Enhancing Road Asset Management with CityGML Enriched by Public Inputs: A Comprehensive Approach to Pothole Repair Prioritization
Bibliographic record
Abstract
Infrastructure asset management involves navigating complex sociotechnical challenges, requiring not only the technical assessment of physical assets but also the timely consideration of end-user satisfaction. This paper presents a novel approach to extracting and documenting asset repair prioritization decisions, emphasizing socioeconomic and demographic factors influencing those decisions. Pothole repair in the Toronto road network is used as a case example with a specific focus on pothole repair prioritization. Traditionally, pothole repairs have been prioritized primarily based on physical factors such as their size and location, and social considerations have been addressed in an unofficial/ad hoc manner, relying on the subjective judgment of decision makers rather than being systematically integrated into the decision-making process. This study proposes a systematic approach utilizing open GIS, specifically integrating technical and social aspects within the road network to uncover hidden patterns in past decisions, which can be applied to future scenarios. This approach is applied in the case study to distill collective knowledge and make informed decisions for prioritizing the potholes to be repaired. In the case study, an extended Geography Markup Language (CityGML) data model was used to link demographic attributes with potholes’ physical and functional characteristics. Statistical machine learning approaches were then applied to correlate such attributes with the priority of pothole repairs in the city of Toronto. To this end, pothole repair data in Toronto between the years 2017 and 2021 were used to train artificial neural networks, support vector machines, and random forest models. By incorporating demographic features, these machine learning models could estimate the urgency of repairing potholes with an accuracy of 74%. Therefore, by fusing physical and functional data with demographic information, the proposed method represents a significant step toward automating the decision process to systematically incorporate both subjective and objective aspects of decisions into a repair prioritization knowledge inference system.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".