MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

Weiyu Zhang; Yiyang Ma; Di Zhu; Lei Dong; Yu Liu

doi:10.1145/3534678.3539239

MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

Weiyu Zhang, Yiyang Ma, Di Zhu, Lei Dong, Yu Liu

Geography, Environment and Society

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

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.

Original language	English (US)
Title of host publication	KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	2482-2492
Number of pages	11
ISBN (Electronic)	9781450393850
DOIs	https://doi.org/10.1145/3534678.3539239
State	Published - Aug 14 2022
Event	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States Duration: Aug 14 2022 → Aug 18 2022

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/Territory	United States
City	Washington
Period	8/14/22 → 8/18/22

Bibliographical note

Funding Information:
This research was funded by the National Natural Science Foundation of China (41830645, 41971331). Dr. Di Zhu is supported by the Faculty Set-up Funding of College of Liberal Arts, University of Minnesota (1000-10964-20042-5672018).

Publisher Copyright:
© 2022 ACM.

Keywords

generative adversarial networks
urban morphology simulation

Publisher link

10.1145/3534678.3539239

Find It

Find It at U of M Libraries

Cite this

Zhang, W., Ma, Y., Zhu, D., Dong, L., & Liu, Y. (2022). MetroGAN: Simulating Urban Morphology with Generative Adversarial Network. In KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 2482-2492). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/3534678.3539239

MetroGAN : Simulating Urban Morphology with Generative Adversarial Network. / Zhang, Weiyu; Ma, Yiyang; Zhu, Di et al.

KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2022. p. 2482-2492 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, W, Ma, Y, Zhu, D, Dong, L & Liu, Y 2022, MetroGAN: Simulating Urban Morphology with Generative Adversarial Network. in KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, pp. 2482-2492, 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022, Washington, United States, 8/14/22. https://doi.org/10.1145/3534678.3539239

Zhang W, Ma Y, Zhu D, Dong L, Liu Y. MetroGAN: Simulating Urban Morphology with Generative Adversarial Network. In KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2022. p. 2482-2492. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3534678.3539239

Zhang, Weiyu ; Ma, Yiyang ; Zhu, Di et al. / MetroGAN : Simulating Urban Morphology with Generative Adversarial Network. KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2022. pp. 2482-2492 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{8f801071a04046f4ba0b0f7e80be285c,

title = "MetroGAN: Simulating Urban Morphology with Generative Adversarial Network",

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.",

keywords = "generative adversarial networks, urban morphology simulation",

author = "Weiyu Zhang and Yiyang Ma and Di Zhu and Lei Dong and Yu Liu",

note = "Funding Information: This research was funded by the National Natural Science Foundation of China (41830645, 41971331). Dr. Di Zhu is supported by the Faculty Set-up Funding of College of Liberal Arts, University of Minnesota (1000-10964-20042-5672018). Publisher Copyright: {\textcopyright} 2022 ACM.; 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; Conference date: 14-08-2022 Through 18-08-2022",

year = "2022",

month = aug,

day = "14",

doi = "10.1145/3534678.3539239",

language = "English (US)",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery",

pages = "2482--2492",

booktitle = "KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

}

TY - GEN

T1 - MetroGAN

T2 - 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022

AU - Zhang, Weiyu

AU - Ma, Yiyang

AU - Zhu, Di

AU - Dong, Lei

AU - Liu, Yu

N1 - Funding Information: This research was funded by the National Natural Science Foundation of China (41830645, 41971331). Dr. Di Zhu is supported by the Faculty Set-up Funding of College of Liberal Arts, University of Minnesota (1000-10964-20042-5672018). Publisher Copyright: © 2022 ACM.

PY - 2022/8/14

Y1 - 2022/8/14

N2 - 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.

AB - 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.

KW - generative adversarial networks

KW - urban morphology simulation

UR - http://www.scopus.com/inward/record.url?scp=85137144337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85137144337&partnerID=8YFLogxK

U2 - 10.1145/3534678.3539239

DO - 10.1145/3534678.3539239

M3 - Conference contribution

AN - SCOPUS:85137144337

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 2482

EP - 2492

BT - KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

Y2 - 14 August 2022 through 18 August 2022

ER -

MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this