CityTransformer: A Transformer-Based Model for Contaminant Dispersion Prediction in a Realistic Urban Area

We develop a Transformer-based deep learning model to predict the plume concentrations in the urban area in statistically stationary flow conditions under a stationary and homogeneous forcing. Our model has two distinct input layers: Transformer layers for sequential data and convolutional layers in convolutional neural networks for image-like data. Our model can predict the plume concentration from realistically available data such as the time series monitoring data at a few observation stations, and the building shapes and the source location. It is shown that the model can give reasonably accurate prediction in less than a second. It is also shown that exactly the same model can be applied to predict the source location and emission rate, which also gives reasonable prediction accuracy.