U-Net prediction of urban flow and pollutant dispersion: example CFD and code
Simulation 10 GB
Example CFD simulation and code for distributed training of a U-Net predicting urban aerodynamic flow and pollutant dispersion. Useful for ML surrogates of urban flow.
- Resource
- Simulation output, Software & tools
- Method
- ML / surrogate, RANS
- Geometry
- Realistic neighbourhood
- Topic
- Dispersion & air quality
- Quantities
- Velocity, Concentration
- Data volume
- 10.2 GB
- Year
- 2026
- Licence
- CC BY 4.0
- Creators
- Alejandro González; Castillo Catalán, María Isabel; chiva, sergio; Iserte, Sergio
- Institution
- Barcelona Supercomputing Center; Universitat Jaume I
From Zenodo, added 2026-11-07. Listed there as “Distributed Training of U-Net Architecture for Data-Driven Aerodynamic Flow and Pollutant Dispersion Prediction in Urban Environments - DATASET”. Tags proposed by AI and not yet checked by hand. Spotted a mistake? Tell the portal contacts.