Enregistré dans:
Détails bibliographiques
Auteurs principaux: Perini, Janne, Bischof, Rafael, Arar, Moab, Duran, Ayça, Kraus, Michael A., Mishra, Siddhartha, Bickel, Bernd
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.21210
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917381785255936
author Perini, Janne
Bischof, Rafael
Arar, Moab
Duran, Ayça
Kraus, Michael A.
Mishra, Siddhartha
Bickel, Bernd
author_facet Perini, Janne
Bischof, Rafael
Arar, Moab
Duran, Ayça
Kraus, Michael A.
Mishra, Siddhartha
Bickel, Bernd
contents Designing urban spaces that provide pedestrian wind comfort and safety requires time-resolved Computational Fluid Dynamics (CFD) simulations, but their current computational cost makes extensive design exploration impractical. We introduce WinDiNet (Wind Diffusion Network), a pretrained video diffusion model that is repurposed as a fast, differentiable surrogate for this task. Starting from LTX-Video, a 2B-parameter latent video transformer, we fine-tune on 10,000 2D incompressible CFD simulations over procedurally generated building layouts. A systematic study of training regimes, conditioning mechanisms, and VAE adaptation strategies, including a physics-informed decoder loss, identifies a configuration that outperforms purpose-built neural PDE solvers. The resulting model generates full 112-frame rollouts in under a second. As the surrogate is end-to-end differentiable, it doubles as a physics simulator for gradient-based inverse optimization: given an urban footprint layout, we optimize building positions directly through backpropagation to improve wind safety as well as pedestrian wind comfort. Experiments on single- and multi-inlet layouts show that the optimizer discovers effective layouts even under challenging multi-objective configurations, with all improvements confirmed by ground-truth CFD simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21210
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
Perini, Janne
Bischof, Rafael
Arar, Moab
Duran, Ayça
Kraus, Michael A.
Mishra, Siddhartha
Bickel, Bernd
Machine Learning
Computational Engineering, Finance, and Science
Designing urban spaces that provide pedestrian wind comfort and safety requires time-resolved Computational Fluid Dynamics (CFD) simulations, but their current computational cost makes extensive design exploration impractical. We introduce WinDiNet (Wind Diffusion Network), a pretrained video diffusion model that is repurposed as a fast, differentiable surrogate for this task. Starting from LTX-Video, a 2B-parameter latent video transformer, we fine-tune on 10,000 2D incompressible CFD simulations over procedurally generated building layouts. A systematic study of training regimes, conditioning mechanisms, and VAE adaptation strategies, including a physics-informed decoder loss, identifies a configuration that outperforms purpose-built neural PDE solvers. The resulting model generates full 112-frame rollouts in under a second. As the surrogate is end-to-end differentiable, it doubles as a physics simulator for gradient-based inverse optimization: given an urban footprint layout, we optimize building positions directly through backpropagation to improve wind safety as well as pedestrian wind comfort. Experiments on single- and multi-inlet layouts show that the optimizer discovers effective layouts even under challenging multi-objective configurations, with all improvements confirmed by ground-truth CFD simulations.
title Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2603.21210