analiza aiqbench
Diff-SPORT leverages generative diffusion models to solve a critical bottleneck in urban fluid dynamics by enabling near-real-time reconstruction of turbulent flows from sparse sensor data. This approach significantly outperforms traditional RANS or LES simulations in speed and accuracy while using Shapley-value attribution to identify optimal, physically interpretable sensor configurations. The framework's ability to generalize across different datasets without retraining offers a scalable solution for air quality monitoring and resilient city design.
Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments
arXiv:2506.00214v2 Announce Type: replace-cross Abstract: Rapid urbanization demands efficient monitoring of turbulent wind and pollutant dispersion, yet existing reconstruction and sensor placement strategies fail under realistic sparsity constraints. Here, we introduce Diff--SPORT, a diffusion-based framework that combines a generative diffusion prior with maximum a posteriori inference and Shapley-value attribution for high-fidelity flow reconstruction and optimal sensor placement. By training a diffusion prior model once over a domain, Diff--SPORT enables non-linear optimal sensor placement and near-real-time flow reconstruction from sparse measurements orders of magnitude faster than RANS or LES simulations, consistently outperforming state-of-the-art methods. The framework also extends, without algorithmic modification, to experimental passive scalar concentration dataset, a direct proxy for pollutant dispersion, measured in a 1:2400 scale water-flume model of the Beijing Haidian neighbourhood under realistic urban flow conditions. Shapley-guided sensor placement achieves up to 57\% lower reconstruction error than randomly placed sensors at extreme sparsity, identifying compact and physically interpretable configurations. These results establish Diff--SPORT as a modular foundation offering a zero-shot alternative to retraining-intensive downstream strategies, supporting scalable urban flow monitoring for air quality management and resilient city design.
Authors:Abhijeet Vishwasrao, Sai Bharath Chandra Gutha, Andres Cremades, Klas Wijk, Aakash Patil, H.D. Lim, Christina Vanderwel, Catherine Gorle, Beverley J McKeon, Hossein Azizpour, Ricardo Vinuesa
Abstract:Rapid urbanization demands efficient monitoring of turbulent wind and pollutant dispersion, yet existing reconstruction and sensor placement strategies fail under realistic sparsity constraints. Here, we introduce Diff--SPORT, a diffusion-based framework that combines a generative diffusion prior with maximum a posteriori inference and Shapley-value attribution for high-fidelity flow reconstruction and optimal sensor placement. By training a diffusion prior model once over a domain, Diff--SPORT enables non-linear optimal sensor placement and near-real-time flow reconstruction from sparse measurements orders of magnitude faster than RANS or LES simulations, consistently outperforming state-of-the-art methods. The framework also extends, without algorithmic modification, to experimental passive scalar concentration dataset, a direct proxy for pollutant dispersion, measured in a 1:2400 scale water-flume model of the Beijing Haidian neighbourhood under realistic urban flow conditions. Shapley-guided sensor placement achieves up to 57\% lower reconstruction error than randomly placed sensors at extreme sparsity, identifying compact and physically interpretable configurations. These results establish Diff--SPORT as a modular foundation offering a zero-shot alternative to retraining-intensive downstream strategies, supporting scalable urban flow monitoring for air quality management and resilient city design.
Fluid Dynamics (physics.flu-dyn); Artificial Intelligence (cs.AI)
arXiv:2506.00214 [physics.flu-dyn]
(or arXiv:2506.00214v2 [physics.flu-dyn] for this version)
Text integral sub licența deschisă a publicației · 215 cuvinte
Subiecte conexe
Observability-Informed Optimal Sensor Placement for Soft Robots
arXiv · 29 sept. 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · 13 oct. 2026
Flow Reconstruction from Sparse Measurements in Urban Drainage Networks: An Application and Evaluation of Data-Driven Sparse Sensing
arXiv · 28 sept. 2026
Fiber sensor tracks 3D shapes with tiny, laser-cut parts
Quantum Zeitgeist · 22 aug. 2026