Generative adversarial networks for ensemble projections of future urban morphology

Melissa R. Allen-Dumas; Abigail R. Wheelis; Levi T. Sweet-Breu; Joshua Anantharaj; Kuldeep R. Kurte

doi:10.1145/3557916.3567819

Generative adversarial networks for ensemble projections of future urban morphology

Melissa R. Allen-Dumas
, Abigail R. Wheelis
, Levi T. Sweet-Breu
, Joshua Anantharaj
, Kuldeep R. Kurte

Computational Urban Sciences

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

3 Scopus citations

Abstract

As city planners design and adapt cities for future resilience and intelligence, interactions among neighborhood morphological development with respect to changes in population and resultant built infrastructure's impact on the natural environment must be considered. For deep understanding of these interactions, explicit representation of future neighborhoods is necessary for future city modeling. Generative Adversarial Networks (GANs) have been shown to produce spatially accurate urban forms at scales representing entire cities to those at neighborhood and single building scale. Here we demonstrate a GAN method for generating an ensemble of possible new neighborhoods given land use characteristics and designated neighborhood type.

Original language	English
Title of host publication	Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022
Editors	Bandana Kar, Shima Mohebbi, Guangtao Fu, Xinyue Ye, Olufemi A. Omitaomu
Publisher	Association for Computing Machinery, Inc
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781450395304
DOIs	https://doi.org/10.1145/3557916.3567819
State	Published - Nov 1 2022
Event	5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022 - Seattle, United States Duration: Nov 1 2022 → …

Publication series

Name	Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022

Conference

Conference	5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022
Country/Territory	United States
City	Seattle
Period	11/1/22 → …

Funding

This work is supported by the DOE Office of Science as a part of the research in Multi-Sector Dynamics within the Earth and Environmental System Modeling Program under the Integrated Multiscale Multisector Modeling (IM3) Scientific Focus Area.

Keywords

generative adversarial networks
machine learning
urban morphology

Access to Document

10.1145/3557916.3567819

Cite this

Allen-Dumas, M. R., Wheelis, A. R., Sweet-Breu, L. T., Anantharaj, J., & Kurte, K. R. (2022). Generative adversarial networks for ensemble projections of future urban morphology. In B. Kar, S. Mohebbi, G. Fu, X. Ye, & O. A. Omitaomu (Eds.), Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022 (pp. 1-6). (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022). Association for Computing Machinery, Inc. https://doi.org/10.1145/3557916.3567819

Allen-Dumas, Melissa R. ; Wheelis, Abigail R. ; Sweet-Breu, Levi T. et al. / Generative adversarial networks for ensemble projections of future urban morphology. Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022. editor / Bandana Kar ; Shima Mohebbi ; Guangtao Fu ; Xinyue Ye ; Olufemi A. Omitaomu. Association for Computing Machinery, Inc, 2022. pp. 1-6 (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022).

@inproceedings{8e0a29e26fea450b80ae655effc01e8a,

title = "Generative adversarial networks for ensemble projections of future urban morphology",

abstract = "As city planners design and adapt cities for future resilience and intelligence, interactions among neighborhood morphological development with respect to changes in population and resultant built infrastructure's impact on the natural environment must be considered. For deep understanding of these interactions, explicit representation of future neighborhoods is necessary for future city modeling. Generative Adversarial Networks (GANs) have been shown to produce spatially accurate urban forms at scales representing entire cities to those at neighborhood and single building scale. Here we demonstrate a GAN method for generating an ensemble of possible new neighborhoods given land use characteristics and designated neighborhood type.",

keywords = "generative adversarial networks, machine learning, urban morphology",

author = "Allen-Dumas, \{Melissa R.\} and Wheelis, \{Abigail R.\} and Sweet-Breu, \{Levi T.\} and Joshua Anantharaj and Kurte, \{Kuldeep R.\}",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022 ; Conference date: 01-11-2022",

year = "2022",

month = nov,

day = "1",

doi = "10.1145/3557916.3567819",

language = "English",

series = "Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022",

publisher = "Association for Computing Machinery, Inc",

pages = "1--6",

editor = "Bandana Kar and Shima Mohebbi and Guangtao Fu and Xinyue Ye and Omitaomu, \{Olufemi A.\}",

booktitle = "Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022",

}

Allen-Dumas, MR, Wheelis, AR, Sweet-Breu, LT, Anantharaj, J & Kurte, KR 2022, Generative adversarial networks for ensemble projections of future urban morphology. in B Kar, S Mohebbi, G Fu, X Ye & OA Omitaomu (eds), Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022. Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022, Association for Computing Machinery, Inc, pp. 1-6, 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022, Seattle, United States, 11/1/22. https://doi.org/10.1145/3557916.3567819

Generative adversarial networks for ensemble projections of future urban morphology. / Allen-Dumas, Melissa R.; Wheelis, Abigail R.; Sweet-Breu, Levi T. et al.
Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022. ed. / Bandana Kar; Shima Mohebbi; Guangtao Fu; Xinyue Ye; Olufemi A. Omitaomu. Association for Computing Machinery, Inc, 2022. p. 1-6 (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022).

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

TY - GEN

T1 - Generative adversarial networks for ensemble projections of future urban morphology

AU - Allen-Dumas, Melissa R.

AU - Wheelis, Abigail R.

AU - Sweet-Breu, Levi T.

AU - Anantharaj, Joshua

AU - Kurte, Kuldeep R.

PY - 2022/11/1

Y1 - 2022/11/1

N2 - As city planners design and adapt cities for future resilience and intelligence, interactions among neighborhood morphological development with respect to changes in population and resultant built infrastructure's impact on the natural environment must be considered. For deep understanding of these interactions, explicit representation of future neighborhoods is necessary for future city modeling. Generative Adversarial Networks (GANs) have been shown to produce spatially accurate urban forms at scales representing entire cities to those at neighborhood and single building scale. Here we demonstrate a GAN method for generating an ensemble of possible new neighborhoods given land use characteristics and designated neighborhood type.

AB - As city planners design and adapt cities for future resilience and intelligence, interactions among neighborhood morphological development with respect to changes in population and resultant built infrastructure's impact on the natural environment must be considered. For deep understanding of these interactions, explicit representation of future neighborhoods is necessary for future city modeling. Generative Adversarial Networks (GANs) have been shown to produce spatially accurate urban forms at scales representing entire cities to those at neighborhood and single building scale. Here we demonstrate a GAN method for generating an ensemble of possible new neighborhoods given land use characteristics and designated neighborhood type.

KW - generative adversarial networks

KW - machine learning

KW - urban morphology

UR - https://www.scopus.com/pages/publications/85142651487

U2 - 10.1145/3557916.3567819

DO - 10.1145/3557916.3567819

M3 - Conference contribution

AN - SCOPUS:85142651487

T3 - Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022

SP - 1

EP - 6

BT - Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022

A2 - Kar, Bandana

A2 - Mohebbi, Shima

A2 - Fu, Guangtao

A2 - Ye, Xinyue

A2 - Omitaomu, Olufemi A.

PB - Association for Computing Machinery, Inc

T2 - 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022

Y2 - 1 November 2022

ER -

Allen-Dumas MR, Wheelis AR, Sweet-Breu LT, Anantharaj J, Kurte KR. Generative adversarial networks for ensemble projections of future urban morphology. In Kar B, Mohebbi S, Fu G, Ye X, Omitaomu OA, editors, Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022. Association for Computing Machinery, Inc. 2022. p. 1-6. (Proceedings of the 5th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2022). doi: 10.1145/3557916.3567819

Generative adversarial networks for ensemble projections of future urban morphology

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this