Knowledge Base

Find out about our models and how to use them

 · 2 min read

Wind Model Validation

Our wind model just got a major accuracy upgrade

At infrared.city, we build AI models that predict urban wind speeds fast enough for real-time planning workflows, without waiting days for traditional CFD simulations. Today, we’re sharing results from our latest model, which sets a new accuracy benchmark across a wide range of urban geometries worldwide.

The new model achieves an average Index of Agreement of 0.988 and a mean absolute error of just 0.31 m/s — validated against high-fidelity CFD simulation.


Performance at a glance

MetricValue
Mean Absolute Error (MAE)0.31 m/s
Index of Agreement (IA)0.988

Benchmarked against high-fidelity CFD simulation across diverse urban scenarios.

IA of 1.0 = perfect match.


What we’re predicting

The model takes an encoded urban geometry and outputs a full wind speed field at pedestrian level. No location-specific tuning required: the model generalises across urban typologies globally, from dense street grids to sprawling mid-rise districts.

image


How we validated it

We compared predictions against CFD simulations across diverse urban scenarios. Each case was evaluated on two metrics:

  • MAE — mean absolute wind speed error in m/s
  • Index of Agreement — measures how closely the predicted spatial pattern matches the reference simulation, capturing both magnitude and distribution accuracy

image


Speed, without sacrificing accuracy

Traditional CFD simulations can take hours to set up and run. Our model delivers comparable spatial accuracy in seconds, making it practical for iterative design, early-stage masterplanning, and large-scale urban analysis.

image

image

image

image


What comes next

We’re continuing to push accuracy further and expand validation coverage. If you’re working on wind comfort assessments, pedestrian safety, or urban microclimate analysis — we’d love to talk.

Recent Articles

Pedestrian Wind Comfort Impact Study

This case study explores how tower massing shapes pedestrian wind comfort. By comparing five design scenarios in Hong Kong, real-time simulations highlight the balance between buildable area and comfort, guiding early-stage decisions with measurable insights.

SvN Architects + Planners: Optimizing Urban Wind Comfort through AI-Driven Design

Learn how to post-process wind simulation results from infrared.city. Follow step-by-step instructions to load your project, connect custom geometry, define wind speed thresholds, and visualize performance interactively.