Rapid pedestrian‐level wind field prediction for early‐stage design using Pareto‐optimized convolutional neural networks

Abstract

AbstractTraditional computational fluid dynamics (CFD) methods used for wind field prediction can be time‐consuming, limiting architectural creativity in the early‐stage design process. Deep learning models have the potential to significantly speed up wind field prediction. This work introduces a convolutional neural network (CNN) approach based on the U‐Net architecture, to rapidly predict wind in simplified urban environments, representative of early‐stage design. The process of generating a wind field prediction at pedestrian level is reformulated from a 3D CFD simulation into a 2D image‐to‐image translation task, using the projected building heights as input. Testing on standard consumer hardware shows that our model can efficiently predict wind velocities in urban settings in less than 1 ms. Further tests on different configurations of the model, combined with a Pareto front analysis, helped identify the trade‐off between accuracy and computational efficiency. The fastest configuration is close to seven times faster, while having a relative loss, which is 1.8 times higher than the most accurate configuration. This CNN‐based approach provides a fast and efficient method for pedestrian wind comfort (PWC) analysis, potentially aiding in more efficient urban design processes.