RECOMM. Measuring resilient communities: An analytical and predictive tool-Reference-Cited by-同舟云学术

RECOMM. Measuring resilient communities: An analytical and predictive tool

Published:2023-07-29 Issue:3 Volume:21 Page:536-560
ISSN:1478-0771
Container-title:International Journal of Architectural Computing
language:en
Short-container-title:International Journal of Architectural Computing

Author:

Carta Silvio¹^ORCID,Turchi Tommaso²,Pintacuda Luigi¹,Jankovic Ljubomir¹³

Affiliation:

1. University of Hertfordshire, Hatfield, UK

2. University of Pisa (Italy), Pisa, Italy

3. Zero Carbon Lab, University of Hertfordshire, Hatfield, UK

Abstract

We present initial findings of our project RECOMM: an analytical tool that evaluates the resilience of urban areas. The tool utilises Deep Neural Networks to identify characteristics of resilience and assigns a resilience score to different urban areas based on the proximity to certain features such as green spaces, buildings, natural elements and infrastructure. The tool also identifies which urban morphological factors have the greatest impact on resilience. The method uses Convolutional Neural Networks with the Keras library on Tensorflow for calculations and the results are displayed in an online demo built with Node.js and React.js. This work contributes to the analysis and design of sustainable cities and communities by offering a tool to assess resilience through urban form.

Publisher

SAGE Publications

Subject

Computer Graphics and Computer-Aided Design,Computer Science Applications,Building and Construction

Link

http://journals.sagepub.com/doi/pdf/10.1177/14780771231174891

Reference57 articles.

1. Deep Learning-Based Object Detection Techniques for Remote Sensing Images: A Survey

2. A survey on object detection in optical remote sensing images

3. How Well Do Deep Learning-Based Methods for Land Cover Classification and Object Detection Perform on High Resolution Remote Sensing Imagery?

4. SteinfeldGan Kloci. 2019. Acadia 19: ubiquity and autonomy. In: Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA). Austin: The University of Texas at Austin School of Architecture, Texas 21-26 October, 2019, pp. 392–403.

5. Wallish S. Counterfeiting daily: An Exploration of the Use of Generative Adversarial Neural Networks in The Architectural Design Process. Vancouver University of British Columbia Library, 2019, https://dx.doi.org/10.14288/1.0387289