Scholarlink

<p>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<sup>2</sup>), coefficient of correlation (<i>r</i>), 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<sup>2</sup> = 0.9905, <i>r</i> = 0.9952, MAE = 0.1491, MSE = 0.0485, RMSE = 0.2203, RSR = 0.0981, and NSE = 0.9904 for training and R<sup>2</sup> = 0.9251, <i>r</i> = 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<sub>15</sub> was the most sensitive parameter to output variable.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月30日

查看全文
  • Mahmood Ahmad,
  • Mohammad Al Zubi,
  • Shaikat Biswas,
  • Abdur Rahman Rakib,
  • Abdullah Alzlfawi,
  • Sabahat Hussan,
  • Shay Haq,
  • Rohayu Che Omar,
  • Zia Ullah,
  • Zsolt Tóth

摘要

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 (R2), 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 R2 = 0.9905, r = 0.9952, MAE = 0.1491, MSE = 0.0485, RMSE = 0.2203, RSR = 0.0981, and NSE = 0.9904 for training and R2 = 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 T15 was the most sensitive parameter to output variable.