Home > Research > Publications & Outputs > Between the Promenade and the Seafront

Electronic data

View graph of relations

Between the Promenade and the Seafront: A Generative Adversarial Network Methodology for the Transposition of Architectural Style towards a new Building Typology in Morecambe.

Research output: Contribution to conference - Without ISBN/ISSN Abstractpeer-review

Forthcoming

Standard

Between the Promenade and the Seafront: A Generative Adversarial Network Methodology for the Transposition of Architectural Style towards a new Building Typology in Morecambe. . / Fagan, Des.
2021. Abstract from AMPS Urban Assemblage 2021 , London, United Kingdom.

Research output: Contribution to conference - Without ISBN/ISSN Abstractpeer-review

Harvard

APA

Vancouver

Author

Bibtex

@conference{d1dca92899db4da68f87f1fedc0617a6,
title = "Between the Promenade and the Seafront: A Generative Adversarial Network Methodology for the Transposition of Architectural Style towards a new Building Typology in Morecambe. ",
abstract = "The research considers the context of the Morecambe seafront as uniquely positioned for wider economic investment via the transformative new Eden North project (Grimshaw Architects). The research utilises a training dataset (hundreds of 2D orthographic fa{\c c}ade photos) of existing architectural buildings along the seafront (including the grade II* listed Wintergardens, train station and 60{\textquoteright}s amusement arcades) comparing these with the Eden North proposal, to interpolate and automate a speculative {\textquoteleft}new{\textquoteright} urban form transposed in the empty space between the historic seafront of Morecambe and the Eden North building, sited on the promenade. The training data and GAN methodology allows existing architectural style to be learnt and speculated upon to automate a new building typology inbetween the proposed Eden North and the existing seafront that is uniquely contextual. The form is altered by a series of multi-optimisation criteria suited to the competing requirements of a wide range of key stakeholders including local business owners, tourists, residents and planning officers.The new method tests the status of training data and datasets in relation to the intellectual property rights of the original architect author of the designs. The work concludes with a user evaluation of the outcome, speculating on the increasing impact of machine learning on the role and authorship of the architect.",
keywords = "Artificial intelligence, Machine Learning, GAN, CNN, Generative, Design, Architecture, Pix2PIx, Pix2PixHD, Generative Design, Rhino, Grasshopper, Morecambe, Promenade, Urban",
author = "Des Fagan",
year = "2021",
month = apr,
day = "15",
language = "English",
note = "AMPS Urban Assemblage 2021 : The City as Architecture, Media, AI and Big Data , AMPS ; Conference date: 28-06-2021 Through 30-06-2021",
url = "https://architecturemps.com/london-hatfield/",

}

RIS

TY - CONF

T1 - Between the Promenade and the Seafront

T2 - AMPS Urban Assemblage 2021

AU - Fagan, Des

PY - 2021/4/15

Y1 - 2021/4/15

N2 - The research considers the context of the Morecambe seafront as uniquely positioned for wider economic investment via the transformative new Eden North project (Grimshaw Architects). The research utilises a training dataset (hundreds of 2D orthographic façade photos) of existing architectural buildings along the seafront (including the grade II* listed Wintergardens, train station and 60’s amusement arcades) comparing these with the Eden North proposal, to interpolate and automate a speculative ‘new’ urban form transposed in the empty space between the historic seafront of Morecambe and the Eden North building, sited on the promenade. The training data and GAN methodology allows existing architectural style to be learnt and speculated upon to automate a new building typology inbetween the proposed Eden North and the existing seafront that is uniquely contextual. The form is altered by a series of multi-optimisation criteria suited to the competing requirements of a wide range of key stakeholders including local business owners, tourists, residents and planning officers.The new method tests the status of training data and datasets in relation to the intellectual property rights of the original architect author of the designs. The work concludes with a user evaluation of the outcome, speculating on the increasing impact of machine learning on the role and authorship of the architect.

AB - The research considers the context of the Morecambe seafront as uniquely positioned for wider economic investment via the transformative new Eden North project (Grimshaw Architects). The research utilises a training dataset (hundreds of 2D orthographic façade photos) of existing architectural buildings along the seafront (including the grade II* listed Wintergardens, train station and 60’s amusement arcades) comparing these with the Eden North proposal, to interpolate and automate a speculative ‘new’ urban form transposed in the empty space between the historic seafront of Morecambe and the Eden North building, sited on the promenade. The training data and GAN methodology allows existing architectural style to be learnt and speculated upon to automate a new building typology inbetween the proposed Eden North and the existing seafront that is uniquely contextual. The form is altered by a series of multi-optimisation criteria suited to the competing requirements of a wide range of key stakeholders including local business owners, tourists, residents and planning officers.The new method tests the status of training data and datasets in relation to the intellectual property rights of the original architect author of the designs. The work concludes with a user evaluation of the outcome, speculating on the increasing impact of machine learning on the role and authorship of the architect.

KW - Artificial intelligence

KW - Machine Learning

KW - GAN

KW - CNN

KW - Generative

KW - Design

KW - Architecture

KW - Pix2PIx

KW - Pix2PixHD

KW - Generative Design

KW - Rhino

KW - Grasshopper

KW - Morecambe

KW - Promenade

KW - Urban

M3 - Abstract

Y2 - 28 June 2021 through 30 June 2021

ER -