End-to-end autonomous driving models are typically trained on multi-city datasets using supervised ImageNet-pretrained backbones, yet their ability to generalize to unseen cities remains largely unexamined. When training and evaluation data are geographically mixed, models may implicitly rely on city-specific cues, masking failure modes that would occur under real domain shifts when generalizing to new locations. In this work we investigate zero-shot cross-city generalization in end-to-end trajectory planning and ask whether self-supervised visual representations improve transfer across cities. We conduct a comprehensive study by integrating self-supervised backbones (I-JEPA, DINOv2, and MAE) into planning frameworks. We evaluate performance under strict geographic splits on nuScenes in the open-loop setting and on NAVSIM in the closed-loop evaluation protocol. Our experiments reveal a substantial generalization gap when transferring models relying on traditional supervised backbones across cities with different road topologies and driving conventions, particularly when transferring from right-side to left-side driving environments. Self-supervised representation learning reduces this gap. In open-loop evaluation, a supervised backbone exhibits severe inflation when transferring from Boston to Singapore (L2 displacement ratio 9.77x, collision ratio 19.43x), whereas domain-specific self-supervised pretraining reduces this to 1.20x and 0.75x respectively. In closed-loop evaluation, self-supervised pretraining improves PDMS by up to 4 percent for all single-city training cities. These results show that representation learning strongly influences the robustness of cross-city planning and establish zero-shot geographic transfer as a necessary test for evaluating end-to-end autonomous driving systems.
Cities increasingly utilise digital technologies to tackle climate risks and urban shocks, yet their real impact on resilience remains uncertain. This paper systematically reviews 115 peer-reviewed studies (2012–2024) to explore how smart city technologies engage with planning instruments, governance arrangements, and social processes, following PRISMA 2020 and combining bibliometric co-occurrence mapping with a qualitative synthesis of full texts. Three themes organise the findings: (i) urban planning and design, (ii) smart technologies in resilience, and (iii) strategic planning and policy integration. Across these themes, Internet of Things (IoT) and geographic information system (GIS) applications have the strongest empirical support for enhancing absorptive and adaptive capacities through risk mapping, early warning systems, and infrastructure operations, while artificial intelligence, digital twins, and blockchain remain largely at pilot or conceptual stages. The review also highlights significant geographical and hazard biases: most cases come from high-income cities and concentrate on floods and earthquakes, while slow stresses (such as heat, housing insecurity, and inequality) and cities in the Global South are under-represented. Overall, the study promotes a “smart–resilience co-production” perspective, demonstrating that resilience improvements rely less on technology alone and more on how digital systems are integrated into governance and participatory practices.
Este articulo explora la contribución de la Estructura Ecológica Principal de Bogotá para crear un urbanismo más diverso, amplio e inclusivo. El argumento central del trabajo considera es que la transición de la planeación urbana hacia su articulación con la naturaleza, en el caso de la Sabana de Bogotá, se va construyendo desde el concepto y la configuración de la estructura ecológica. Se presenta al suelo como componente común y mediador en la formulación de nuevos escenarios plurales en las nuevas prácticas del urbanismo. Desde de la preocupación emergente de integración de la naturaleza en el proyecto colectivo de ciudad el artículo examina la geografía particular de la Sabana y la articulación progresivas del urbanismo y la ecología desde la segunda mitad del siglo XX. El proceso del ordenamiento territorial se amplía con un enfoque socio ecológico. Bajo un renovado paradigma hacia un urbanismo para un suelo vivo, el caso de Bogotá presenta una interesante convergencia, de nuevas ideas, debates e instrumentos para reorientar los escenarios integrando ciudad y región. Por tanto, las particularidades del proceso de conformación de la región metropolitana de Bogotá, así como el conocimiento de su entorno natural de gran biodiversidad son los materiales para la construcción colectiva y a largo plazo de un escenario más plural.
Aesthetics of cities. City planning and beautifying, Anthropology
Este trabajo propone el uso del índice de diferencia normalizada de áreas construidas (NDBI, por sus siglas en inglés) como complemento metodológico en las investigaciones sobre procesos de periurbanización, tomando como estudio de caso la ciudad de Manizales entre 2014 y 2024. La investigación adopta un enfoque deductivo y se fundamenta en un corpus teórico centrado en la construcción del concepto de periurbanización, el cual se articula con la aplicación del NDBI a imágenes satelitales en un intervalo de diez años. En este periodo se observa una correspondencia significativa entre los resultados obtenidos mediante marcos metodológicos y epistemológicos de las ciencias sociales —frecuentemente carentes de enfoques geoespaciales— y los patrones identificados a través del índice, que permiten una lectura panorámica de la configuración urbana y periurbana. Se concluye que el NDBI constituye una herramienta eficaz para corroborar la información generada en investigaciones previas sobre periurbanización, al tiempo que estas ofrecen insumos interpretativos para comprender los hallazgos del análisis satelital. Asimismo, se plantea el uso del NDBI como instrumento útil para la selección justificada de áreas o puntos de interés en los cuales iniciar nuevas investigaciones sobre dinámicas urbano-territoriales.
Aesthetics of cities. City planning and beautifying, Urban groups. The city. Urban sociology
Hacia mediados del siglo XX, Mar del Plata dejó de ser un balneario exclusivo para las elites argentinas y se consolidó como destino turístico accesible para las clases bajas. Esta transición se materializó en su tejido urbano mediante un boom de la construcción basado en el edificio en altura y en el régimen de propiedad horizontal. Víctor Pegoraro reconstruye la historia de la industria de la construcción marplatense durante este período determinante para la consolidación de su identidad urbana, y realiza un aporte microhistórico relevante acerca del modelo de empresa familiar en el que se sustentó.
Architecture, Aesthetics of cities. City planning and beautifying
Quantifying and assessing urban greenery is consequential for planning and development, reflecting the everlasting importance of green spaces for multiple climate and well-being dimensions of cities. Evaluation can be broadly grouped into objective (e.g., measuring the amount of greenery) and subjective (e.g., polling the perception of people) approaches, which may differ -- what people see and feel about how green a place is might not match the measurements of the actual amount of vegetation. In this work, we advance the state of the art by measuring such differences and explaining them through human, geographic, and spatial dimensions. The experiments rely on contextual information extracted from street view imagery and a comprehensive urban visual perception survey collected from 1,000 people across five countries with their extensive demographic and personality information. We analyze the discrepancies between objective measures (e.g., Green View Index (GVI)) and subjective scores (e.g., pairwise ratings), examining whether they can be explained by a variety of human and visual factors such as age group and spatial variation of greenery in the scene. The findings reveal that such discrepancies are comparable around the world and that demographics and personality do not play a significant role in perception. Further, while perceived and measured greenery correlate consistently across geographies (both where people and where imagery are from), where people live plays a significant role in explaining perceptual differences, with these two, as the top among seven, features that influences perceived greenery the most. This location influence suggests that cultural, environmental, and experiential factors substantially shape how individuals observe greenery in cities.
Understanding how urban systems and traffic dynamics co-evolve is crucial for advancing sustainable and resilient cities. However, their bidirectional causal relationships remain underexplored due to challenges of simultaneously inferring spatial heterogeneity, temporal variation, and feedback mechanisms. To address this gap, we propose a novel spatio-temporal causality framework that bridges correlation and causation by integrating spatio-temporal weighted regression with a newly developed spatio-temporal convergent cross-mapping approach. Characterizing cities through urban structure, form, and function, the framework uncovers bidirectional causal patterns between urban systems and traffic dynamics across 30 cities on six continents. Our findings reveal asymmetric bidirectional causality, with urban systems exerting stronger influences on traffic dynamics than the reverse in most cities. Urban form and function shape mobility more profoundly than structure, even though structure often exhibits higher correlations, as observed in cities such as Singapore, New Delhi, London, Chicago, and Moscow. This does not preclude the reversed causal direction, whereby long-established mobility patterns can also reshape the built environment over time. Finally, we identify three distinct causal archetypes: tightly coupled, pattern-heterogeneous, and workday-attenuated, which map pathways from causal diagnosis to intervention. This typology supports city-to-city learning and lays a foundation for context-sensitive strategies in sustainable urban and transport planning.
The impacts of climate change are increasingly evident in settlements, especially in cities and other urban areas, which poses a challenge for new approaches in urban planning. Climate change, such as rising temperatures, altered precipitation patterns with extreme weather events, changes in cloudiness and solar radiation, and an increase in the number of hot summer days, have already caused changes in climate types in Slovenia. Urban areas that are not adapted to the new conditions face negative consequences, such as flooding during heavy rainfall due to excessive soil cover and an overloaded sewage system. The soil sealing with buildings and other impermeable surfaces inhibits evapotranspiration and limits the infiltration of rainwater on natural terrain, as is otherwise possible on terrain that has direct contact with the geological base - such terrain supports water retention, runoff and infiltration and allows the planting of tall vegetation. Effective adaptation to climate change requires new urban planning approaches that include thoughtful planning of building plots. These approaches emphasize the mixing of compatible activities and the establishment of a balance between sealed and natural areas in accordance with the placement of buildings in urban space. The article presents an urban planning tool that responds to the challenges of climate change from the perspective of a quality mixing of activities in different types of buildings, from the perspective of the organization of building plots, the representation of different activities in buildings and the placement of buildings in urban settlements, densification, the provision of green spaces and improving residents' accessibility to services.
Aesthetics of cities. City planning and beautifying, City planning
Ayad Ghany Ismaeel, S. J. Jereesha Mary, C. Anitha
et al.
Smart cities have revolutionized urban living by incorporating sophisticated technologies to optimize various aspects of urban infrastructure, such as transportation systems. Effective traffic management is a crucial component of smart cities, as it has a direct impact on the quality of life of residents and tourists. Utilizing deep radial basis function (RBF) networks, this paper describes a novel strategy for enhancing traffic intelligence in smart cities. Traditional methods of traffic analysis frequently rely on simplistic models that are incapable of capturing the intricate patterns and dynamics of urban traffic systems. Deep learning techniques, such as deep RBF networks, have the potential to extract valuable insights from traffic data and enable more precise predictions and decisions. In this paper, we propose an RBF based method for enhancing smart city traffic intelligence. Deep RBF networks combine the adaptability and generalization capabilities of deep learning with the discriminative capability of radial basis functions. The proposed method can effectively learn intricate relationships and nonlinear patterns in traffic data by leveraging the hierarchical structure of deep neural networks. The deep RBF model can learn to predict traffic conditions, identify congestion patterns, and make informed recommendations for optimizing traffic management strategies by incorporating these rich and diverse data To evaluate the efficacy of our proposed method, extensive experiments and comparisons with real world traffic datasets from a smart city environment were conducted. In terms of prediction accuracy and efficiency, the results demonstrate that the deep RBF based approach outperforms conventional traffic analysis methods. Smart city traffic intelligence is enhanced by the model capacity to capture nonlinear relationships and manage large scale data sets.
A phenomenon of racial segregation in U.S. cities is a multifaceted area of study. A recent advancement in this field is the development of a methodology that transforms census population count-by-race data into a grid of monoracial cells. This format enables assessment of heterogeneity of segregation within a city. This paper leverages such a grid for the quantification of race-constrained population patterns, allowing for the calculation and mapping of binary segregation patterns within arbitrary region. A key innovation is the application of Multifractal Analysis (MFA) to quantify the residency patterns of race-constrained populations. The residency pattern is characterized by a multifractal spectrum function, where the independent variable is a local metric of pattern's "gappiness", and the dependent variable is proportional to the size of the sub-pattern consisting of all locations having the same value of this metric. In the context of binary populations, the gappiness of the race-constrained population's pattern is intrinsically linked to its segregation. This paper provides a comprehensive description of the methodology, illustrated with examples focusing on the residency pattern of Black population in the central region of Washington, DC. Further, the methodology is demonstrated using a sample of residency patterns of Black population in fourteen large U.S. cities. By numerically describing each pattern through a multifractal spectrum, the fourteen patterns are clustered into three distinct categories, each having unique characteristics. Maps of local gappiness and segregation for each city are provided to show the connection between the nature of the multifractal spectrum and the corresponding residency and segregation patterns. This method offers an excellent quantification of race-restricted residency and residential segregation patterns within U.S. cities.
This study explores the capabilities of large language models (LLMs) in providing knowledge about cities and regions on a global scale. We employ two methods: directly querying the LLM for target variable values and extracting explicit and implicit features from the LLM correlated with the target variable. Our experiments reveal that LLMs embed a broad but varying degree of knowledge across global cities, with ML models trained on LLM-derived features consistently leading to improved predictive accuracy. Additionally, we observe that LLMs demonstrate a certain level of knowledge across global cities on all continents, but it is evident when they lack knowledge, as they tend to generate generic or random outputs for unfamiliar tasks. These findings suggest that LLMs can offer new opportunities for data-driven decision-making in the study of cities.
We study how efficient resource reallocation across cities affects potential aggregate growth. Using optimal resource allocation models and data on 284 China's prefecture-level cities in the years 2003--2019, we quantitatively measure the cost of misallocation of resources. We show that average aggregate output gains from reallocating resources across nationwide cities to their efficient use are 1.349- and 1.287-fold in the perfect and imperfect allocation scenarios. We further provide evidence on the effects of administrative division adjustments and local allocation. This suggests that city-level adjustments can yield more aggregate gain and that the output gain from nationwide allocation is likely to be more substantial than that from local allocation. Policy implications are proposed to improve the resource allocation efficiency in China.
High-quality 3D urban reconstruction is essential for applications in urban planning, navigation, and AR/VR. However, capturing detailed ground-level data across cities is both labor-intensive and raises significant privacy concerns related to sensitive information, such as vehicle plates, faces, and other personal identifiers. To address these challenges, we propose AerialGo, a novel framework that generates realistic walking-through city views from aerial images, leveraging multi-view diffusion models to achieve scalable, photorealistic urban reconstructions without direct ground-level data collection. By conditioning ground-view synthesis on accessible aerial data, AerialGo bypasses the privacy risks inherent in ground-level imagery. To support the model training, we introduce AerialGo dataset, a large-scale dataset containing diverse aerial and ground-view images, paired with camera and depth information, designed to support generative urban reconstruction. Experiments show that AerialGo significantly enhances ground-level realism and structural coherence, providing a privacy-conscious, scalable solution for city-scale 3D modeling.
The picture of Victor E. Navarro Jr. looks back at you from the sidewalk.
He’s probably in his mid 50s, not too thin, deep eyes looking at the camera. His mohawk is promi-
nent, with hair cut very short on the sides to underline the volume above. It is a picture intended to
be, most likely, for an official document, one of those pictures with a neutral and uniform back-
ground, against a pinkish wall meant to disappear but which here makes it looks like Victor is jump-
ing off the picture to punch you in the eye. He’s not posing neutrally. He’s not even posing. It seems
as if he was about to say something in the moment in which the photographer said “smile”. Probably
a “fuck you” or most likely a “jagoff”, in pure Pittsburgh style.
Architecture, Aesthetics of cities. City planning and beautifying
Cities are becoming smarter and more resilient by integrating urban infrastructure with information technology. However, concerns grow that smart cities might reverse progress on civil liberties when sensing, profiling, and predicting citizen activities; undermining citizen autonomy in connectivity, mobility, and energy consumption; and deprivatizing digital infrastructure. In response, cities need to deploy technical breakthroughs, such as privacy-enhancing technologies, cohort modelling, and fair and explainable machine learning. However, as throwing technologies at cities cannot always address civil liberty concerns, cities must ensure transparency and foster citizen participation to win public trust about the way resilience and liberties are balanced.
To reduce waste and improve public health and sanitation in New York City, innovative policies tailored to the city's unique urban landscape are necessary. The first program we propose is the Dumpster and Compost Accessibility Program. This program is affordable and utilizes dumpsters placed near fire hydrants to keep waste off the street without eliminating parking spaces. It also includes legal changes and the provision of compost bins to single/two-family households, which together will increase composting rates. The second program is the Pay-As-You-Throw Program. This requires New Yorkers living in single/two-family households to purchase stickers for each refuse bag they have collected by the city, incentivizing them to sort out compostable waste and recyclables. We conduct a weighted multi-objective optimization to determine the optimal sticker price based on the City's priorities. Roughly in proportion to the price, this program will increase diversion rates and decrease the net costs to New York City's Department of Sanitation. In conjunction, these two programs will improve NYC's diversion rates, eliminate garbage bags from the streets, and potentially save New York City money.
Ports are striving for innovative technological solutions to cope with the ever-increasing growth of transport, while at the same time improving their environmental footprint. An emerging technology that has the potential to substantially increase the efficiency of the multifaceted and interconnected port processes is the digital twin. Although digital twins have been successfully integrated in many industries, there is still a lack of cross-domain understanding of what constitutes a digital twin. Furthermore, the implementation of the digital twin in complex systems such as the port is still in its infancy. This paper attempts to fill this research gap by conducting an extensive cross-domain literature review of what constitutes a digital twin, keeping in mind the extent to which the respective findings can be applied to the port. It turns out that the digital twin of the port is most comparable to complex systems such as smart cities and supply chains, both in terms of its functional relevance as well as in terms of its requirements and characteristics. The conducted literature review, considering the different port processes and port characteristics, results in the identification of three core requirements of a digital port twin, which are described in detail. These include situational awareness, comprehensive data analytics capabilities for intelligent decision making, and the provision of an interface to promote multi-stakeholder governance and collaboration. Finally, specific operational scenarios are proposed on how the port's digital twin can contribute to energy savings by improving the use of port resources, facilities and operations.
Surajit Chakravarty, Mohammed S Bin Mansoor, Bibek Kumar
et al.
The growing involvement of private-sector consultants in urban planning has been critiqued as a potential problem, mainly due to doubts over their ethical position. India’s Smart Cities Mission which aims to equip 100 cities with smart technologies, relies on private consultants both to plan the interventions and to implement them. With the planning phase now complete, and implementation in its early stages, this study examines the proposals generated by the consultants. The study deploys natural language processing computational techniques to compare a large corpus of text extracted from the proposal documents to a framework of common planning terms. The analysis yields insights regarding the consultants’ “styles,” and the evolution of the proposals over four rounds of selection. Findings suggest that some consultants show better results than others, but as many as a third of the reports prepared for the mission have low scores on the study’s metrics. In addition, a close reading of the program design helps understand the institutional context within which consultants are embedded. The paper concludes with recommendations for closer scrutiny of the consultants’ work within the mission.
In search of a feminist perspective for Berlin and an answer to the question of what a non-sexist city could and should look like, an analysis of hegemonic and feminist spatial systems was carried out based on practice-based teaching research formats. Using critical mapping (Harley, 1989; Wood, 1992) with a collective-feminist approach, this paper will demonstrate the potential of the map as a tool that allows for a non-hegemonic perspective of space. The mapping research reveals how the dichotomy of the terms public and private determines hegemonic spatial systems and how the concept of commons as a counter-image and third spatial realm opens up a possible typology of feminist spatial systems. Thus, in the evaluation of the results, the need for new common notions in urban planning discourse is discussed.
Aesthetics of cities. City planning and beautifying, Urban groups. The city. Urban sociology