Developing a strategy of data collection and pre-processing to assess bike-sharing system station placements with the help of GIS

Zero waste manufacturing: A framework and review of technology, research, and implementation barriers for enabling a circular economy transition in Singapore

Modelling building energy use at urban scale: A review on their account for the urban environment

Urban roof segmentation plays a pivotal role in applications such as urban planning, infrastructure management, and renewable energy deployment. This study explores the evolution of deep learning techniques from traditional Convolutional Neural Networks (CNNs) to cutting-edge transformer-based models in the context of roof segmentation from satellite imagery. We highlight the limitations of conventional methods when applied to urban environments, including resolution constraints and the complexity of roof structures. To address these challenges, we evaluate two advanced deep learning models, Mask R-CNN and MaskFormer, which have shown significant promise in accurately segmenting roofs, even in dense urban settings with diverse roof geometries. These models, especially the one based on transformers, offer improved segmentation accuracy by capturing both global and local image features, enhancing their performance in tasks where fine detail and contextual awareness are critical. A case study on Ben Guerir City in Morocco, an urban area experiencing rapid development, serves as the foundation for testing these models. Using high-resolution satellite imagery, the segmentation results offer a deeper understanding of the accuracy and effectiveness of these models, particularly in optimizing urban planning and renewable energy assessments. Quantitative metrics such as Intersection over Union (IoU), precision, recall, and F1-score are used to benchmark model performance. Mask R-CNN achieved a mean IoU of 74.6%, precision of 81.3%, recall of 78.9%, and F1-score of 80.1%, while MaskFormer reached a mean IoU of 79.8%, precision of 85.6%, recall of 82.7%, and F1-score of 84.1% (pixel-level, micro-averaged at IoU = 0.50 on the held-out test set), highlighting the transformative potential of transformer-based architectures for scalable and precise urban imaging. The study also outlines future work in 3D modeling and height estimation, positioning these advancements as critical tools for sustainable urban development.

Laws governing development of additional settlements of buildings constructed in the 1960s and 70s on shallow strip foundations when the bed is loaded by the weight of a newly constructed entity in a dense urban setting are examined.

ABSTRACTThis study demonstrates the trade-offs between vehicle energy consumption and on-site solar energy potential in a city landscape. While higher urban density may curb many of the problems associated with sprawl mainly by reducing vehicle travels and associated energy use, it can also limit on-site rooftop solar energy utilization due to more shade on rooftops in dense urban settings and less available rooftop area per person. Using travel survey, Geographic Information System (GIS) and Light Detection and Ranging (LiDAR) data, we estimated vehicle energy use and rooftop solar potential in the City of San Francisco as a case study and calculated possible offsetting effects between vehicle energy consumption and rooftop solar potential. Given the prevalence of gasoline-based vehicles and today's solar photovoltaic (PV) panel efficiency, vehicle energy use per capita appears to exceed energy generated by rooftop solar PVs per capita across all density ranges, especially in lower density environments. At the point when electric cars and advanced, highly efficient solar PV panels penetrate the market, the results change based on the combination of different technological options. A significant reduction of energy consumption can be achieved through the immediate and rapid spread of energy efficient technologies in vehicles and solar PVs along with the long-term effect from gradual urban densification.

This study tackles the challenges of documenting architectural heritage in Macao’s dense urban settings. Traditional methods are often inefficient and invasive for the complex materials of actively used temples. We propose a lightweight method that integrates portable 3D laser scanning with non-destructive testing (NDT), using the Kuan Tai and Tin Hau Temple in Taipa as a case study. A millimetre-accuracy 3D point cloud was used as a unified spatial framework to correlate multi-source inspection data. This framework spatially correlates multi-source data on elemental composition, thermal anomalies, and surface hardness. Our approach achieves high-precision digital documentation. It reveals that the primary degradation mechanism is sulfate-induced corrosion, caused by incense pollutants under high humidity. The entire system weighs under 4 kg, making it portable and minimally invasive. It provides a scientific basis for the preventive conservation and digital management of heritage in similar complex environments.

Urban roof segmentation plays a pivotal role in applications such as urban planning, infrastructure management, and renewable energy deployment. This study explores the evolution of deep learning techniques from traditional Convolutional Neural Networks (CNNs) to cutting-edge Transformer-based models in the context of roof segmentation from satellite imagery. We highlight the limitations of conventional methods when applied to urban environments, including resolution constraints and the complexity of roof structures. To address these challenges, we evaluate two advanced deep learning models: Mask R-CNN and MaskFormer, which have shown significant promise in accurately segmenting roofs, even in dense urban settings with diverse roof geometries. These models, especially the one based on transformers, offer improved segmentation accuracy by capturing both global and local image features, enhancing their performance in tasks where fine detail and contextual awareness are critical. A case study on Ben Guerir City in Morocco, an urban area experiencing rapid development, serves as the foundation for testing these models. Using high-resolution satellite imagery, the segmentation results offer a deeper understanding of the accuracy and effectiveness of these models, particularly in optimizing urban planning and renewable energy assessments. Quantitative metrics such as Intersection over Union (IoU), precision, recall, and F1-score are used to benchmark model performance. Mask R-CNN achieved a mean IoU of 74.6%, precision of 81.3%, recall of 78.9%, and F1-score of 80.1%. MaskFormer outperformed Mask R-CNN, reaching a mean IoU of 79.8%, precision of 85.6%, recall of 82.7%, and F1-score of 84.1%, highlighting the transformative potential of transformer-based architectures for scalable and precise urban imaging. The study also outlines future work in 3D modelling and height estimation, positioning these advancements as critical tools for sustainable urban development.

In the face of current challenges due to a pandemic, urban protests, an affordability crisis, and a series of other shocks to the quality of urban life, is the desirability of housing in dense urban settings at a turning point? Assessing the future of cities’ long term trends remains an empirical question. The first part of this chapter describes the short-run dynamics of the housing market in 2020. Evidence from prices and price-to-rent ratios suggests expectations of resilience. Zip code-level evidence suggests a short-run trend towards suburbanization, and some impacts of urban protests on house prices. The second part of the chapter analyzes the long-run dynamics of urban growth between 1970 and 2010. It analyzes what, in such urban growth, is explained by short-run shocks as opposed to fundamentals such as education, industrial specialization, industrial diversification, urban segregation, and housing supply elasticity. This chapter’s original results as well as a large established body of literature suggest that fundamentals are the key drivers of growth, and that the shocks considered in this paper have not had historically a measurable long-term impact on metropolitan population growth. The chapter illustrates this finding with two case studies: the New York City housing market after September 11, 2001; and the San Francisco Bay Area in the aftermath of the 1989 Loma Prieta earthquake. Both areas rebounded strongly after these shocks, suggesting the resilience of the urban metropolis.

This study investigated the influence of built environment features on crosswalk safety in dense urban settings, with a focus on visual streetscape characteristics extracted from street-view imagery using both semantic and instance segmentation. It used data from 36,750 crosswalks in Seoul, South Korea, to rigorously evaluate multiple machine learning algorithms for predicting pedestrian crash risk. Among the models assessed, the Random forest (RF) demonstrated the highest precision, aligning with the objective of enhancing pedestrian safety through accurate risk identification. The RF model enhanced by SHapley Additive exPlanations (SHAP) achieved strong predictive performance (precision: 0.91), and SHAP analysis identified visual features, particularly sky openness ratio, building coverage, and sidewalk ratio, as influential factors affecting crash risk. A lower sky openness ratio combined with a higher building ratio was associated with increased crash likelihood, whereas greater sidewalk coverage and the presence of traffic control measures, including traffic lights and crosswalk time indicators, mitigated risk. Interaction effects further highlighted the complexity of urban safety, showing that combinations of streetscape and infrastructural elements can amplify or reduce hazards. These results highlight the importance of combining visual and structural data for thorough risk assessment and further the use of interpretable machine learning in urban safety research. The findings imply that to address particular combinations of built environment elements that increase the risk of crosswalk crashes, policy and planning initiatives should concentrate on context-sensitive interventions, particularly by placing bus stops strategically, maintaining tree canopies for visibility, clearing visual clutter, and improving pedestrian infrastructure.

Recent improvements in the spatial resolution of commercial satellite imagery make it possible to apply very highresolution (VHR) satellite data for assessing structural damage in the aftermath of humanitarian crises, such as, armed conflicts. Visual interpretation of pre- and post-crisis very high-resolution satellite imagery is the most straightforward method for discriminating structural damage and assessing its extent. However, the feasibility of using visual interpretation alone diminishes in the cases of large and dense urban settlements and spatial resolutions in the range of 2 m to 3 meters and larger. Visual interpretation can be further complicated at spatial resolutions greater than 1 m if accompanied by shadow formation and differences in sensor and solar conditions between the pre- and post-conflict images. In this study, we address these problems through investigating the use of traditional change techniques, namely, image differencing and principle component analysis, with an object-oriented image classification software, e-Cognition. Pre-conflict Ikonos (2 m resolution) images of Jenin in the Palestinian territories and Brest (1 m resolution) in FYROM were classified using the e-Cognition software. Thereafter, the pre-conflict classification was used to guide the classification, using e-Cognition, of the pixel-based change detection analysis. The second part of the study examines the feasibility of using mathematical morphological operators to automatically identify likely structurally damaged zones in dense urban settings. The overall results are promising and show that object-oriented segmentation and classification systems facilitate the interpretation of change detection results derived from very high-resolution (1 m and 2 m) commercial satellite data. The results show that objectoriented classification techniques enhance quantitative analysis of traditional pixel-based change detection applied to very high-resolution satellite data and facilitate the interpretation of changes in urban features. Finally, the results suggest that mathematical morphological methods are a potential new avenue for automatically extracting likely damaged zones from very high-resolution satellite imagery in the aftermath of disasters.

Amid the different contemporary strategies for the delivery and management of sustainable development in the African context, not much emphasis has been placed on seeking for the existence or otherwise, of thermal opportunities from the inherent building types of our forebears. This paper therefore, through case study design approach, reported the developmental trend of indoor thermal comfort opportunities of building types with the design and construction traits representing the historic eras of pre-colonial, colonial and contemporary in Okigwe, Nigeria. The primary data were got from field observations made for 366 days (1 November 2015 – 31 October 2016) on the indoor and outdoor temperature and relative humidity values using Tinytag Explorer 4.9 Germini data loggers and secondary data from the nearest Meteorological Station, Imo State International Cargo Airport, Owerri, Nigeria. The mean annual outdoor temperature and relative humidity values were 29.00C and 69.9% respectively. Analyses of the results using one-way ANOVA test for differences were statistically significant; indoor air temperature [F (2, 1095) = 77.56, p = 0.0001] and relative humidity [F (2, 1095) = 5.76, p = 0.0001]. Further interrogation using the Tukey’s HSD (Honest Significant Difference) post-hoc comparison test amongst the building types revealed that indoor air temperature (27.830C) and relative humidity (71%) of pre-colonial building type were significantly different from those of colonial (28.430C and 67.39%) and contemporary building types (29.270C and 66.75%). The paper recommended that the valid traditional practices as expressed in the pre-colonial building types be re-integrated into the delivery and management of sustainable development in Nigeria. Thus, it concluded that opportunities abound in the indoor thermal comfort traceable to the traditional building (pre-colonial) types of our forebears as they performed thermally better than colonial and contemporary building types.

• Visual green exposure (>30 %) increases park stay duration and walking distance. • Integration of mobility data, panoramic imagery, and propensity score matching for causal inference. • VGE boosts engagement most in dense city centers but less in peri -urban settings. • VGE effects peak during weekends, mornings, and midday, declining by evening. • Seasonal analysis reveals stronger VGE influence in spring and fall months. Urban green spaces are vital components of city landscapes, yet the role of visible greenery in promoting park use remains poorly understood due to limitations of static, correlational evidence. This study provides quasi-experimental evidence linking visual green exposure (VGE) to urban park engagement, specifically visit duration and physical activity intensity, using large-scale human mobility data and panoramic imagery across Tokyo’s 23 special wards. Employing propensity score matching (PSM), inverse probability weighting (IPW), and overlap weighting (OW), the analysis reveals that park visits with average VGE exceeding 30% are result in 3.36 min longer stays and 116.95 m additional walking distance relative to lower-exposure visits. However, these effects exhibit systematic spatial and temporal heterogeneity. Spatially, urban density mediates VGE’s impact, high VGE boosts engagement in dense city centers but shortens walking distance in peri -urban areas. Temporally, the positive influence of VGE on stat duration is most pronounced on weekends and during morning to midday hours, while declines in evenings. Seasonally, spring and fall amplify the influence of VGE’s on physical activity, while winter shows minimal effects despite year-round accessibility. These findings demonstrate VGE is influential yet context-dependent driver of park usage. By translating visibility into quantifiable engagement metrics, this study offers actionable guidance for planners, including optimized canopy placement and strategic vegetation configuration, to enhance public interaction with nature in dense urban settings.

Self-driving cars typically rely on a set of radars for mapping the environment to avoid obstacles and operate safely. Currently, the radar parameters are uncoordinated and can interfere with each other. This results in inefficient use of the spectrum and, more importantly, in dangerous blinding of the radars especially in dense urban settings, posing a barrier to widespread deployment of self-driving cars. We present RadarMAC - the first system architecture and dynamic radar parameter assignment algorithms for radar interference mitigation in self-driving cars. We characterize the degrees of freedom for vehicular radar parameters, and model the channel parameter assignment problem as one of dynamically coloring the corresponding time-varying interference graph. RadarMAC guarantees interference-free radar operations within a defined capacity region. Using extensive simulations, we demonstrate that RadarMAC significantly outperforms the state-of-the-art random assignment scheme commonly used today with off-the-shelf radars in terms of safety and spectrum efficiency metrics in both dense and sparse settings. Finally, we identify a set of research challenges in medium access control for vehicular radars.

A procedure is proposed for the computational modeling of the driving of a deep tunnel by a tunnel-boring machine (TBM) with an active surcharge on the face, which is realized in the “GEO-MIGG” program. Basic factors affecting the stress-strain state (SSS) of the “soil bed-TBM- buildings and structures of the urban setting” system are demonstrated in a trial example. The feasibility of using the proposed procedure is confirmed by comparing results of computational modeling of a practical example of tunneling for the third transportation beltway around Moscow in the area of Lefortovo using a TBM manufactured by the German firm Herrenknecht” with data derived from field observations.

Quantitative health impact assessment of outdoor air pollution in the Arve valley, France