Automated standardization of bridge inspection data using generative AI
Bibliographic record
Abstract
This paper presents a method leveraging generative AI and natural language processing to standardize bridge inspection data, transforming it into a ready-to-use format for direct use in condition assessment, predictive modeling, and informed decision-making. This entails capturing and evaluating severity levels of reinforced concrete bridge defects from textual inspection data, such as comments provided by inspection personnel regarding type, location, and intensity of these defects. This paper employs three models: (1) a baseline generative pre-trained transformer model, which leverages OpenAI’s large language models to process textual inspection data through an optimized prompt engineering procedure; (2) a fine-tuned generative pre-trained transformer model, which builds upon the baseline by incorporating domain-specific training before being deployed to improve its performance; and (3) a newly developed natural language processing model, which employs conventional natural language processing techniques, providing a benchmark for comparison with the generative AI models. These models are implemented and validated to standardize vast amounts of inspection data extracted from 2255 inspection reports spanning five years (2018–2022) for a set of bridges in Québec, Canada. The fine-tuned model is found to outperform other models in terms of performance, stability, and reliability in detecting and standardizing the severity of different types of concrete defects in bridge decks. It achieves accuracy rates of 98.79 % for corrosion of reinforcing bars, 99.09 % for concrete delamination, and 98.64 % for cracking, scaling, and spalling of concrete. This paper demonstrates the potential for integrating generative AI into infrastructure asset management, an application that has yet to be realized.
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.
How this classification was reachedexpand
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".