MEASURING RESILIENT COMMUNITIES: An analytical and predictive tool

Silvio Carta; Tommaso Turchi; Luigi Pintacuda

MEASURING RESILIENT COMMUNITIES: An analytical and predictive tool

Silvio Carta, Tommaso Turchi, Luigi Pintacuda

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

32 Downloads (Pure)

Abstract

This work presents the initial results of an analytical tool designed to quantitatively assess the level of resilience of urban areas. We use Deep Neural Networks to extract features of resilience from a trained model that classifies urban areas using a pre-assigned value range of resilience. The model returns the resilience value for any urban area, indicating the distance between the centre of the selected area and relevant typologies, including green areas, buildings, natural elements and infrastructures. Our tool also indicates the urban morphological characteristics that have a larger impact on the resilience score. In this way we can learn why a neighbourhood is successful (or not) and how to improve its level of resilience. The model employs Convolutional Neural Networks (CNNs) with Keras on Tensorflow for the computation. The outputs are loaded onto a Node.JS environment and bootstrapped with React.js to generate the online demo.

Original language	English
Title of host publication	CAADRIA 2022 Proceedings
Subtitle of host publication	27th International Conference of the Association for Computer-Aided Architectural Design Research in Asia / Sydney, Australia
Number of pages	10
Publication status	Published - 15 Apr 2022
Event	CAADRIA2022 - Sydney, Australia Duration: 9 Apr 2022 → 15 Apr 2022 https://caadria2022.org/

Conference

Conference	CAADRIA2022
Country/Territory	Australia
City	Sydney
Period	9/04/22 → 15/04/22
Internet address	https://caadria2022.org/

Access to Document

Accepted_Version
© 2022 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong. This is the accepted manuscript version of an article which has been published in final form at https://caadria2022.org/measuring_resilient_communities_an_analytical_and_predictive_tool/
Accepted author manuscript, 1.19 MBLicence: Unspecified

https://caadria2022.org/wp-content/uploads/2022/04/68-1.pdfLicence: Unspecified

Cite this

@inproceedings{895dc4f7ea9e4e2c87a7a9d5b57b1fb1,

title = "MEASURING RESILIENT COMMUNITIES: An analytical and predictive tool",

abstract = "This work presents the initial results of an analytical tool designed to quantitatively assess the level of resilience of urban areas. We use Deep Neural Networks to extract features of resilience from a trained model that classifies urban areas using a pre-assigned value range of resilience. The model returns the resilience value for any urban area, indicating the distance between the centre of the selected area and relevant typologies, including green areas, buildings, natural elements and infrastructures. Our tool also indicates the urban morphological characteristics that have a larger impact on the resilience score. In this way we can learn why a neighbourhood is successful (or not) and how to improve its level of resilience. The model employs Convolutional Neural Networks (CNNs) with Keras on Tensorflow for the computation. The outputs are loaded onto a Node.JS environment and bootstrapped with React.js to generate the online demo.",

author = "Silvio Carta and Tommaso Turchi and Luigi Pintacuda",

note = "{\textcopyright} 2022 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong. This is the accepted manuscript version of an article which has been published in final form at https://caadria2022.org/measuring_resilient_communities_an_analytical_and_predictive_tool/; CAADRIA2022 ; Conference date: 09-04-2022 Through 15-04-2022",

year = "2022",

month = apr,

day = "15",

language = "English",

booktitle = "CAADRIA 2022 Proceedings",

url = "https://caadria2022.org/",

}

TY - GEN

T1 - MEASURING RESILIENT COMMUNITIES

T2 - CAADRIA2022

AU - Carta, Silvio

AU - Turchi, Tommaso

AU - Pintacuda, Luigi

N1 - © 2022 and published by the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong. This is the accepted manuscript version of an article which has been published in final form at https://caadria2022.org/measuring_resilient_communities_an_analytical_and_predictive_tool/

PY - 2022/4/15

Y1 - 2022/4/15

N2 - This work presents the initial results of an analytical tool designed to quantitatively assess the level of resilience of urban areas. We use Deep Neural Networks to extract features of resilience from a trained model that classifies urban areas using a pre-assigned value range of resilience. The model returns the resilience value for any urban area, indicating the distance between the centre of the selected area and relevant typologies, including green areas, buildings, natural elements and infrastructures. Our tool also indicates the urban morphological characteristics that have a larger impact on the resilience score. In this way we can learn why a neighbourhood is successful (or not) and how to improve its level of resilience. The model employs Convolutional Neural Networks (CNNs) with Keras on Tensorflow for the computation. The outputs are loaded onto a Node.JS environment and bootstrapped with React.js to generate the online demo.

AB - This work presents the initial results of an analytical tool designed to quantitatively assess the level of resilience of urban areas. We use Deep Neural Networks to extract features of resilience from a trained model that classifies urban areas using a pre-assigned value range of resilience. The model returns the resilience value for any urban area, indicating the distance between the centre of the selected area and relevant typologies, including green areas, buildings, natural elements and infrastructures. Our tool also indicates the urban morphological characteristics that have a larger impact on the resilience score. In this way we can learn why a neighbourhood is successful (or not) and how to improve its level of resilience. The model employs Convolutional Neural Networks (CNNs) with Keras on Tensorflow for the computation. The outputs are loaded onto a Node.JS environment and bootstrapped with React.js to generate the online demo.

M3 - Conference contribution

BT - CAADRIA 2022 Proceedings

Y2 - 9 April 2022 through 15 April 2022

ER -

MEASURING RESILIENT COMMUNITIES: An analytical and predictive tool

Abstract

Conference

Access to Document

Fingerprint

Cite this