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

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

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

Absztrakt (kivonat)

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

műszaki tudományok
műszaki tudományok > anyagtudományok és technológiák

Kar

Nem releváns

Intézmény

Soproni Egyetem

Mű tipusa:	Cikk
SWORD Depositor:	Teszt Sword
Felhasználó:	Csaba Horváth
A mű MTMT azonosítója:	MTMT:37367354
Dátum:	17 Júl 2026 08:40
Utolsó módosítás:	17 Júl 2026 08:40
URI:	http://publicatio.uni-sopron.hu/id/eprint/4113

Actions (login required)

Tétel nézet