Open Road Risk
  • Home
  • Project
    • Project overview
    • Current model status
    • AI-assisted development
  • Background
    • Metrics and methodology
    • Literature evidence register
  • Literature
    • Crash frequency models
    • Exposure and traffic volume
    • Spatial methods and network risk
    • Junctions and conflict structure
    • Severity modelling
    • Validation and metrics
    • Transferability and open data limits
  • Data Sources
    • Overview
    • STATS19 Collisions
    • OS Open Roads
    • AADF Traffic Counts
    • WebTRIS Sensors
    • Network Model GDB
  • Methodology
    • Methodology Overview
    • Joining the Datasets
    • Feature Engineering
    • Empirical Bayes Shrinkage
  • Exploratory Data Analysis
    • Collision EDA
    • Collision-Exposure Behaviour
    • Vehicle Mix Analysis
    • Road Curvature
    • Months and Days of Week
    • Traffic Volume EDA
    • OSM Coverage
  • Models
    • Modelling Approach
    • Stage 1a: Traffic Volume
    • Stage 1b: Time-Zone Profiles
    • Stage 2: Collision Risk Model
    • Facility Family Split
    • Model Inventory
  • Outputs
    • Top-risk map
  • Future Work

On this page

  • Interactive Map
  • Summary Tables
  • Data Notes

Top-Risk Road Segments

Interactive screening map for the top 1% highest-risk road links.

This page maps the global top 1% highest-risk road links after controlling for traffic exposure. The ranking uses risk_percentile_eb, the preferred empirical-Bayes-adjusted screening ranking for this output; raw risk_percentile remains available in the source outputs.

These links are screening candidates for inspection, mapping, portfolio review, and demo use. They are not causal proof, crash prediction guarantees, or engineering-audit results. This page uses global EB shrinkage, not the diagnostic family-stitched model, so motorway calibration remains unresolved for this published screening layer. Sparse collision histories should be interpreted cautiously.

The refreshed outputs were reviewed in May 2026 and judged suitable for screening with caveats. Short segments under 50 m are present in the full dataset and map layer; they are flagged for manual review before use as case study examples. Family-level EB outliers are also flagged for later review.

The map colours links by log_predicted_eb = log1p(predicted_eb) rather than by risk_percentile_eb, because the global top-1% percentile values are tightly compressed at the top end. The percentile rank remains available in each popup.

Interactive Map

Loading static GeoJSON…

The map uses client-side multi-select filters over one static GeoJSON file. Values within a filter are combined with OR logic; different filters are combined with AND logic. No selection in a filter means all values for that filter.

Summary Tables

Count by family

Count by road classification

Count by road archetype

Numeric summary

Data Notes

  • Source layer: data/outputs/top_1pct_risk_segments.parquet.
  • Web layer: data/outputs/web/top_1pct_risk_segments.geojson.
  • Context network layers: data/outputs/web/context/context_manifest.json plus split GeoJSON files. Motorway and trunk-A links are shown in full; other_urban and other_rural show the top context percentile by risk_percentile_eb recorded in the manifest.
  • Features: 21,676 road links.
  • GeoJSON size: 14,709,969 bytes.
  • Geometry simplification: 25 m tolerance in EPSG:3857, then written as EPSG:4326 with coordinates rounded to 0.00001 degrees.
  • Colour scaling: log_predicted_eb = log1p(predicted_eb).
  • QA status: reviewed May 2026; suitable for screening with caveats. See reports/top_risk_output_qa.md.
  • Background map: OpenStreetMap tiles, with static project GeoJSON files for the risk and context layers.

Open Road Risk

 

Built with Quarto