Performance evaluation of machine learning algorithms for predicting liquefaction-induced lateral displacement

Ahmad, Mahmood and Zubi, Mohammad Al and Biswas, Shaikat and Rakib, Abdur Rahman and Alzlfawi, Abdullah and Hussan, Sabahat and Haq, Shay and Omar, Rohayu Che and Ullah, Zia and Tóth, Zsolt György (2026) Performance evaluation of machine learning algorithms for predicting liquefaction-induced lateral displacement. SCIENTIFIC REPORTS, 16 (1). ISSN 2045-2322

Text s41598-026-50670-4.pdf Download (3MB)

Abstract

Accurate prediction of liquefaction-induced lateral displacement is essential for seismic risk assessment, resilient infrastructure design, and cost-effective mitigation. Such predictions are complex and cannot be reliably addressed using conventional analytical approaches. This research utilizes XGBoost, CatBoost and AdaBoost algorithms with 247 post-liquefaction in-situ free-face ground condition case studies to model and investigate liquefaction induced lateral displacements. The models are assessed according to the coefficient of determination (R 2 ), coefficient of correlation ( r ), mean absolute error (MAE), mean squared error (MSE), root means square error (RMSE), and Root Mean Squared Error-Observations standard deviation Ratio (RSR) and Nash Sutcliffe Efficiency (NSE) coefficient. The develop models are compared with each other, and also to the Gaussian process regression, artificial neural network, Evolutionary polynomial regression and Multiple linear regression models described in the literature. The XGBoost model had the best prediction performance, with R 2 = 0.9905, r = 0.9952, MAE = 0.1491, MSE = 0.0485, RMSE = 0.2203, RSR = 0.0981, and NSE = 0.9904 for training and R 2 = 0.9251, r = 0.9618, MAE = 0.3642, MSE = 0.3723, RMSE = 0.6101, RSR = 0.278, and NSE = 0.9227 for testing results respectively. The rank score analysis confirmed XGBoost to be superior, as it reached the highest total score of 40. Sensitivity analysis further revealed that T 15 was the most sensitive parameter to output variable.

Tudományterület / tudományág

engineering and technology
engineering and technology > material sciences and technologies

Faculty

Not relevant

Institution

Soproni Egyetem

Item Type:	Article
SWORD Depositor:	Teszt Sword
Depositing User:	Csaba Horváth
Identification Number:	MTMT:37367354
Date Deposited:	17 Jul 2026 08:40
Last Modified:	17 Jul 2026 08:40
URI:	http://publicatio.uni-sopron.hu/id/eprint/4113

Actions (login required)

View Item