Deep learning-based urban morphology for city-scale environmental modeling
PNAS Nexus

Abstract

Herein, we introduce a novel methodology to generate urban morphometric parameters that takes advantage of deep neural networks and inverse modeling. We take the example of Chicago, USA, where the Urban Canopy Parameters (UCPs) available from the National Urban Database and Access Portal Tool (NUDAPT) are used as input to the Weather Research and Forecasting (WRF) model. Next, the WRF simulations are carried out with Local Climate Zones (LCZs) as part of the World Urban Data Analysis and Portal Tools (WUDAPT) approach. Lastly, a third novel simulation, Digital Synthetic City (DSC), was undertaken where urban morphometry was generated using deep neural networks and inverse modeling, following which UCPs are re-calculated for the LCZs. The three experiments (NUDAPT, WUDAPT, and DSC) were compared against Mesowest observation stations. The results suggest that the introduction of LCZs improves the overall model simulation of urban air temperature. The DSC simulations yielded equal to or better results than the WUDAPT simulation. Furthermore, the change in the UCPs led to a notable difference in the simulated temperature gradients and wind speed within the urban region and the local convergence/divergence zones. These results provide the first successful implementation of the digital urban visualization dataset within an NWP system. This development now can lead the way for a more scalable and widespread ability to perform more accurate urban meteorological modeling and forecasting, especially in developing cities. Additionally, city planners will be able to generate synthetic cities and study their actual impact on the environment.

Method

We have developed a novel deep-learning and procedural modeling based method for creating a city-scale 3D urban model, called in this paper Digital Synthetic City (DSC), from which we can derive various urban morphology parameters. Our method uses satellite imagery and global-scale population and elevation data as input to our automatic method for producing a statistically similar and synthetic city-scale 3D urban model as output.

Weather Research & Forecasting Model (WRF) simulations compared to public dataset

Temporal trackings of WRF compared to station observations

BibTeX

@article{10.1093/pnasnexus/pgad027,

    title={Deep learning-based urban morphology for city-scale environmental modeling},

    author={Patel, Pratiman and Kalyanam, Rajesh and He, Liu and Aliaga, Daniel and Niyogi, Dev},

    journal={PNAS Nexus}, 

    volume={2}, 

    number={3}, 

    pages={pgad027},

    year = {2023},

    month = {02},

    issn = {2752-6542},

    doi = {10.1093/pnasnexus/pgad027},

    url = {https://doi.org/10.1093/pnasnexus/pgad027}

  }

The website template was borrowed from Michaël Gharbi.