From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions

• URL: http://arxiv.org/abs/2507.06533v1
• Date: Wed, 09 Jul 2025 04:25:13 GMT
• Title: From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions
• Abstract summary: This study presents a deep neural network (DNN) approach for fast and accurate predictions of urban wind flow fields.<n>We employ a U-Net architecture trained on LES data including 252 synthetic urban configurations at seven wind directions.<n>Model evaluation on 50 test cases demonstrates high accuracy with an overall mean relative error of 9.3% for velocity magnitude and 5.2% for turbulence intensity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Accurate prediction of wind flow fields in urban canopies is crucial for ensuring pedestrian comfort, safety, and sustainable urban design. Traditional methods using wind tunnels and Computational Fluid Dynamics, such as Large-Eddy Simulations (LES), are limited by high costs, computational demands, and time requirements. This study presents a deep neural network (DNN) approach for fast and accurate predictions of urban wind flow fields, reducing computation time from an order of 10 hours on 32 CPUs for one LES evaluation to an order of 1 second on a single GPU using the DNN model. We employ a U-Net architecture trained on LES data including 252 synthetic urban configurations at seven wind directions ($0^{o}$ to $90^{o}$ in $15^{o}$ increments). The model predicts two key quantities of interest: mean velocity magnitude and streamwise turbulence intensity, at multiple heights within the urban canopy. The U-net uses 2D building representations augmented with signed distance functions and their gradients as inputs, forming a $256\times256\times9$ tensor. In addition, a Spatial Attention Module is used for feature transfer through skip connections. The loss function combines the root-mean-square error of predictions, their gradient magnitudes, and L2 regularization. Model evaluation on 50 test cases demonstrates high accuracy with an overall mean relative error of 9.3% for velocity magnitude and 5.2% for turbulence intensity. This research shows the potential of deep learning approaches to provide fast, accurate urban wind assessments essential for creating comfortable and safe urban environments. Code is available at https://github.com/tvarg/Urban-FlowUnet.git

Related papers

• Physics-Based Deep Spatiotemporal Hyperlocal Radar Nowcasting with a Multi-Variable U-Net for High-Resolution Precipitation Forecasting [0.0]
  We develop a radar-only nowcasting framework that combines multi-elevation reflectivity, Doppler radial velocity, and radial-velocity-gradient proxy features within an encoder-decoder U-Net.<n>The model is trained using Mumbai Doppler radar observations from May to August 2023 and evaluated on temporally independent events.
  arXiv  Detail & Related papers  (2026-07-17T16:09:48Z)
• Inpainting U-Net for seamless pedestrian-level wind prediction across urban morphologies [4.890956388445967]
  This study develops a two-stage U-Net framework for efficient prediction of pedestrian-level wind speed over realistic urban morphologies.<n>Results show that M1 captures the main spatial distribution of pedestrian-level wind speed and performs well in low- and moderate-velocity regions.<n>Overall, the proposed framework provides an efficient and flexible surrogate model for high-resolution pedestrian-level wind prediction across realistic urban morphologies.
  arXiv  Detail & Related papers  (2026-06-28T15:11:16Z)
• Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model [0.0]
  Long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems.<n>Existing deep learning approaches struggle to maintain prediction stability beyond 48 hours.<n>This paper presents a framework that combines DTW for intelligent station similarity selection with a CNN-GRU architecture.
  arXiv  Detail & Related papers  (2025-10-26T23:04:10Z)
• Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows [15.085995615456019]
  Full-Glowizings (Full-Glowizings) generates standards-compliant urban sound-pressure maps from 2D urban layouts in real time per 256x256 map on a single GTX 4090)<n>On datasets covering Baseline, Diffraction, and Reflection regimes, our model accelerates map generation by >2000 times over a reference solver while improving NLoS accuracy by up to 24% versus prior deep models; in Baseline NLoS we reach 0.65 dB MAE with high structural fidelity.<n>The model reproduces diffraction and interference patterns and supports instant recomputation under source or geometry changes, making it a practical engine for
  arXiv  Detail & Related papers  (2025-10-06T06:00:08Z)
• Deep learning methods for modeling infrasound transmission loss in the middle atmosphere [5.842419815638353]
  We develop an optimized convolutional network designed to minimize prediction errors while predicting TLs from globally simulated combined temperature and wind fields.<n>The implemented model predicts TLs with an average error of 8.6 dB in the whole frequency band (0.1-3.2 Hz) and explored realistic atmospheric scenarios.
  arXiv  Detail & Related papers  (2025-06-02T13:10:29Z)
• Multi-Source Urban Traffic Flow Forecasting with Drone and Loop Detector Data [61.9426776237409]
  Drone-captured data can create an accurate multi-sensor mobility observatory for large-scale urban networks.<n>A simple yet effective graph-based model HiMSNet is proposed to integrate multiple data modalities and learn-temporal correlations.
  arXiv  Detail & Related papers  (2025-01-07T03:23:28Z)
• Application of Long-Short Term Memory and Convolutional Neural Networks for Real-Time Bridge Scour Prediction [0.0]
  We exploit the power of deep learning algorithms to forecast scour depth variations around bridge piers based on historical sensor monitoring data. We investigated the performance of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) models for real-time scour forecasting.
  arXiv  Detail & Related papers  (2024-04-25T12:04:36Z)
• Rapid Flood Inundation Forecast Using Fourier Neural Operator [77.30160833875513]
  Flood inundation forecast provides critical information for emergency planning before and during flood events. High-resolution hydrodynamic modeling has become more accessible in recent years, however, predicting flood extents at the street and building levels in real-time is still computationally demanding. We present a hybrid process-based and data-driven machine learning (ML) approach for flood extent and inundation depth prediction.
  arXiv  Detail & Related papers  (2023-07-29T22:49:50Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• FastFlow: AI for Fast Urban Wind Velocity Prediction [0.0]
  We present the use of CNNs for urban layout characterization that is typically done via high-fidelity numerical simulation. We apply this model towards a first demonstration of its utility for data-driven pedestrian-level wind velocity prediction.
  arXiv  Detail & Related papers  (2022-11-22T06:13:48Z)
• Efficient Traffic State Forecasting using Spatio-Temporal Network Dependencies: A Sparse Graph Neural Network Approach [6.203371866342754]
  Traffic prediction in a transportation network is paramount for effective traffic operations and management. Long-term traffic prediction (beyond 30 minutes into the future) remains challenging in current research. We propose sparse training to the training cost, while preserving the prediction accuracy.
  arXiv  Detail & Related papers  (2022-11-06T05:41:39Z)
• Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach [76.45949280328838]
  We propose a Laplacian enhanced low-rank tensor (LETC) framework featuring both lowrankness and multi-temporal correlations for large-scale traffic speed kriging. We then design an efficient solution algorithm via several effective numeric techniques to scale up the proposed model to network-wide kriging.
  arXiv  Detail & Related papers  (2022-10-21T07:25:57Z)
• Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet [2.568084386350801]
  The aim is to build a machine learning model for predicting the normalized average traffic speed and flow of subregions of multiple-scale cities using historical data points. We explore 3DRparseNetes and Sparse-UNet approaches for the tasks in this competition. Our results show that both of the proposed models achieve much better performance than the baseline algorithms.
  arXiv  Detail & Related papers  (2021-11-10T23:40:52Z)
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining [58.10436813430554]
  Mini-batch training of graph neural networks (GNNs) requires a lot of computation and data movement. We argue in favor of performing mini-batch training with neighborhood sampling in a distributed multi-GPU environment. We present a sequence of improvements to mitigate these bottlenecks, including a performance-engineered neighborhood sampler. We also conduct an empirical analysis that supports the use of sampling for inference, showing that test accuracies are not materially compromised.
  arXiv  Detail & Related papers  (2021-10-16T02:41:35Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.