What question did this study set out to answer?

The aim is to automate computational fluid dynamics simulations to investigate vortex state transitions in urban street canyons.

Vortex state transitions in deep street canyons enabled by an automated large language model workflow

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved vortex dynamics in urban canyons, suggesting automation enhances simulation capabilities.

The aim is to automate computational fluid dynamics simulations to investigate vortex state transitions in urban street canyons.
Employs a large language model (LLM)-based framework, Auto-Fluent, for automated CFD workflows.
Investigates vortex-regime transitions in deep canyons with aspect ratios H/W = 3–5 under varying upstream fetches.
Conducts simulations from geometry construction to solver setup based on natural language inputs.
Initial upstream canyons show vertically stacked recirculation structures, with up to four vortices for H/W = 5.
As fetch increases, vortices merge into a single dominant clockwise vortex after five to six canyons.
The primary recirculation center descends, significantly enhancing pedestrian-level ventilation.

Peng et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark