Next meeting 14th UFM Meeting · 23 Mar 2027 · Bristol Save the date →
Urban Fluid MechanicsSpecial Interest Group

PTSWO: fast surrogate for near-surface winds over urban surfaces and terrain

Simulation

Data and scripts for a fast surrogate wind model over heterogeneous urban surfaces and terrain. Useful for rapid urban wind simulation.

Get the data

Zenodo DOI 10.5281/zenodo.24006055
Licence
CC BY 4.0 Free to use and share, including commercially, as long as you credit the creators.

How to cite

Liu, Z., Li, W., Zhong, X., Zhang, C., Han, W., Zhang, Y., Liu, J., & Hu, J. (2026). A Physics-Trained Surface-Forced Wind Operator (PTSWO v1.0) for Fast Simulation of Near-Surface Winds over Heterogeneous Urban Surfaces and Terrain [Data set]. Zenodo. https://doi.org/10.5281/zenodo.24006055

Check the repository for the citation its authors prefer.

Details

Resource
Software & tools, Simulation output
Method
ML / surrogate
Geometry
City scale
Topic
Urban boundary layer
Quantities
Velocity, Wind profile
Year
2026
Creators
Liu, Zhenxin; Li, Weimin; Zhong, Xuanhui; Zhang, Chao; Han, Wei; Zhang, Yi; Liu, Jia; Hu, Jianlin

Related resources

  1. DNS of urban turbulent flow for sensor placement and reconstruction (Diff-SPORT)

    36 GB

    Data for diffusion-based sensor placement and reconstruction of turbulent flows in urban environments from DNS. Useful for ML reconstruction.

    Simulation Simulation output DNSML / surrogate

    2026 · CC BY 4.0 · Paper: Causality analysis of large-scale structures in the flow around a wall-mounted square cylinder ↗

  2. Flow simulations around randomly generated urban geometries (Random Buildings)

    3.6 GB

    Dataset of microscale atmospheric flow simulations around randomly generated urban geometries for several stability classes. Useful for training and testing ML surrogates of urban flow.

    Simulation Simulation output RANSML / surrogate

    2026 · MIT

  3. Diff-SPORT: diffusion-based sensor placement and reconstruction of urban turbulent flow

    2 MB

    Code for diffusion-based sensor placement and reconstruction of turbulent flows in urban environments. Useful for flow reconstruction and sensor design.

    Simulation Software & tools ML / surrogate

    2026 · MIT

  4. LES of urban canopy flow with U-Net predictions

    50 MB

    LES velocity fields over urban canopies with inputs and U-net predicted fields, including perturbed cases. Useful for training and testing ML surrogates of urban flow.

    Simulation Simulation output LESML / surrogate

    2022 · CC BY

  5. Street-level weather station network, Freiburg

    27 parts

    Harmonised data from a street-level network of 42 automatic weather stations in Freiburg for 2022. Useful for intra-urban temperature and wind variability.

    Collection · 27 parts Field Measurements

    Freiburg, Germany · 2026 · CC BY 4.0 · Paper: Using Gradient Boosting for gap-filling to analyze temperature and humidity patterns in an urban weather station network in Freiburg, Germany ↗ +2

  6. urbisphere Doppler wind lidar: Paris

    11 parts

    Raw Doppler wind lidar measurements at the Paris-region site Arboretum Vallee-aux-Loups from the urbisphere campaign. Useful for urban boundary-layer wind and turbulence profiles.

    Collection · 11 parts Field Measurements

    Paris, France · 2025 · Restricted · Paper: Harmonised boundary layer wind profile dataset from six ground-based doppler wind lidars in a transect across Paris, France ↗ +2

All 101 resources on urban boundary layer →

From Zenodo, added 2026-11-07. Listed there as “A Physics-Trained Surface-Forced Wind Operator (PTSWO v1.0) for Fast Simulation of Near-Surface Winds over Heterogeneous Urban Surfaces and Terrain”. Tags proposed by AI and not yet checked by hand. Spotted a mistake? Tell the portal contacts.