.png){kind=icon}
.png){kind=icon}
Return
A comprehensive approach for Bayesian soil classification using Cone Penetration Test data
.png){kind=icon}
OA
AI
DOI：10.1016/j.compgeo.2025.107671.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• New method for soil type classification from CPT data. • Predicts probabilities of each soil type rather than deterministic estimates. • Includes automated data curation and model training algorithms alongside prediction. • Entirely data-driven; trained on over 500,000 data points from 25 sites worldwide. • Bayesian formulation allows model to be updated with new (e.g., site-specific) data.
Keywords:
Cone Penetration Test
CPT
Classification
Soil type
Machine Learning
Bayesian
Data-driven
Uncertainty
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.2
Papers:
7.1K
Citations:
2.9W
Organization
No organization information available