Urban Mobility Digital Twin

The road network with junctions and signal control, public-transport lines for rail, metro and bus, parking facilities and land use are built from open map data and municipal GIS for any administrative area.

Traffic cameras, navigation-app speed and travel-time data, roadside counters and IoT vehicle sensors, transit schedules and origin–destination surveys are ingested into one model. Every figure is labelled as measured, calibrated or estimated.

Automatic traffic analysis zones; demand from gravity models, uploaded origin–destination matrices, or a graph neural network that recovers demand from observed traffic.

Edit roads and junctions, lines and headways, developments, parking supply and price, and policy levers such as congestion charging, access restrictions, transit frequency and fuel pricing. Every change is a reversible, reproducible scenario.

Staged simulation pipeline with fixed seeds, replications, confidence intervals, background jobs and gridlock detection, so results are statistically comparable between scenarios.

Layer one reports speed, queue length, waiting time, travel time, throughput and density per link. Layer two derives fuel, CO₂, NOx, particulate and CO emissions and cost with speed-dependent, fleet-weighted factors, annualised with the method attached.

Line capacity and crowding, logit mode choice with capacity feedback, parking cruising and pricing, land-use developments, a recommendation engine and parametric infrastructure costing with utility-conflict alarms.

Live map with particle flow, 3D congestion columns and a 24-hour timeline; before/after comparison; per-zone reports and executive decision briefs; role-based approval; exports to PDF, CSV, GeoJSON and Shapefile; an assistant grounded in scenario results; cloud or on-premises.