No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Computational Urban Design: An Exploration of New Urban Science
Abstract
Classic urban design theories and research methods have been limited to qualitative approaches, such as subjective intuition and small-scale surveys. With the emergence of new urban science, adopting big data, virtual reality (VR), and wearable sensors, it is possible to achieve a precise analysis of people’s perceptions and behaviors in urban spaces. In this way, not only will new insights in urban studies be inspired but also high-quality, human-scale space design can be generated. This study constructs a systematic and computational urban design system that covers the three aspects of technical applications, data-informed, evidence-based, and algorithm-driven urban design. First, the data-informed urban design helps identify problems and formulate strategies. Multi-source city data, such as Point of Interest (PoIs)data and AutoNavi map path planning API, help to identify the needs, functions, and characteristics of the citizens. The evidence-based urban design with specific inquiries helps to select the design intervention point and control spatial elements. VR technology, wearable biosensors, and the visualizationSP method are combined to measure space utility. The final algorithm-driven part can use sDNA, UNA, and visualizer to summarize the types of urban spaces, perform morphological analysis and vitality evaluation, and further adjust the design. It can be seen that the application of this framework can make the entire design process more automatic, efficient, and robust under the existing constraints. In addition, it helps the perspective of urban design expand from the previous “top-down” perspective to the “bottom up” perspective, transforming from a two-dimensional to a three-dimensional, obtaining real-time feedback and optimizing design accordingly, emphasizing human perception and human-oriented scale.
ResearchGate has not been able to resolve any citations for this publication.
Living convenience, as a perceptual quality of life, is gradually playing an increasingly important role in the context of seeking livable cities. A high degree of living convenience positively affects urban vitality, livability, and daily physical activities. However, it is hard to achieve a quantitative measurement of this intangible, subjective issue. This study presents a data-informed analytical approach to measuring the human-scale living convenience using multi-sourced urban data and geodesign techniques. Firstly, according to classical theories, living convenience is translated as the co-presentation of accessed number and diversity of urban facilities. Based on that, this study applies multi-sourced urban data, including points of interest (PoIs), buildings, and street networks, to compute the living convenience of each building in the 15 min community–life circle. Through the geoprocessing tools developed by ArcGIS API for Python (ArcPy), the living convenience of millions of buildings in an entire city can be computed efficiently. Kaifeng City from Henan Province, China, is selected as the case study, and the verification from local experts in urbanism shows high accuracy. The capacity to measure intangible perception exhibits the potential for this analytical approach in urban planning practices. Several explorations have been conducted in this direction, including analyzing the spatial heterogeneity in Kaifeng City and planning decision support for bus station arrangement. In short, this study contributes to the development of human-centered planning by providing continuous measurements of an ‘unmeasurable’ quality across large-scale areas. Insights into the perceptual-based quality and detailed mapping of living conveniences in buildings can assist in efficient planning strategies toward more livable and sustainable urbanism.
To meet the needs of park users, planners and designers must know what park users want to do and how they want the park to offer different activities. Big data may help planners and designers gain this knowledge. This study examines how big data collected in an urban park could be used to identify meaningful implications for planning and design. While big data have emerged as a new data source, big data have not become an accepted source of data due to a lack of understanding of big data analytics. By comparing a survey as a traditional data source with big data, this study identifies the strengths and weaknesses of using big data analytics in park planning and design. There are two research questions: (1) what activities do park users want; and (2) how satisfied are users with different activities. The Gyeongui Line Forest Park, which was built on an abandoned railway, was selected as the study site. A total of 177 responses were collected through the onsite survey, and 3703 tweets mentioning the park were collected from Twitter. Results from the survey show that ordinary activities such as walking and taking a rest in the park were the most common. These findings also support existing studies. The results from social media analytics found notable things such as positive tweets about how the railway was turned into a park, and negative tweets about diseases that may occur in the park. Therefore, a survey as traditional data and social media analytics as big data can be complementary methods for the design and planning process.
This study proposes a workable approach for quantitatively measuring the perceptual-based visual quality of streets, which has often relied on subjective impressions or feelings. With the help of recently emerged street view images and machine learning algorithms, an evaluation model has been trained to assess the perceived visual quality with accuracy similar to that of experienced urban designers, to provide full coverage and detailed results for a citywide area. The town centre of Shanghai was selected for the site. Around 140,000 screenshots from Baidu Street View were processed and a machine learning algorithm, SegNet, was applied to intelligently extract the pixels representing key elements affecting the visual quality of streets, including the building frontage, greenery, sky view, pedestrian space, motorisation, and diversity. A Java-based program was then produced to automatically collect the preferences of experienced urban designers on representative sample images. Another machine learning algorithm, i.e. an artificial neural network, was used to train an evaluation model to achieve a citywide, high-resolution evaluation of the visual quality of the streets. Further validation through different approaches shows this evaluation model obtains a satisfactory accuracy. The results from the artificial neural network also help to explore the high or low effects of various key elements on visual quality. In short, this study contributes to the development of human-centred planning and design by providing continuous measurements of an ‘unmeasurable’ quality across large-scale areas. Meanwhile, insights on the perceptual-based visual quality and detailed mapping of various key elements in streets can assist in more efficient street renewal by providing accurate design guidance.
Various research applications require detailed metrics to describe the form and composition of cities at fine scales, but the parameter computation remains a challenge due to limited data availability, quality, and processing capabilities. We developed an innovative big data approach to derive street-level morphology and urban feature composition as experienced by a pedestrian from Google Street View (GSV) imagery. We employed a scalable deep learning framework to segment 90-degree field of view GSV image cubes into six classes: sky, trees, buildings, impervious surfaces, pervious surfaces, and non-permanent objects. We increased the classification accuracy by differentiating between three view directions (lateral, down, and up) and by introducing a void class as training label. To model the urban environment as perceived by a pedestrian in a street canyon, we projected the segmented image cubes onto spheres and evaluated the fraction of each surface class on the sphere. To demonstrate the application of our approach, we analyzed the urban form and composition of Philadelphia County and three Philadelphia neighborhoods (suburb, center city, lower income neighborhood) using stacked area graphs. Our method is fully scalable to other geographic locations and constitutes an important step towards building a global morphological database to describe the form and composition of cities from a human-centric perspective.
Robust quantitative descriptions of the social and physical characteristics of urban contexts are essential for assessing the impacts of urban environments on other, potentially dependent variables. Common methodologies used for that purpose, however, are either coarse or suffer from biasing effects. At the social level, the use of indicators encoded into pre-defined areal units, makes results prone to the Modifiable Areal Unit Problem. At the physical level, the adopted morphological indicators are usually highly aggregated descriptors of urban form. Moreover, there is a lack of explicit methodologies for the purposive sampling of urban contexts with specific combinations of social and physical characteristics, which—we argue—may be more effective than probabilistic sampling, when exploring phenomena as elusive as the effects of urban contextual factors. This article presents a set of GIS-based methods for addressing these issues, based on: a) local indicators of spatial association; b) detailed quantitative morphological descriptions, coupled with unsupervised classification techniques; and c) purposive sampling strategies carried out on the data generated by the proposed context characterization methods (a and b). The methods are illustrated through the characterization of the urban contexts of the 77 state-sector secondary schools in Liverpool, but are generalizable across all categories of urban objects and are independent of the geographical context of implementation.
Recent urban transformations in China have led to critical reflections on the low-quality urban expansion in the previous decades and called for the making of vital and lively urban places. To date, limited research has been devoted to empirically testing the relationship between urban design, urban morphology, and urban vitality in Chinese cities. This paper employs new urban data and analytical methods and explores the relationship between urban morphology and urban vitality using regression models. Shenzhen, one of the largest and fastest growing cities in China, is selected as the case study. The regression analysis focuses on two morphological factors, density and typology, while controlling for the accessibility, functional mix, and size of individual blocks. The presence of small catering businesses is used as a proxy for urban vitality. The analysis suggests that both typology and density matter for urban vitality, with typology playing a more important role. More specifically, “block” and “strip” types tend to show significant positive effects on urban vitality. The implications for urban planning and design practices are discussed.
Urban planning involves many aspects and various disciplines, demanding an asynchronous planning approach. The level of complexity rises with each aspect to be considered and makes it difficult to find universally satisfactory solutions. To improve this situation we propose a new approach, which complement traditional design methods with a computational urban plan- ning method that can fulfil formalizable design requirements automatically. Based on this approach we present a design space exploration framework for complex urban planning projects. For a better understanding of the idea of design space exploration, we introduce the concept of a digital scout which guides planners through the design space and assists them in their creative explorations. The scout can support planners during manual design by informing them about potential im- pacts or by suggesting different solutions that fulfill predefined quality requirements. The planner can change flexibly between a manually controlled and a completely automated design process. The developed system is presented using an exemplary urban planning scenario on two levels from the street layout to the placement of building volumes. Based on Self-Organizing Maps we implemented a method which makes it possible to visualize the multi-dimensional solution space in an easily analysable and comprehensible form.
This study proposes a prototype for the smart rendering of urban master plans via artificial intelligence algorithms, a process which is time-consuming and relies on professionals’ experience. With the help of crowdsourced data and generative adversarial networks (GAN), a generation model was trained to provide colorful rendering of master plans similar to those produced by experienced urban designers. Approximately 5000 master plans from Pinterest were processed and CycleGAN was applied as the core algorithm to build this model, the so-called MasterplanGAN. Using the uncolored input design files in an AutoCAD format, the MasterplanGAN can provide master plan renderings within a few seconds. The validation of the generated results was achieved using quantitative and qualitative judgments. The achievements of this study contribute to the development of automatic generation of previously subjective and experience-oriented processes, which can serve as a useful tool for urban designers and planners to save time in real projects. It also contributes to push the methodological boundaries of urban design by addressing urban design requirements with new urban data and new techniques. This initial exploration indicates that a large but clear picture of computational urban design can be presented, integrating scientific thinking, design, and computer techniques.
Communication of climate-responsive urban design guidelines is becoming increasingly relevant in the light of climate adaptation challenges in cities. Widespread uptake in practice of such guidelines can be promoted by visualizations of the principles on which they are based. The “Really cooling water bodies in cities” research project developed and tested the required knowledge on visual communication. Evidence-based design guidelines assisting designers with creating cooler urban water environments were developed and communicated with 3D animations. The animations were shaped according to three core theoretical criteria about visual representations: “visual clarity”, “trust” and “interest”. We assessed in how far these criteria were met in an inquiry with design professionals, the target group of the design guidelines. The article concludes with recommendations for developing visual design guidelines in climate-responsive urban design: to weigh the level of detail, components and balance between site-specificity/abstraction (“visual clarity”); to make microclimatic processes visible without distorting them (“trust”); and to keep timing short and visual attractiveness high (“interest”). It is argued that taking these aspects into account and setting a clear correspondence between theoretical concepts, representation objectives and options, can largely benefit visual design guidelines communicating climate-responsive urban design knowledge.
The future of urban design is implicitly connected with datasets. Thomas Kvan, founding director of AURIN, a national digital infrastructure to support urban research, and Professor of Architecture at the University of Melbourne, argues that architects have already lost ground to data scientists in this respect. The architectural profession and its education system must embrace urban data analysis as input for urban and building design of the future.
Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.
The public benefits of visible street greenery have been well recognised in a growing literature. Nevertheless, this issue was rare to be included into urban greenery and planning practices. As a response to this situation, we proposed an actionable approach for quantifying the daily exposure of urban residents to eye-level street greenery by integrating high resolution measurements on both greenery and accessibility. Google Street View (GSV) images in Singapore were collected and extracted through machine learning algorithms to achieve an accurate measurement on visible greenery. Street networks collected from Open Street Map (OSM) were analysed through spatial design network analysis (sDNA) to quantify the accessibility value of each street. The integration of street greenery and accessibility helps to measure greenery from a human-centred perspective, and it provides a decision-support tool for urban planners to highlight areas with prioritisation for planning interventions. Moreover, the performance between GSV-based street greenery and the urban green cover mapped by remote sensing was compared to justify the contribution of this new measurement. It suggested there was a mismatch between these two measurements, i.e., existing top-down viewpoint through satellites might not be equivalent to the benefits enjoyed by city residents. In short, this analytical approach contributes to a growing trend in integrating large, freely-available datasets with machine learning to inform planners, and it makes a step forward for urban planning practices through focusing on the human-scale measurement of accessed street greenery.
This article is motivated by the fact that in Cape Town, South Africa, approximately 7.5 million people live in informal settlements and focuses on potential upgrading strategies for such sites. To this end, we developed a computational method for rapid urban design prototyping. The corresponding planning tool generates urban layouts including street network, blocks, parcels and buildings based on an urban designer’s specific requirements. It can be used to scale and replicate a developed urban planning concept to fit different sites. To facilitate the layout generation process computationally, we developed a new data structure to represent street networks, land parcellation, and the relationship between the two. We also introduced a nested parcellation strategy to reduce the number of irregular shapes generated due to algorithmic limitations. Network analysis methods are applied to control the distribution of buildings in the communities so that preferred neighborhood relationships can be considered in the design process. Finally, we demonstrate how to compare designs based on various urban analysis measures and discuss the limitations that arise when we apply our method in practice, especially when dealing with more complex urban design scenarios.
The “China Dream” is an “Urban Dream”. Urbanization is an inevitable requirement for promoting social progress. The Chinese government sees sustainable urbanization as an engine of modernization and economic growth. And the country's urbanization has followed a unique course and is perhaps the greatest human-resettlement experiment in the world history, unprecedentedly transforming the Chinese society in a very short period of time. Yet problems have arisen during the historical process, China's unique path to urbanization has avoided many of pitfalls existing in the developing countries in Africa, Asia and South America. This paper attempts to conclude the good jobs as well as problems in China's urbanizing process which might provide successful experience for the underdeveloped nations and regions to promote urbanization. The most brilliant achievement of urbanization in China is that thousands of years' agriculture-dominated country has ended and a new urbanized country has formed, which only consumed several decades. The country's urban infrastructure, living conditions and public service for urban residents have made great improvements. The fostering urban agglomerations are considered to lead the country's socio-economic transformation and possess the greatest potential for the urbanization and economic growth in the coming decades. In general, the traditional land-centered urbanization in China is a typical “incomplete urbanization” and “low-quality urbanization”, presenting impressive characteristics of “four highs and five lows”—high investment, consumption, emission and expansion, and low level, quality, harmony degree, inclusiveness and sustainability. Undoubtedly, the traditional urbanization of China is increasingly difficult to continue and the transformation process should be speeded up as soon as possible. The country should actively explore a people-oriented new-type urbanization way, i.e. an intensive, efficient, rural-urban integration, harmonious and sustainable urbanization model.
The MIT based SENSEable City Lab under Carlo Ratti is one of the research centers that deal with the flow of people and goods, but also of refuse that moves around the world. Experience with large-scale infrastructure projects suggest that more complex and above all flexible answers must be sought to questions of transportation or disposal. This edition, edited by Dietmar Offenhuber and Carlo Ratti, shows how Big Data change reality and, hence, the way we deal with the city. It discusses the impact of real-time data on architecture and urban planning, using examples developed in the SENSEable City Lab. They demonstrate how the Lab interprets digital data as material that can be used for the formulation of a different urban future. It also looks at the negative aspects of the city-related data acquisition and control. The authors address issues with which urban planning disciplines will work intensively in the future: questions that not only radically and critically review, but also change fundamentally, the existing tasks and how the professions view their own roles.
Since the very origins of urban planning in the late nineteenth century, the field has aspired to establish a firm scientific footing for the nature of cities, their cycles of growth and decline, and ways that we can better plan and predict the outcomes of interventions through design and policy. While these efforts have long been stymied by a lack of sufficiently detailed data and limited computing power, these obstacles are rapidly being overcome. In response, a growing number of city governments and a new cadre of academic research centers are investing in data-intensive analysis and simulation of cities. While this campaign shares many similarities with computer-based efforts to study cities and inform urban policy during the United States’ urban crisis in the 1960s, the rise of the Internet presents new opportunities to involve citizens more actively, on a larger scale, and in more empowered roles than in the past. This development offers an opportunity to develop more transparent, ethical, and effective models for collaborative urban research involving universities, local government, and citizen science networks
Definitions of Urban Design: The Nature and Concerns of Urban Design
- Peter Buchanan
Peter Buchanan, "What City? A Plea for Place in the Public Realm,"
The Architectural Review 184, no. 1101 (1988): 31-41; Alan Rowley,
"Definitions of Urban Design: The Nature and Concerns of Urban Design,"
Planning Practice and Research 9, no. 3 (1994): 179-97, https://doi.
org/10.1080/02697459408722929.
Streetscore-Predicting the Perceived Safety of One Million Streetscapes
- Nikhil Naik
Nikhil Naik et al., "Streetscore-Predicting the Perceived Safety of One Million
Streetscapes," in Proceedings of the IEEE Conference on Computer Vision and
Pattern Recognition Work-shops, 2014, 779-85.
Geodesign: Fundamental Principles and Routes Forward
- Michael Flaxman
Michael Flaxman, "Geodesign: Fundamental Principles and Routes Forward,"
Talk at Ge-oDesign Summit, 2010.
A Framework for Geodesign: Changing Geography by Design
- A Mônica
- Haddad
Mônica A. Haddad, A Framework for Geodesign: Changing Geography by Design
(SAGE Publications Sage CA: Los Angeles, CA, 2015).