Roads Management Insights concepts

The Roads Management Insights data models are built by combining different information sources to provide insights into road congestion.

Road congestion

The Roads Management Insights data models for trip duration and speed reading are built by combining different information sources:

  • Aggregated maps data: The most critical source is aggregated, anonymized data from Google Maps, which allows Google Maps to calculate the real-time speed of vehicles on roads around the world.

  • Historical traffic data: Over time, the aggregated user data is used to build historical traffic patterns, which help the system understand the "normal" traffic for a specific road at any given time and day of the week.

  • Supplemental data: Historical data is combined with other data, including third-party information from partners like local Departments of Transportation, as well as real-time user feedback from Maps users reporting incidents like crashes or construction.

AI combines these information sources together to understand current conditions with real-time data, and to provide baseline predictions with historical data. This fusion is key for how routes are predicted, for example:

  • Short routes depend largely on current, real-time information
  • Longer routes use advanced AI modeling, where nearby segments are predicted using real-time data, while more-distant segments rely more heavily on historical patterns.
  • Roads with limited real-time signals rely more heavily on its historical data to predict slowdowns.

Speed reading intervals

A speed reading interval (SRI) is a contiguous stretch of a route where traffic falls into a single speed category. Together, a route's speed reading intervals cover the entire route in order from origin to destination.

Speed categories

The speed categories align with the colors shown in the Google Maps traffic layer:

Speed category Google Maps traffic color Description
NORMAL Green Traffic is flowing smoothly; no slowdown is detected.
SLOW Yellow Slowdown is detected, but no traffic jam has formed.
TRAFFIC_JAM Red Traffic jam is detected.
TRAFFIC_JAM_HEAVY Dark red Heavy traffic jam is detected. Available as of October 8, 2026 in offset-based speed reading intervals (speed_reading_offsets) only.

Formats

  • Offset-based speed reading intervals (speed_reading_offsets): Each interval is demarcated by start_offset (inclusive) and end_offset (exclusive), measured in meters from the start of the route. The end_offset of each interval equals the start_offset of the subsequent interval.

    For example, a 100-meter route where the first 80 meters have a slowdown and the remaining 20 meters flow normally is represented as:

    start_offset end_offset speed
    0 80 SLOW
    80 100 NORMAL

  • Coordinate-based speed reading intervals (speed_reading_intervals, legacy): Each interval is defined by polyline coordinates (interval_coordinates). In this format, heavy traffic jams (dark red) are reported as TRAFFIC_JAM; TRAFFIC_JAM_HEAVY is never used. This legacy field might stop being populated on or after November 9, 2026. Use speed_reading_offsets instead.

For schema details, see Real-time road data and the recent_roads_data table.

BigQuery tables

To query the accumulated data for trip duration and speed reading intervals, see the historical_travel_time table and the recent_roads_data table in BigQuery.