Sensor optimization for urban wind estimation with cluster-based probabilistic framework

2025-09-24

AI Summary

To address the uncertainty in wind field estimation for UAV path planning in complex urban environments, this paper proposes a physics-informed sensor placement optimization framework. Methodologically, it integrates computational fluid dynamics (CFD) simulation with machine learning: leveraging Reynolds-number scaling, physics-driven domain decomposition, subdomain clustering for feature representation, and information-entropy-guided multivariate probabilistic modeling—where sensor locations are treated as explicit optimization variables. The algorithm exhibits linear complexity scaling with domain size and supports extrapolation across wind speed conditions. Evaluated on a three-building cluster scenario, the framework significantly reduces uncertainty in wind speed and direction estimation, enabling high-fidelity wind field reconstruction. Key contributions include: (i) the first explicit formulation of sensor positions as tunable optimization variables—overcoming limitations of fixed-layout paradigms; and (ii) simultaneous attainment of physical interpretability, computational scalability, and cross-condition generalizability—establishing a new paradigm for city-scale wind sensing and meteorology-UAV co-awareness.

Technology Category

• Planning, Routing, and Scheduling: Planning under Uncertainty
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We propose a physics-informed machine-learned framework for sensor-based flow estimation for drone trajectories in complex urban terrain. The input is a rich set of flow simulations at many wind conditions. The outputs are velocity and uncertainty estimates for a target domain and subsequent sensor optimization for minimal uncertainty. The framework has three innovations compared to traditional flow estimators. First, the algorithm scales proportionally to the domain complexity, making it suitable for flows that are too complex for any monolithic reduced-order representation. Second, the framework extrapolates beyond the training data, e.g., smaller and larger wind velocities. Last, and perhaps most importantly, the sensor location is a free input, significantly extending the vast majority of the literature. The key enablers are (1) a Reynolds number-based scaling of the flow variables, (2) a physics-based domain decomposition, (3) a cluster-based flow representation for each subdomain, (4) an information entropy correlating the subdomains, and (5) a multi-variate probability function relating sensor input and targeted velocity estimates. This framework is demonstrated using drone flight paths through a three-building cluster as a simple example. We anticipate adaptations and applications for estimating complete cities and incorporating weather input.

Problem

• Estimating wind flow for drone paths in complex urban environments
• Optimizing sensor placement to minimize velocity estimation uncertainty
• Developing scalable framework that extrapolates beyond training wind conditions

Innovation

• Scales proportionally to domain complexity
• Extrapolates beyond training data
• Sensor location as free input