MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

TL;DR

MetroGAN is a novel GAN framework that incorporates geographical knowledge and hierarchical learning to effectively simulate urban morphology, overcoming data sparsity and training instability issues in urban modeling.

Contribution

The paper introduces MetroGAN, a GAN-based model with geographical constraints and progressive learning, improving urban morphology simulation accuracy and stability.

Findings

Outperforms state-of-the-art methods by over 20% in all metrics.

Effectively generates city shapes using only physical geography features.

Addresses instability issues in urban GAN training.

Abstract

Simulating urban morphology with location attributes is a challenging task in urban science. Recent studies have shown that Generative Adversarial Networks (GANs) have the potential to shed light on this task. However, existing GAN-based models are limited by the sparsity of urban data and instability in model training, hampering their applications. Here, we propose a GAN framework with geographical knowledge, namely Metropolitan GAN (MetroGAN), for urban morphology simulation. We incorporate a progressive growing structure to learn hierarchical features and design a geographical loss to impose the constraints of water areas. Besides, we propose a comprehensive evaluation framework for the complex structure of urban systems. Results show that MetroGAN outperforms the state-of-the-art urban simulation methods by over 20% in all metrics. Inspiringly, using physical geography features singly, MetroGAN can still generate shapes of the cities. These results demonstrate that MetroGAN solves the instability problem of previous urban simulation GANs and is generalizable to deal with various urban attributes.