Bring measures together
Import simple CSV files for speeds, demand volumes, output trips, travel times, weather severities, and incident crashes.
Bring locations, times, and days into one analytical view. Explore traffic performance alongside demand, weather, and incidents.
Free to download and use · Windows desktop application
For traffic engineers, transportation agencies, researchers, and consultants who need to understand how conditions change across space and time.
Import simple CSV files for speeds, demand volumes, output trips, travel times, weather severities, and incident crashes.
Inspect heat maps and cube views. Move between measures using shared location, time, and date or simulation-seed dimensions.
Use basic statistics, congestion episode screening, clustering, and representative-day analysis to examine operating conditions.
TrafficCube complements established traffic modeling tools, large commercial online analytics platforms, and agency-hosted data environments.
Those larger platforms can provide integrated data feeds, enterprise workflows, and ongoing network management. TrafficCube offers a lightweight desktop environment for focused studies: organizing multisource data, inspecting patterns, and applying repeatable analytical methods across locations, time intervals, days, and simulation runs.
Its niche is to make spatiotemporal analysis more accessible to agencies, consultants, and researchers, while providing a practical setting to examine and test methods that could later be incorporated into larger systems.
Data analytics tools like TrafficCube can help analysts understand traffic network conditions and define spatiotemporal analysis limits: the roadway extent, times of day, and operating conditions that a study should capture.
Use structured observed and simulated data to support verification, calibration, and validation (VC&V) of traffic modeling tools. Examine where model results agree with field conditions and where further investigation or adjustment is needed.
Data analytics can support before-and-after analysis of transportation investments and system monitoring over time. Compare similar operating conditions, examine localized effects, and identify changes that warrant closer attention.
These roles describe the broader value of data analytics across the project lifecycle. TrafficCube’s available functions and planned developments are described separately below; automated real-time monitoring is a future application.
Examine speed and travel-time patterns alongside potential contributing conditions. Look for upstream effects and congestion that persists into later intervals.
Start with the included two-week demonstration data, then explore optional full-year datasets. The synthetic examples provide a controlled environment for learning the workflow.
Explore full-year sample data ↗TrafficCube supports a workflow from multisource data preparation to clustering, representative-day selection, and variation and calibration envelopes.
Compare observed and simulated traffic measures within a consistent analytical framework. Use the results to guide further investigation and calibration decisions.
An evolving implementation: review the technical paper and release information for scope and limitations.
The application runs on your Windows computer. GitHub hosts the software downloads, sample datasets, and release instructions.
Open the software release page and download TrafficCube.zip. Check the release instructions for installation details.
Before extracting, right-click the ZIP and choose Properties → Unblock, if shown. Extract it and run TrafficCube.Desktop.exe.
Choose Open in TrafficCube and select one or several demo files. Use the examples to prepare your own CSV datasets.
Software release linked in this draft: October 11, 2026.
Explore TrafficCube’s data structure, analytical approach, example applications, and development vision.
October 2026 technical paper ↗Bug reports, feature requests, sample datasets, and technical assistance requests are welcome.
Contact David Hale ↗Planned work includes similarity searches, contributing-factor analysis, machine learning, short-term prediction, and AI-assisted traffic analysis insights. These are development directions, rather than a list of available features.
Follow development on GitHub ↗