Generative Pre-Trained Transformers for 15-Minute City Design

Rutvik DESHPANDE; Sayjel Vijay PATEL; Camiel WEIJENBERG; Maciej NISZTUK; Miriam CORCUERA; Jianxi LUO; Qihao ZHU

doi:10.52842/conf.caadria.2023.1.595

Generative Pre-Trained Transformers for 15-Minute City Design

Rutvik DESHPANDE
, Sayjel Vijay PATEL
, Camiel WEIJENBERG
, Maciej NISZTUK
, Miriam CORCUERA
, Jianxi LUO
, Qihao ZHU

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

9 Citations (Scopus)

Abstract

Cities globally are adopting “The 15-Minute City” as an urban response to various crises, including the Covid-19 Pandemic and climate change. However, the challenge of linking location-specific requirements with potential design solutions hinders its effective implementation. To bridge this gap, this paper introduces a novel urban 15 Minute City concept generation tool that applies an artificial intelligence (AI) method called a pre-trained language model (PLM). The PLM model was fine-tuned with structured examples based on 15-Minute City principles. Using a PLM, the tool maps 15-Minute City concepts to a location and project specific prompt, automatically generating neighbourhood design concepts in the form of natural language. © 2023 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.

Original language	English
Title of host publication	HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023)
Editors	Immanuel Koh , Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao
Place of Publication	Ahmedabad, INDIA
Publisher	The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)
Pages	595-604
Volume	1
ISBN (Print)	9789887891796
DOIs	https://doi.org/10.52842/conf.caadria.2023.1.595
Publication status	Published - Mar 2023
Externally published	Yes
Event	28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023): Human-Centric - CEPT University, Ahmedabad, India Duration: 21 Mar 2023 → 23 Mar 2023 https://caadria2023.org/ https://cept.ac.in/events/caadria-2023-human-centric

Publication series

Name	CAADRIA
ISSN (Print)	2710-4257
ISSN (Electronic)	2710-4265

Conference

Conference	28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023)
Abbreviated title	CAADRIA2023
Place	India
City	Ahmedabad
Period	21/03/23 → 23/03/23
Internet address	https://caadria2023.org/ https://cept.ac.in/events/caadria-2023-human-centric

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Research Keywords

15-Minute City
Data-driven Design
Generative Pretrained Transformer
Natural Language Generation
Neighbourhood Design
Urban Design

Access Output

10.52842/conf.caadria.2023.1.595

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

DESHPANDE, R., PATEL, S. V., WEIJENBERG, C., NISZTUK, M., CORCUERA, M., LUO, J., & ZHU, Q. (2023). Generative Pre-Trained Transformers for 15-Minute City Design. In I. K., D. Reinhardt, M. Makki, M. Khakhar, & N. Bao (Eds.), HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023) (Vol. 1, pp. 595-604). (CAADRIA). The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). https://doi.org/10.52842/conf.caadria.2023.1.595

DESHPANDE, Rutvik ; PATEL, Sayjel Vijay ; WEIJENBERG, Camiel et al. / Generative Pre-Trained Transformers for 15-Minute City Design. HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023). editor / Immanuel Koh ; Dagmar Reinhardt ; Mohammed Makki ; Mona Khakhar ; Nic Bao. Vol. 1 Ahmedabad, INDIA : The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2023. pp. 595-604 (CAADRIA).

@inproceedings{6a0831c395984d06b9e4878646f6f0ca,

title = "Generative Pre-Trained Transformers for 15-Minute City Design",

abstract = "Cities globally are adopting “The 15-Minute City” as an urban response to various crises, including the Covid-19 Pandemic and climate change. However, the challenge of linking location-specific requirements with potential design solutions hinders its effective implementation. To bridge this gap, this paper introduces a novel urban 15 Minute City concept generation tool that applies an artificial intelligence (AI) method called a pre-trained language model (PLM). The PLM model was fine-tuned with structured examples based on 15-Minute City principles. Using a PLM, the tool maps 15-Minute City concepts to a location and project specific prompt, automatically generating neighbourhood design concepts in the form of natural language. {\textcopyright} 2023 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.",

keywords = "15-Minute City, Data-driven Design, Generative Pretrained Transformer, Natural Language Generation, Neighbourhood Design, Urban Design",

author = "Rutvik DESHPANDE and PATEL, \{Sayjel Vijay\} and Camiel WEIJENBERG and Maciej NISZTUK and Miriam CORCUERA and Jianxi LUO and Qihao ZHU",

year = "2023",

month = mar,

doi = "10.52842/conf.caadria.2023.1.595",

language = "English",

isbn = "9789887891796",

volume = "1",

series = "CAADRIA",

publisher = "The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)",

pages = "595--604",

editor = "\{Immanuel Koh\} and Dagmar Reinhardt and Mohammed Makki and Mona Khakhar and Nic Bao",

booktitle = "HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023)",

note = "28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023) : Human-Centric, CAADRIA2023 ; Conference date: 21-03-2023 Through 23-03-2023",

url = "https://caadria2023.org/, https://cept.ac.in/events/caadria-2023-human-centric",

}

DESHPANDE, R, PATEL, SV, WEIJENBERG, C, NISZTUK, M, CORCUERA, M, LUO, J & ZHU, Q 2023, Generative Pre-Trained Transformers for 15-Minute City Design. in IK, D Reinhardt, M Makki, M Khakhar & N Bao (eds), HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023). vol. 1, CAADRIA, The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Ahmedabad, INDIA, pp. 595-604, 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023), Ahmedabad, India, 21/03/23. https://doi.org/10.52842/conf.caadria.2023.1.595

Generative Pre-Trained Transformers for 15-Minute City Design. / DESHPANDE, Rutvik; PATEL, Sayjel Vijay; WEIJENBERG, Camiel et al.
HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023). ed. / Immanuel Koh; Dagmar Reinhardt; Mohammed Makki; Mona Khakhar; Nic Bao. Vol. 1 Ahmedabad, INDIA: The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), 2023. p. 595-604 (CAADRIA).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Generative Pre-Trained Transformers for 15-Minute City Design

AU - DESHPANDE, Rutvik

AU - PATEL, Sayjel Vijay

AU - WEIJENBERG, Camiel

AU - NISZTUK, Maciej

AU - CORCUERA, Miriam

AU - LUO, Jianxi

AU - ZHU, Qihao

PY - 2023/3

Y1 - 2023/3

N2 - Cities globally are adopting “The 15-Minute City” as an urban response to various crises, including the Covid-19 Pandemic and climate change. However, the challenge of linking location-specific requirements with potential design solutions hinders its effective implementation. To bridge this gap, this paper introduces a novel urban 15 Minute City concept generation tool that applies an artificial intelligence (AI) method called a pre-trained language model (PLM). The PLM model was fine-tuned with structured examples based on 15-Minute City principles. Using a PLM, the tool maps 15-Minute City concepts to a location and project specific prompt, automatically generating neighbourhood design concepts in the form of natural language. © 2023 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.

AB - Cities globally are adopting “The 15-Minute City” as an urban response to various crises, including the Covid-19 Pandemic and climate change. However, the challenge of linking location-specific requirements with potential design solutions hinders its effective implementation. To bridge this gap, this paper introduces a novel urban 15 Minute City concept generation tool that applies an artificial intelligence (AI) method called a pre-trained language model (PLM). The PLM model was fine-tuned with structured examples based on 15-Minute City principles. Using a PLM, the tool maps 15-Minute City concepts to a location and project specific prompt, automatically generating neighbourhood design concepts in the form of natural language. © 2023 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.

KW - 15-Minute City

KW - Data-driven Design

KW - Generative Pretrained Transformer

KW - Natural Language Generation

KW - Neighbourhood Design

KW - Urban Design

UR - https://www.scopus.com/pages/publications/85181480088

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85181480088&origin=recordpage

U2 - 10.52842/conf.caadria.2023.1.595

DO - 10.52842/conf.caadria.2023.1.595

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9789887891796

VL - 1

T3 - CAADRIA

SP - 595

EP - 604

BT - HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023)

A2 - null, Immanuel Koh

A2 - Reinhardt, Dagmar

A2 - Makki, Mohammed

A2 - Khakhar, Mona

A2 - Bao, Nic

PB - The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)

CY - Ahmedabad, INDIA

T2 - 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023)

Y2 - 21 March 2023 through 23 March 2023

ER -

DESHPANDE R, PATEL SV, WEIJENBERG C, NISZTUK M, CORCUERA M, LUO J et al. Generative Pre-Trained Transformers for 15-Minute City Design. In IK, Reinhardt D, Makki M, Khakhar M, Bao N, editors, HUMAN-CENTRIC - Proceedings of the 28th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2023). Vol. 1. Ahmedabad, INDIA: The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). 2023. p. 595-604. (CAADRIA). doi: 10.52842/conf.caadria.2023.1.595

Generative Pre-Trained Transformers for 15-Minute City Design

Abstract

Publication series

Conference

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this