A Comparative Study of Prediction Models for Road Bridge Safety Ratings Using Inspection History Data

View at Publisher

Ask AI

Bookmark

Share

Key Points

This research aims to compare the predictive performance of statistical models and machine learning models for road bridge safety ratings using historical inspection data.
Utilized inspection data from approximately 8,800 bridges collected between 2010 and 2024.
Applied ordinal logistic regression, multinomial logistic regression, ordinal forest, and random forest models.
Focused analysis on overall prediction performance and detection performance for high-risk deteriorated bridges.
Machine learning models outperformed statistical models overall.
The ordinal forest model was identified as the best performer for both overall and high-risk detection.
Important variables influencing safety ratings include previous safety ratings, years since completion, and managing authority.

Compares prediction models for road bridge safety ratings using inspection data, suggesting improved safety assessments.

No abstract yet. The journal hasn't published one we can show.

No takes yet. Share an insight, caveat, or question.

Jeong et al. (2026) studied this question.

View at Publisher

Ask AI

Bookmark

Share