자유낙하 관입시험기 데이터를 활용하여 퇴적물 거동 유형을 정확하게 분류하고 예측 불확실성을 정량화할 수 있는 혁신적인 예측 모델을 제안한다.
This study introduces a novel predictive model that combines Random Forest and 1D Bayesian Convolutional Neural Network algorithms to classify near-surface shallow-water sediments into four behavior types based on data from Portable Free-Fall Penetrometer (PFFP) deployments. The model provides not only the predicted sediment class but also quantifies the associated uncertainty, offering a more comprehensive and informed approach to sediment characterization.
Explainable machine learning models, specifically XGBoost with SHAP analysis, can effectively predict the occurrence of liquefaction-induced lateral spreading by capturing complex soil characteristics and site conditions, while also providing insights into the key factors driving the model's predictions.
A novel transformer-based deep learning model can accurately predict the load-deformation behavior of large bored piles in Bangkok's complex subsoil conditions.
Investigating shear banding and cracking in unsaturated porous media under non-isothermal conditions using a nonlocal THM meshfree paradigm.
Automating rock mass quality assessment using machine learning models improves tunnel engineering design.