Examining Spatial Transferability of Direct-Demand Models for Estimating Cyclist Counts at Intersections
Bibliographic record
Abstract
Jurisdictions need estimates of bicycle activity levels for road safety and infrastructure planning studies. When counts are not available, direct-demand (DD) models can be used to estimate bicycle activity (often as annual average daily bicycle [AADB] counts) as a function of demographic and network data. However, not all jurisdictions have sufficient count data or resources to develop their own DD model and would benefit from applying a DD model developed in another jurisdiction. However, there is little prior evidence of the spatial transferability performance of DD models or of the factors that affect spatial transferability performance. This paper addresses this gap. The spatial transferability of five DD models from the literature was evaluated across four target jurisdictions: the City of Toronto, the City of Milton, and the Region of Waterloo in Canada, and Pima County, AZ, USA. True AADB data from continuous counts were available for all four target jurisdictions. Spatial transferability was quantified using four metrics. Results demonstrated generally poor spatial transferability, with root mean squared errors (RMSE) up to 600 times higher than those reported in the original model development data sets. Moreover, analysis showed only moderate correlation between model accuracy and the similarity of the target and development jurisdictions (both for average levels of cycling activity and site and network characteristics). These findings underscore a pressing need for enhanced methods to improve the spatial transferability of DD models for estimating bicycle counts.
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 | 0.018 | 0.071 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".