Hybrid CFD-Deep Learning Approach for Urban Wind Flow Predictions and Risk-Aware UAV Path Planning
Open Access
Abstract
We present a CFD-driven surrogate modeling framework that integrates a Convolutional Autoencoder (CAE) with a Deep Neural Network (DNN) for the rapid prediction of urban wind environments and their subsequent use in UAV trajectory planning. A Reynolds-Averaged Navier–Stokes (RANS) CFD database is generated, parameterized by boundary-condition descriptors, to train the surrogate for velocity magnitude and turbulent kinetic energy (TKE). The CAE compresses horizontal flow fields into a low-dimensional latent space, providing an efficient representation of complex flow structures. The DNN establishes a mapping from input descriptors to the latent space, and flow reconstructions are obtained through the frozen decoder. Validation against CFD demonstrates that the surrogate captures velocity gradients and TKE distributions with mean absolute errors below 1% in most of the domain, while residual discrepancies remain confined to near-wall regions. The approach yields a computational speed-up of approximately 4000× relative to CFD, enabling deployment on embedded or edge hardware. For path planning, the domain is discretized as a k-Non-Aligned Nearest Neighbors (k-NANN) graph, and an A* search algorithm incorporates heading constraints and surrogate-based TKE thresholds. The integrated pipeline produces turbulence-aware, dynamically feasible trajectories, advancing the integration of high-fidelity flow predictions into urban air mobility decision frameworks.Keywords
This publication has 29 references indexed in Scilit:
- Challenges in urban air mobility implementation: A comparative analysis of barriers in Germany and the United StatesJournal of Air Transport Management, 2025
- Multi-fidelity Bayesian neural networks for aerodynamic data fusion with heterogeneous uncertaintiesComputer Methods in Applied Mechanics and Engineering, 2024
- Can Urban Air Mobility become reality? Opportunities and challenges of UAM as innovative mode of transport and DLR contribution to ongoing researchCEAS Aeronautical Journal, 2024
- Wind disturbance compensated path-following control for fixed-wing UAVs in arbitrarily strong windsChinese Journal of Aeronautics, 2023
- Energy optimal 3D flight path planning for unmanned aerial vehicle in urban environmentsCEAS Aeronautical Journal, 2023
- A convolutional auto-encoder regression for parametric modeling of mixed convection in concentric annulusInternational Journal of Thermal Sciences, 2023
- An integrated approach to predict scalar fields of a simulated turbulent jet diffusion flame using multiple fully connected variational autoencoders and MLP networksApplied Soft Computing, 2021
- Computational Fluid Dynamics (CFD) modelling of atmospheric dispersion for land-use planning around major hazards sites in Great BritainJournal of Loss Prevention in the Process Industries, 2018
- New inflow boundary conditions for modelling the neutral equilibrium atmospheric boundary layer in computational wind engineeringJournal of Wind Engineering and Industrial Aerodynamics, 2009
- On the use of the k– model in commercial CFD software to model the neutral atmospheric boundary layerJournal of Wind Engineering and Industrial Aerodynamics, 2007