.png){kind=icon}
Return
Interpretable machine learning framework for resilient modulus estimation using LTPP data for pavements
.png){kind=icon}
OA
AI
DOI：10.1016/j.cscm.2025.e05403.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• XGBoost SHAP Optuna framework predicts subgrade resilient modulus (Mr). • Model achieves high accuracy (R² = 0.91 train, 0.82 test; RMSE = 1.77; MAE = 0.78). • SHAP identifies SG, P200, and PI as key factors influencing Mr. • Reliable Mr estimation where laboratory testing is not feasible.
Keywords:
Mr
Resilient modulus
LTPP
Long-Term Pavement Performance
P200
Percentage passing the No. 200 sieve
LL
Liquid limit
PL
Plastic limit
PI
Plasticity index
SG
Specific gravity
MDD
Maximum dry density
OMC
Optimum moisture content
XGB
Extreme Gradient Boosting
SHAP
Shapley Additive Explanations
RMSE
Root mean square error
MAE
Mean absolute error
MAPE
Mean absolute percentage error
R²
Coefficient of determination
Resilient modulus
Prediction
Machine learning
XGBoost
SHAP
LTPP
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.6
Papers:
6.3K
Citations:
2.0W
Organization
Cited Papers
ShareSaveOptimizing the hyper-parameters of deep reinforcement learning for building control.png)
BUILDING SIMULATION
BUILDING SIMULATIONIF5.9
PREAI
ShareSaveShareSaveOptimizing Depression Classification Using Combined Datasets and Hyperparameter Tuning with OptunaSENSORSOAAI
SENSORSIF3.5
OAAIShareSaveIndirect estimation of resilient modulus (Mr) of subgrade soil: Gene expression programming vs multi expression programmingSTRUCTURES
STRUCTURESIF4.3
PREAI
ShareSave
View more