Using Machine Learning to Predict Urban Canopy Flows for Land Surface Modeling

Abstract

Developing urban land surface models for modeling cities at high resolutions needs to better account for the city-specific multi-scale land surface heterogeneities at a reasonable computational cost. We propose using an encoder-decoder convolutional neural network to develop a computationally efficient model for predicting the mean velocity field directly from urban geometries. The network is trained using the geometry-resolving large eddy simulation results. Systematic testing on urban structures with increasing deviations from the training geometries shows the prediction error plateaus at 15%, compared to errors sharply increasing up to 35% in the null models. This is explained by the trained model successfully capturing the effects of pressure drag, especially for tall buildings. The prediction error of the aerodynamic drag coefficient is reduced by 32% compared with the default parameterization implemented in mesoscale modeling. This study highlights the potential of combining computational fluid dynamics modeling and machine learning to develop city-specific parameterizations.