Where infrared.city fits
3,204,804 simulations run on Infrared Core (as of 29 Oct 2026).
infrared.city runs 12 models from one engine, Infrared Core, among them wind, wind comfort, sun, daylight, radiant heat and felt heat (UTCI). It works on real 3D building and terrain meshes, in a browser app, through an API and SDK, and in plugins for Grasshopper, QGIS and ArcGIS. Felt heat for 1 km² takes about 5 s once the geometry is uploaded, and 400 km² took 44 s as four 100 km² runs in parallel. Run times are not like for like across tools: area, grid, simulated hours and physics differ. Sun, sky and radiant heat come from ray tracing. Wind comes from an AI model trained on CFD results, not from a CFD run for each request. The live layer runs a whole city every hour on a forecast. It is a climate layer: it brings the simulation results, not the twin itself.
- You need the heat a person feels on a 1 m grid, in a street, between buildings.
- You need wind comfort, sun and daylight for the buildings of a city.
- You compare design options before they are built.
Use both
A weather forecast says how hot the region gets. infrared.city turns weather into street-level felt heat and wind for the buildings and streets of a city.
Facts side by side
| infrared.city | NVIDIA Earth-2 | |
|---|---|---|
| What you get | Simulated felt heat (UTCI), radiant heat, wind, sun and shade at street level | Weather forecasts, over 70 variables, up to 15 days ahead |
| Measured or simulated | Simulation, for the city as it is and for design options | AI models for weather forecasting (open models) |
The infrared.city values repeat the full comparison. Each value for NVIDIA Earth-2 comes from the sources below.
Sources
- NVIDIA: Earth-2 , accessed 30 Oct 2026.