AI case study

University of MichiganUrban flow simulation

Simulations were stuck in 2D and took hours. Physics-informed AI now models 3D urban airflow in seconds.

Published|1 month ago

Key results

Simulation Capability
3D
vs 2D modeling

Result highlights

Unlock 2 result highlights

The story

Context

An aerospace engineering research laboratory focused on fluid mechanics and urban airflow simulations for climate resilience.

Challenge

Traditional computational fluid dynamics methods forced a trade-off between accuracy and speed, restricting models to 2D planes that could not...

Solution
Unlock full story

Scope & timeline

  • 10x faster model training

Quotes

Unlock 1 more quote

The company

University of Michigan logo

University of Michigan

umich.edu

Public research university with comprehensive academic and graduate programs.

IndustryGovernment & Public Sector
LocationAnn Arbor, MI, USA
Employees10K-50K
Founded1817

The vendor

NVIDIA is a technology company that specializes in semiconductors, graphics processing units, and artificial intelligence for applications in data centers, gaming, and more.

IndustryTechnology
LocationSanta Clara, California, United States
Employees10K-50K
Founded1993

The implementation partner

Finnish Center for Artificial Intelligence (FCAI) logo

Finnish Center for Artificial Intelligence (FCAI)

fcai.fi
Role in this case study

Provided hands-on engineering assistance for NVIDIA frameworks to the VinuesaLab research team.

IndustryEducation & Training
LocationEspoo, Finland
Employees51-250
Founded2018

Similar Case Studies

Related implementations across industries and use cases

43 AI case studies in Autonomous Systems

121 AI case studies in Government & Public Sector

1,425 AI case studies in Product Engineering