.png){kind=icon}
.png){kind=icon}
Return
SHAP based interpretable machine learning for predicting pressuremeter modulus from common geotechnical tests
.png){kind=icon}
OA
AI
DOI：10.1016/j.rineng.2026.110979.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Predicting pressuremeter modulus from routine geotechnical investigation data. • CatBoost achieved the best performance for Em prediction (R2 = 0.888). • SPT N-value dominated prediction with 39.7% SHAP importance. • Soil moisture and unit weight strongly affect the pressuremeter modulus value. • A SHAP-derived equation retained 86.8% accuracy and outperformed empirical models.
Keywords:
Pressuremeter modulus
SHAP explainability
Ensemble learning
Standard Penetration Test
Geotechnical site characterization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.