Translating Analytical Descriptions of Cities into Planning and Simulation Models

Abstract

With the increase in urban complexity, plausible analytical and synthetic models became highly valued as the way to decode and reconstruct the organization that makes urban systems. What they lacked is a mechanism by which an analytical description of urban complexity could be translated into a synthetic description. An attempt to define such a mechanism is presented in this paper, where knowledge is retrieved from the natural organization that cities settle into, and devised in a design model to support urban design at the problem definition stage. The model comprises two automated design modules, giving preference to street accessibility. The first module implements plausible spatial laws to generate street structures. The performance criteria of these structures are measured against accessibility scores and clustering patterns of street segments. In the second module, an Artificial Neural Networks model (ANNs) is trained on Barcelona's data, outlining how street width, building height, block density and retail land use might be dependent on street accessibility. The ANNs is tested on Manhattan's data. The application of the two computational modules is explored at the problem definition stage of a design process in order to verify how far deterministic knowledge-based models are in the transition from the analysis of design problems to the synthesis of design solutions. Our findings suggest that the computational framework proposed could be instrumental at generating simplified representation of an urban grid, whilst being effective at forecasting form-related and functional attributes within a minimum resolution of 200 meters. It is finally concluded that as design progresses, knowledge-based models may serve as to minimize uncertainty about complex urban design problems.

Intelligent Assessment for Visual Quality of Streets: Exploration Based on Machine Learning and Large-Scale Street View Data

“…Naik et al evaluated the security of urban spaces using the Street Score algorithm based on the features contained in Google Street View images for five cities in the US [14,15]. Al-Sayed and Penn noted that the artificial neural network (ANN) model was trained to outline that street accessibility may be determined by street width, building height, neighborhood density, and retail land use [16]. Using Baidu Street View images, Tang and Long combined Street View Pictures (SVPs) and CNN tools (SegNet) to evaluate the visual quality of street spaces, proposing a method to assess the visual quality of large street spaces and to be able to identify changes, using the Hutong area in Beijing as an example [17].…”

Developing an Interactive Method for Generation and Evaluation of Urban Environments

“…The studies dealing with algorithmic approaches to generating urban-scale design alternatives can be classified into three categories. The first approach focuses on algorithmic aspects of urban fabric generation, especially in geometric and morphological complexity aspects (Ayaroğlu, 2007;Beirão et al, 2010;Beirão & Duarte, 2018;Chowdhury & Schnabel, 2018;Koenig et al, 2017;König & Bauriedel, 2004;Steinø & Obeling, 2014;Vanegas et al, 2012;Vidmar & Koželj, 2015;Wilson et al, 2019), The second approach focuses on the optimizationdriven generation process (Austern et al, 2014;Duering et al, 2020;Fink & Koenig, 2019;Nagy et al, 2018;Rakha & Reinhart, 2012;Titulaer et al, 2019) and a third approach focuses on bottom-up urban growth and emergence algorithms (Al-Sayed & Penn, 2016;Batty, 1997;Hillier & Hanson, 1989;Nickerson, 2008;Stouffs & Janssen, 2017;Wang et al, 2020). This study draws inspiration from the first generative approach.…”