaining walls using explainable ensemble learning algorithms. Materials 2022; 15(14): 1-15.
Cakiroglu C, Islam K, Bekdaş G, Nehdi ML. Data-driven ensemble learning approach for optimal design of cantilever soldier pile retaining walls. Structures 2023; 51: 1268-1280.
Ertosun Karabulut Z, Kurt Z, Kalemci E, Dede T, Ikizler SB. Reinforced concrete cantilever retaining wall design consisting of two stage stem using rao1 algorithm. Engineering Computations 2025.
Kalemci EN, İkizler SB, Dede T, Angın Z. Design of reinforced concrete cantilever retaining wall using grey wolf optimization algorithm. Structures 2020; 23: 245-253.
Liu W, He L, Liu J, Xie X, Hao N, Shen C, Zhou J. Design optimization of an innovative instrumental single-sided formwork supporting system for retaining walls using physics-constrained generative adversarial network. Buildings 2025; 15(1): 132.
Rhayma N, Khorchani M, Breul P. Reliability-based design optimization of gravity retaining walls. Computers and Concrete 2025; 35(2): 203.
Uray E, Tan Ö, Çarbaş S, Erkan İH. Metaheuristics-based pre-design guide for cantilever retaining walls. Teknik Dergi 2021; 32(4): 10967-10993.
Das BM. Principles of geotechnical engineering, 7th edition. Cengage learning; 2010.
Seed HB, Whitman RV. Design of earth retaining structures for dynamic loads. ASCE, Specialty Conf on Lateral Stresses in Ground and Design of Earth-Retaining Structures; Ithaca, NY 1970: 103-147.
Terzaghi K. Theoretical soil mechanics. 1943.
Das BM. Principles of foundation engineering, si. Seventh Edition ed. 794. USA: Global Engineering; 2011.
Kardani N, Bardhan A, Samui P, Nazem M, Zhou A, Armaghani DJ. A novel technique based on the improved firefly algorithm coupled with extreme learning machine (elm-iff) for predicting the thermal conductivity of soil. Engineering with Computers 2021; 38(4): 1-20.
Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, San Francisco California, USA; 2016.
Feng D-C, Wang W-J, Mangalathu S, Taciroglu E. Interpretable xgboost-shap machine-learning model for shear strength prediction of squat rc walls. Journal of Structural Engineering 2021; 147(11): 04021173.
Zhang J, Yuan J, Mahmoudi A, Ji W, Fang Q. A data-driven framework for conceptual cost estimation of infrastructure projects using xgboost and bayesian optimization. Journal of Asian Architecture and Building Engineering 2025; 24(2): 751-774.
Wu J, Chen X-Y, Zhang H, Xiong L-D, Lei H, Deng S-H. Hyperparameter optimization for machine learning models based on bayesian optimization. Journal of Electronic Science and Technology 2019; 17(1): 26-40.
Luong P, Nguyen D, Gupta S, Rana S, Venkatesh S. Adaptive cost-aware bayesian optimization. Knowledge-Based Systems 2021; 232: 107481.
Shi R, Xu X, Li J, Li Y. Prediction and analysis of train arrival delay based on xgboost and bayesian optimization. Applied Soft Computing 2021; 109: 107538.
Shin S, Lee Y, Kim M, Park J, Lee S, Min K. Deep neural network model with bayesian hyperparameter optimization for prediction of nox at transient conditions in a diesel engine. Engineering Applications of Artificial Intelligence 2020; 94: 103761.
Shahriari B, Swersky K, Wang Z, Adams RP, De Freitas N. Taking the human out of the loop: A review of bayesian optimization. Proceedings of the IEEE 2015; 104(1): 148-175.
Mangalathu S, Hwang S-H, Jeon J-S. Failure mode and effects analysis of rc members based on machine-learning-based shapley additive explanations (shap) approach. Engineering Structures 2020; 219: 110927.
Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 2017; 30.
Lundberg SM, Erion GG, Lee S-I. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 2018.
Mangalathu S, Jang H, Hwang S-H, Jeon J-S. Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls. Engineering Structures 2020; 208: 110331.
Mangalathu S, Jeon J-S. Machine learning–based failure mode recognition of circular reinforced concrete bridge columns: Comparative study. Journal of Structural Engineering 2019; 145(10): 04019104.
Somala SN, Chanda S, Karthikeyan K, Mangalathu S. Explainable machine learning on new zealand strong motion for pgv and pga. In: Structures; Elsevier; 2021.

Ayrıntılar

Birincil Dil

Türkçe

Konular

İnşaat Geoteknik Mühendisliği

Bölüm

Araştırma Makalesi

Yazarlar

Utku Köktan ^*
0000-0002-8287-9586
Türkiye

Yayımlanma Tarihi

19 Nisan 2026

Gönderilme Tarihi

5 Kasım 2025

Kabul Tarihi

8 Şubat 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 13 Sayı: 1

DOI

https://doi.org/10.54365/adyumbd.1817408

IZ

https://izlik.org/JA22TZ38GH

APA

Köktan, U. (2026). Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, 13(1), 1-15. https://doi.org/10.54365/adyumbd.1817408

AMA

1.Köktan U. Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi. 2026;13(1):1-15. doi:10.54365/adyumbd.1817408

Chicago

Köktan, Utku. 2026. “Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini”. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi 13 (1): 1-15. https://doi.org/10.54365/adyumbd.1817408.

EndNote

Köktan U (01 Nisan 2026) Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi 13 1 1–15.

IEEE

[1]U. Köktan, “Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini”, Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, c. 13, sy 1, ss. 1–15, Nis. 2026, doi: 10.54365/adyumbd.1817408.

ISNAD

Köktan, Utku. “Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini”. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi 13/1 (01 Nisan 2026): 1-15. https://doi.org/10.54365/adyumbd.1817408.

JAMA

1.Köktan U. Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi. 2026;13:1–15.

MLA

Köktan, Utku. “Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini”. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, c. 13, sy 1, Nisan 2026, ss. 1-15, doi:10.54365/adyumbd.1817408.

Vancouver

1.Utku Köktan. Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi. 01 Nisan 2026;13(1):1-15. doi:10.54365/adyumbd.1817408

Estimation of the Safety Factor of Retaining Walls Using a Bayesian Optimization Supported XGBoost Model

Abstract

Keywords

Bayesian Optimizasyon Destekli XGBoost Modeli ile Konsol İstinat Duvarlarının Güvenlik Sayısının Tahmini

Öz

Anahtar Kelimeler

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

DOI

IZ

Kaynak Göster