Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments

TL;DR

Diff-SPORT introduces a diffusion-based method for accurate, fast, and interpretable sensor placement and flow reconstruction in urban environments, addressing limitations of traditional approaches under practical constraints.

Contribution

It combines generative diffusion models with MAP inference and Shapley-value attribution to enable scalable, zero-shot urban flow monitoring without retraining.

Findings

Achieves significant speedups over traditional numerical methods.

Maintains high statistical and instantaneous flow fidelity.

Supports reliable urban flow monitoring under extreme sparsity.

Abstract

Rapid urbanization demands accurate and efficient monitoring of turbulent wind patterns to support air quality, climate resilience and infrastructure design. Traditional sparse reconstruction and sensor placement strategies face major accuracy degradations under practical constraints. Here, we introduce Diff-SPORT, a diffusion-based framework for high-fidelity flow reconstruction and optimal sensor placement in urban environments. Diff-SPORT combines a generative diffusion model with a maximum a posteriori (MAP) inference scheme and a Shapley-value attribution framework to propose a scalable and interpretable solution. Compared to traditional numerical methods, Diff-SPORT achieves significant speedups while maintaining both statistical and instantaneous flow fidelity. Our approach offers a modular, zero-shot alternative to retraining-intensive strategies, supporting fast and reliable urban flow monitoring under extreme sparsity. Diff-SPORT paves the way for integrating generative modeling and explainability in sustainable urban intelligence.