What question did this study set out to answer?

The aim is to assess soil susceptibility to liquefaction using advanced machine-learning techniques.

Assessment of SPT-based Liquefaction Potential using Ensemble Learning and Feature Importance Approaches

View Full Paper

Ask AI

Bookmark

Authors

Engineers assess liquefaction potential in soils using machine learning techniques, suggesting improved accuracy and efficiency.

The aim is to assess soil susceptibility to liquefaction using advanced machine-learning techniques.
Compiled a comprehensive dataset related to liquefaction potential.
Utilized ensemble learning methods, including logistic regression and random forest.
Employed GridSearchCV for hyperparameter tuning of models.
Fitted AdaBoost and voting classifiers for improved prediction accuracy.
Achieved an accuracy of 88% using the AdaBoost model.
Voting Classifier had superior performance with lower false negatives and higher true positives.
Identified Standard Penetration Test-derived parameters as the most important features for predicting liquefaction.

Far et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark