# Anchored-Branched Steady-state WInd Flow Transformer (AB-SWIFT): a metamodel for 3D atmospheric flow in urban environments

Source: [Anchored-Branched Steady-state WInd Flow Transformer (AB-SWIFT): a metamodel for 3D atmospheric flow in urban environments](<https://www.sota2.com/research/paper/69c60f3e0636e5bf4afc873b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-28T05:00:12.409Z

Authors: Armand de Villeroch\\'e, Rem-Sophia Mouradi, Vincent Le Guen, Sibo Cheng, Marc Bocquet, Alban Farchi, Patrick Armand, Patrick Massin

Published: 2026-03-26T16:46:54.000Z

## Abstract

Air flow modeling at a local scale is essential for applications such as pollutant dispersion modeling or wind farm modeling. To circumvent costly Computational Fluid Dynamics (CFD) computations, deep learning surrogate models have recently emerged as promising alternatives. However, in the context of urban air flow, deep learning models struggle to adapt to the high variations of the urban geometry and to large mesh sizes. To tackle these challenges, we introduce Anchored Branched Steady-state WInd Flow Transformer (AB-SWIFT), a transformer-based model with an internal branched structure uniquely designed for atmospheric flow modeling. We train our model on a specially designed database of atmospheric simulations around randomised urban geometries and with a mixture of unstable, neutral, and stable atmospheric stratifications. Our model reaches the best accuracy on all predicted fields compared to state-of-the-art transformers and graph-based models. Our code and data is available at https://github.com/cerea-daml/abswift.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Steady-state Wind Flow Prediction on Steady-state Wind Flow Dataset (test)](<https://www.sota2.com/research/sota/steady-state-wind-flow-prediction-on-steady-state-wind-flow-dataset-test.md>): Steady-state Wind Flow Prediction; Steady-state Wind Flow Dataset (test); v NMSE: 0.3.

- [Steady-state Wind Flow Prediction on Wind Flow Prediction Dataset (test)](<https://www.sota2.com/research/sota/steady-state-wind-flow-prediction-on-wind-flow-prediction-dataset-test.md>): Steady-state Wind Flow Prediction; Wind Flow Prediction Dataset (test); Training Time (Epoch): 8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.25635>)

[PDF](<https://arxiv.org/pdf/2603.25635.pdf>)
