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

2025-05-30

AI Summary

To address reconstruction distortion and uninterpretable sensor placement arising from sparse sensing in urban turbulent wind field monitoring, this study proposes the first interpretable co-optimization framework integrating generative diffusion models, maximum a posteriori (MAP) Bayesian inference, and Shapley value attribution. The framework enables zero-shot, modular, and scalable flow field reconstruction and sensor layout design, incorporating physics-guided sampling and sparse observation modeling. Compared to conventional numerical methods, it achieves significantly higher computational efficiency while maintaining high statistical and instantaneous fidelity—even under extremely sparse sensing conditions (<5% sensor density). The approach establishes a new paradigm for high-accuracy, low-cost urban air quality assessment and real-time decision-making for resilient infrastructure.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• Optimizing sensor placement for turbulent urban flow monitoring
• Reconstructing high-fidelity turbulent flows with extreme sparsity
• Integrating generative modeling for scalable urban flow solutions

Innovation

• Diffusion-based framework for urban flow reconstruction
• Combines generative model with MAP inference
• Modular zero-shot alternative to retraining strategies