Sustainable rehabilitation of corroded RC culverts using ECC and interpretable machine learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Culverts are vital for managing subsurface water flow beneath transport infrastructure, especially in areas with poor drainage and low bearing capacity. Precast reinforced concrete (RC) box culverts are widely used for their structural efficiency and constructability; however, prolonged exposure to moisture and corrosive environments leads to significant deterioration, particularly reinforcement corrosion. This study introduces a novel strengthening strategy using Engineered Cementitious Composites (ECC), applied beneath the top slab—the most corrosion-prone zone. A series of 200 nonlinear finite element (FE) simulations were conducted to evaluate culvert performance across varying corrosion thicknesses and ECC configurations. Subsequently, six machine learning (ML) models XGBoost, AdaBoost, RF, SGD, kNN, and GEP were trained to predict ultimate load capacity using key geometric and material parameters. Explainable AI (XAI) techniques SHAP and Partial Dependence Plot (PDP) analyses were employed to interpret the ML outputs, revealing parameter sensitivities and physical relevance. Results showed that ECC effectively restores load capacity (up to 41 % increase) of corroded culverts and improves deformation behavior. Among the models, XGBoost yielded the highest predictive accuracy, while SHAP analysis confirmed culvert width, corrosion thickness, and ECC strength as dominant features. This integrated FEM-ML-XAI approach offers a data-driven, interpretable, and material-efficient solution for rehabilitating corroded culverts. This study contributes a novel combination of advanced materials and explainable AI, offering actionable insights for the sustainable and intelligent rehabilitation of deteriorated culverts in corrosion-prone environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it