Technology Category
Search and Optimization: Learning to SearchPlanning, Routing, and Scheduling: Learning for Planning and SchedulingMachine Learning: Learning with Manifolds
Generalization of Urban Wind Environment Using Fourier Neural Operator Across Different Wind Directions and Cities
🤖 AI Summary
To address the trade-off between high accuracy and low computational cost in urban wind environment modeling, this paper proposes an efficient wind field prediction method based on the Fourier Neural Operator (FNO). Methodologically, we introduce a novel patch-based training strategy to enhance multi-scale frequency feature learning and incorporate Signed Distance Functions (SDFs) to explicitly encode building boundaries, thereby improving physical consistency and generalization across wind directions and urban layouts. The model is trained end-to-end using Large Eddy Simulation (LES) data as supervision. Experiments demonstrate that our approach achieves CFD-level prediction accuracy while reducing computational time by 99%, significantly outperforming existing data-driven models. It exhibits strong robustness and practicality across diverse wind directions and urban morphologies. This work provides a scalable, high-performance alternative for urban planning, pollutant dispersion simulation, and wind energy assessment.
Technology Category
Application Category
📝 Abstract
Simulation of urban wind environments is crucial for urban planning, pollution control, and renewable energy utilization. However, the computational requirements of high-fidelity computational fluid dynamics (CFD) methods make them impractical for real cities. To address these limitations, this study investigates the effectiveness of the Fourier Neural Operator (FNO) model in predicting flow fields under different wind directions and urban layouts. In this study, we investigate the effectiveness of the Fourier Neural Operator (FNO) model in predicting urban wind conditions under different wind directions and urban layouts. By training the model on velocity data from large eddy simulation data, we evaluate the performance of the model under different urban configurations and wind conditions. The results show that the FNO model can provide accurate predictions while significantly reducing the computational time by 99%. Our innovative approach of dividing the wind field into smaller spatial blocks for training improves the ability of the FNO model to capture wind frequency features effectively. The SDF data also provides important spatial building information, enhancing the model's ability to recognize physical boundaries and generate more realistic predictions. The proposed FNO approach enhances the AI model's generalizability for different wind directions and urban layouts.
Problem
Research questions and friction points this paper is trying to address.
Wind Field Prediction
Computational Efficiency
Urban Planning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Fourier Neural Operator
Large Eddy Simulation
Wind Field Prediction
🔎 Similar Papers
No similar papers found.
