The interactions between vulnerability and human activities have largely been regarded in terms of the level of risk they pose, both internally and externally, for certain groups of disadvantaged individuals and regions/areas. However, to date, very few studies have attempted to develop a comprehensive composite regional vulnerability index, in relation to travel, housing, and social deprivation, which can be used to measure vulnerability at an aggregated level in the social sciences. Therefore, this research aims to develop a composite regional vulnerability index with which to examine the combined issues of travel, housing and socio-economic vulnerability (THASV index). It also explores the index’s relationship with the impacts of the COVID-19 pandemic, reflecting both social and spatial inequality, using Greater London as a case study, with data analysed at the level of Middle Layer Super Output Areas (MSOAs). The findings show that most of the areas with high levels of composite vulnerability are distributed in Outer London, particularly in suburban areas. In addition, it is also found that there is a spatial correlation between the THASV index and the risk of COVID-19 deaths, which further exacerbates the potential implications of social deprivation and spatial inequality. Moreover, the results of the multiscale geographically weighted regression (MGWR) show that the travel and socio-economic indicators in a neighbouring district and the related vulnerability indices are strongly associated with the risk of dying from COVID-19. In terms of policy implications, the findings can be used to inform sustainable city planning and urban development strategies designed to resolve urban socio-spatial inequalities and the potential related impacts of COVID-19, as well as guiding future policy evaluation of urban structural patterns in relation to vulnerable areas.

• Realistic representation of Land Use and Land Cover (LULC) changes improves the prediction of convection over urban regimes.

• The 2019 urban amalgamation in LULC spread in the weather model discloses that the rainfall intensity has increased compared to the 1980 LULC simulation

• The maximum rainfall limited to a shorter spell (~1 hour), due to the urban heating effect.

Understanding human mobility in touristic and historical cities is of the utmost importance for managing traffic and deploying new resources and services. In recent years, the need to enhance mobility has been exacerbated due to rapid urbanisation and climate changes. The main objective of this work is to study cycling mobility within the city of Bologna, Italy. We used six months dataset that consists of 320,118 self-reported bike trips. First, we performed several descriptive analysis to understand the temporal and spatial patterns of bike users for understanding popular roads and most favourite points within the city. The findings show how bike users present regular daily and weekly temporal patterns and the characteristics of their trips (i.e. distance, time and speed) follow well-known distribution laws. We also identified several points of interest in the city that are particularly attractive for cycling. Moreover, using several other public datasets, we found that bike usage is more correlated to temperature and precipitation and has no correlation to wind speed and pollution. We also exploited machine learning approaches for predicting short-term trips in the near future (that is for the following 10, 30, and 60 minutes), which could help local governmental agencies with urban planning. The best model achieved an R square of 0.91 for the 30-minute time interval, and a Mean Absolute Error of 2.52 and a Root Mean Squared Error of 3.88 for the 10-minute time interval.

The adverse health impacts of climate change have been well documented. It is increasingly apparent that the impacts are disproportionately higher in urban populations, especially underserved communities. Studies have linked urbanization and air pollution with health impacts, but the exacerbating role of urban heat islands (UHI) in the context of neurodegenerative diseases has not been well addressed. The complex interplay between climate change, local urban air pollution, urbanization, and a rising population in cities has led to the byproduct of increased heat stress in urban areas. Some urban neighborhoods with poor infrastructure can have excessive heat even after sunset, increasing internal body temperature and leading to hyperthermic conditions. Such conditions can put individuals at higher risk of stroke by creating a persistent neuroinflammatory state, including, in some instances, Alzheimer’s Disease (AD) phenotypes. Components of the AD phenotype, such as amyloid beta plaques, can disrupt long-term potentiation (LTP) and long-term depression (LTD), which can negatively alter the mesolimbic function and thus contribute to the pathogenesis of mood disorders. Furthermore, although a link has not previously been established between heat and Parkinson’s Disease (PD), it can be postulated that neuroinflammation and cell death can contribute to mitochondrial dysfunction and thus lead to Lewy Body formation, which is a hallmark of PD. Such postulations are currently being presented in the emerging field of ‘neurourbanism’. This study highlights that: (i) the impact of urban climate, air pollution and urbanization on the pathogenesis of neurodegenerative diseases and mood disorders is an area that needs further investigation; (ii) urban climate- health studies need to consider the heterogeneity in the urban environment and the impact it has on the UHI. In that, a clear need exists to go beyond the use of airport-based representative climate data to a consideration of more spatially explicit, high-resolution environmental datasets for such health studies, especially as they pertain to the development of locally-relevant climate adaptive health solutions. Recent advances in the development of super-resolution (downscaled climate) datasets using computational tools such as convolution neural networks (CNNs) and other machine learning approaches, as well as the emergence of urban field labs that generate spatially explicit temperature and other environmental datasets across different city neighborhoods, will continue to become important. Future climate – health studies need to develop strategies to benefit from such urban climate datasets that can aid the creation of localized, effective public health assessments and solutions.

As human activities highly depend on the land resources and changed the land cover (LC) condition, the relationship between LC and nighttime light (NTL) intensity has been widely analyzed to support the foundation of NTL applications and help explain the drivers of urban economic development. However, previous studies always paid attention to the effect of each LC type on NTL intensity, with limited consideration of the joint effects of any two LC types. To fill this gap, this study measured the land cover spatial combination (LCSC) by using a spatial adjacency matrix, and then analyzed its impacts on NTL intensity based on an extreme gradient boosting (XGBoost) regression model with the assistant of sharpley additive explanations (SHAP) method. Our results presented that the LCSC can better (R² of 82.4% and 98.1% in 2010 and 2020) explain the relationship between LC and NTL intensity with the traditional LC metrics (e.g., area and patch count), since the LCSC is much more sensitive to the diverse land functions. It is noteworthy that the impacts, as well as their dynamics, of LCSC between any two LC types on NTL intensity are various. LCSC associated with artificial surface contributed more to NTL intensity. In detail, the LCSC of water/wetland and artificial surface can increasingly promote the NTL intensity while the LCSC of grassland/forest and artificial surface has a decreasing or inverse U-shaped contribution to NTL intensity. Whereas LCSC associated with non-artificial surface were not conducive to the increase in NTL intensity due to high vegetation density. We also provided three implications to help further urbanization process and discussed the applications of LCSC.

Affected by the burden reduction policy, out-of-school hours care places have become a hot issue of social concern. Taking Xi’an out-of-school hours care places as a research case, this paper discusses its location choice, spatial relationships and influencing factors using methods such as text analysis, spatial analysis, and mathematical statistics. The results show that: (1) the distribution of out-of-school hours care places in Xi’an is closely related to the community and schools. The names mostly use words such as “sunshine,” “teacher,” and “love,” which are mainly distributed on the lower floors (one to three floors), of which the first floor accounts for the largest proportion. (2) The high-value areas of out-of-school hours care places are mainly concentrated in the Lianhu District, Yanta District, Xincheng District, and the north Chang’an District. Their distribution has obvious directionality, showing a “northeast-southwest” trend, and the global spatial autocorrelation is positively correlated. (3) The spatial pattern of out-of-school hours care places is basically consistent with that of primary and secondary schools, and most of them are located within 1000 m of it. (4) The influencing factors mainly include the distribution of primary and secondary schools, residential areas, population density, house rent, and policies.

People express opinions, make connections, and disseminate information on social media platforms. We considered grocery-related tweets as a proxy for grocery shopping behaviors or intentions. We collected data from January 2019 to January 2022, representing three typical times of the normal period before the COVID-19 pandemic, the outbreak period, and the widespread period. We obtained grocery-related geotagged tweets using a search term index based on the top 10 grocery chains in the US and compiled Google Trends online grocery shopping data. We performed a topic modeling analysis using the Latent Dirichlet Allocation (LDA), and verified that most of the collected tweets were related to grocery-shopping demands or experiences. Temporal and geographical analyses were applied to investigate when and where people talked more about groceries, and how COVID-19 affected them. The results show that the pandemic has been gradually changing people’s daily shopping concerns and behaviors, which have become more spread throughout the week since the pandemic began. Under the causal impact of COVID-19, people first experienced panic buying groceries followed by pandemic fatigue a year later. The normalized tweet counts show a decrease of 40% since the pandemic began, and the negative causal effect can be considered statistically significant (p-value = 0.001). The variation in the quantity of grocery-related tweets also reflects geographic diversity in grocery concerns. We found that people in non-farm areas with less population and relatively lower levels of educational attainment tend to act more sensitively to the evolution of the pandemic. Utilizing the COVID-19 death cases and consumer price index (CPI) for food at home as background information, we proposed an understanding of the pandemic’s impact on online grocery shopping by assembling, geovisualizing, and analyzing the evolution of online grocery behaviors and discussion on social media before and during the pandemic.

Bhubaneswar is the first designed ‘smart city’ in India and has experienced rapid urbanization since 2000. The question undertaken in this study is to assess if there is a change in the rainfall over this rapidly urbanizing region, and if so, what are the characteristics of the change? The broader intent is to understand if the change in urbanization and rainfall are interlinked? The India Meteorological Department (hourly station and daily gridded) and Tropical Rainfall Measurement Mission (3-hourly) datasets are analyzed for the 1980–2018 period (39 years) for different seasons separately. Wavelet and trend analysis reveal that precipitation intensity has increased over the study period. The assessments of the hourly rainfall data show an interesting feature. There is a decrease in the midnight to early-morning rain, with a corresponding increase in the late-afternoon to midnight rainfall. The increase in the rainfall is preferentially downwind and on the east side of the city. A supervised classified land use land cover map of the Bhubaneswar region is developed for 1980, 1990, 2000, 2010, and 2019 using Landsat imagery to compute the urban sprawl. The urban area and population density over Bhubaneswar is increasing with time. Analysis of the LULC and rainfall data indicates that the rainfall over urban regions and the shift in the timing of rains to evenings is highly correlated with the urban sprawl.

The bath industry has multiple attributes, such as economic, health, and cultural communication. Therefore, exploring this industry's spatial pattern evolution is crucial to forming a healthy and balanced development model. Based on POI (Points of Interest) and population migration data, this paper uses spatial statistics and radial basis function neural network to explore the spatial pattern evolution and influencing factors of the bath industry in mainland China. The results show that: (1) The bath industry presents a strong development pattern in the north, south-northeast, and east-northwest regions and weak development in the rest of the country. As a result, the spatial development of new bath space is more malleable. (2) The input of bathing culture has a guiding role in developing the bath industry. The growth of market demand and related industries has a specific influence on the development of the bath industry. (3) Improving the bath industry's adaptability, integration, and service level are feasible to ensure healthy and balanced development. (4) Bathhouses should improve their service system and risk management control during the pandemic.

With the population of older adults growing globally, this study asks the question: are older adults living in compact developments more active than those living in sprawling developments? Older adults can be deemed more active if they travel more in total or travel more by non-auto travel modes (such as walking, transit). By analyzing disaggregated data from 36 regions of the United States, this study finds that older adults living in compact neighborhoods do not travel more in total but travel more by walking and public transportation than those living in sprawling neighborhoods. In addition, older adults travel less, are more auto-dependent, and make more home-based-nonwork trips, compared to younger adults. Older adults with lower income travel less than those with higher income. Older adults living in compact neighborhoods with the lowest income level generate the highest number of transit trips. It is important for planners and policy makers to not only create built environments that support older adults’ travel needs, but also to avoid social inequity.

Existing studies lack attention to taxi usage dynamics, considering its trip proportion over other travel modes and its influencing factors at fine spatiotemporal resolutions. To fill these gaps, we propose a method for examining taxi usage in a grid of 1 km × 1 km cells per hour during a one-day cycle in Beijing. This method measures the differences between taxi trips from taxi trajectory data and mobile signaling data in the same week in January 2017. To explain the spatiotemporal variation in taxi usage, multiple linear models were used to investigate taxi usage dynamics with alternative transport modes, socioeconomic factors, and built environments. In summary, this study proposes to develop an indicator to measure taxi usage using multiple data sources. We confirm that taxi usage dynamics exist in both temporal and spatial dimensions. In addition, the effects of taxi usage factors vary over each hour in a one-day cycle. These findings are useful for urban planning and transport management, in which the dynamic interactions between taxi demand and distribution of facilities should be included.

Urban green and blue spaces refer to the natural and semi-natural areas within a city or urban area. These spaces can include parks, gardens, rivers, lakes, and other bodies of water. They play a vital role in the sustainability of cities by providing a range of ecosystem services such as air purification, carbon sequestration, water management, and biodiversity conservation. They also provide recreational and social benefits, such as promoting physical activity, mental well-being, and community cohesion. Urban green and blue spaces can also act as buffers against the negative impacts of urbanization, such as reducing the heat island effect and mitigating the effects of stormwater runoff. Therefore, it is important to maintain and enhance these spaces to ensure a healthy and sustainable urban environment. Assessing urban green and blue spaces with space-based multi-sensor datasets can be a valuable tool for sustainable development. These datasets can provide information on the location, size, and condition of green and blue spaces in urban areas, which can be used to inform decisions about land use, conservation, and urban planning. Space-based sensors, such as satellites, can provide high-resolution data that can be used to map and monitor changes in these spaces over time. Additionally, multi-sensor datasets can be used to gather information on a variety of environmental factors, such as air and water quality, that can impact the health and well-being of urban residents. This information can be used to develop sustainable solutions for preserving and enhancing urban green and blue spaces. This study examines how urban green and blue infrastructures might improve sustainable development. Space-based multi-sensor datasets are used to estimate urban green and blue zones for sustainable development. This work can inform sustainable development research at additional spatial and temporal scales.

The Community-Group-Buying Points (CGBPs) flourished during COVID-19, safeguarding the daily lives of community residents in community lockdowns, and continuing to serve as a popular daily shopping channel in the Post-Epidemic Era with its advantages of low price, convenience and neighborhood trust. These CGBPs are allocated on location preferences however spatial distribution is not equal. Therefore, in this study, we used point of interest (POI) data of 2,433 CGBPs to analyze spatial distribution, operation mode and accessibility of CGBPs in Xi’an city, China as well as proposed the location optimization model. The results showed that the CGBPs were spatially distributed as clusters at α = 0.01 (Moran’s I = 0.44). The CGBPs operation mode was divided into preparation, marketing, transportation, and self-pickup. Further CGBPs were mainly operating in the form of joint ventures, and the relying targets presented the characteristic of ‘convenience store-based and multi-type coexistence’. Influenced by urban planning, land use, and cultural relics protection regulations, they showed an elliptic distribution pattern with a small oblateness, and the density showed a low–high-low circular distribution pattern from the Palace of Tang Dynasty outwards. Furthermore, the number of communities, population density, GDP, and housing type were important driving factors of the spatial pattern of CGBPs. Finally, to maximize attendance, it was suggested to add 248 new CGBPs, retain 394 existing CGBPs, and replace the remaining CGBPs with farmers’ markets, mobile vendors, and supermarkets. The findings of this study would be beneficial to CGB companies in increasing the efficiency of self-pick-up facilities, to city planners in improving urban community-life cycle planning, and to policymakers in formulating relevant policies to balance the interests of stakeholders: CGB enterprises, residents, and vendors.

The increasing level of air pollutants (e.g. particulates, noise and gases) within the atmosphere are impacting mental wellbeing. In this paper, we define the term ‘DigitalExposome’ as a conceptual framework that takes us closer towards understanding the relationship between environment, personal characteristics, behaviour and wellbeing using multimodal mobile sensing technology. Specifically, we simultaneously collected (for the first time) multi-sensor data including urban environmental factors (e.g. air pollution including: Particulate Matter (PM1), (PM2.5), (PM10), Oxidised, Reduced, Ammonia (NH3) and Noise, People Count in the vicinity), body reaction (physiological reactions including: EDA, HR, HRV, Body Temperature, BVP and movement) and individuals’ perceived responses (e.g. self-reported valence) in urban settings. Our users followed a pre-specified urban path and collected the data using a comprehensive sensing edge device. The data is instantly fused, time-stamped and geo-tagged at the point of collection. A range of multivariate statistical analysis techniques have been applied including Principle Component Analysis, Regression and Spatial Visualisations to unravel the relationship between the variables. Results showed that Electrodermal Activity (EDA) and Heart Rate Variability (HRV) are noticeably impacted by the level of Particulate Matter in the environment. Furthermore, we adopted Convolutional Neural Network (CNN) to classify self-reported wellbeing from the multimodal dataset which achieved an f1-score of 0.76.

The objective of this study is to predict road flooding risks based on topographic, hydrologic, and temporal precipitation features using machine learning models. Existing road inundation studies either lack empirical data for model validations or focus mainly on road inundation exposure assessment based on flood maps. This study addresses this limitation by using crowdsourced and fine-grained traffic data as an indicator of road inundation, and topographic, hydrologic, and temporal precipitation features as predictor variables. Two tree-based machine learning models (random forest and AdaBoost) were then tested and trained for predicting road inundations in the contexts of 2017 Hurricane Harvey and 2019 Tropical Storm Imelda in Harris County, Texas. The findings from Hurricane Harvey indicate that precipitation is the most important feature for predicting road inundation susceptibility, and that topographic features are more critical than hydrologic features for predicting road inundations in both storm cases. The random forest and AdaBoost models had relatively high AUC scores (0.860 and 0.810 for Harvey respectively and 0.790 and 0.720 for Imelda respectively) with the random forest model performing better in both cases. The random forest model showed stable performance for Harvey, while varying significantly for Imelda. This study advances the emerging field of smart flood resilience in terms of predictive flood risk mapping at the road level. In particular, such models could help impacted communities and emergency management agencies develop better preparedness and response strategies with improved situational awareness of road inundation likelihood as an extreme weather event unfolds.

The use of telehealth has increased significantly over the last decade and has become even more popular and essential during the COVID-19 pandemic due to social distancing requirements. Telehealth has many advantages including potentially improving access to healthcare in rural areas and achieving healthcare equality. However, there is still limited research in the literature on how to accurately evaluate telehealth accessibility. Here we present the Enhanced Two-Step Virtual Catchment Area (E2SVCA) model, which replaces the binary broadband strength joint function of the previous Two-Step Virtual Catchment Area (2SVCA) with a step-wise function that more accurately reflects the requirements of telehealth video conferencing. We also examined different metrics for representing broadband speed at the Census Block level and compared the results of 2SVCA and E2VCA. Our study suggests that using the minimum available Internet speed in a Census Block can reveal the worst-case scenario of telehealth care accessibility. On the other hand, using the maximum of the most frequent available speeds reveals optimal accessibility, while the minimum of the most frequent reflects a more common case. All three indicators showed that the 2SVCA model generally overestimates accessibility results. The E2SVCA model addresses this limitation of the 2SVCA model, more accurately reflects reality, and more appropriately reveals low accessibility regions. This new method can help policymakers in making better decisions about healthcare resource allocations aiming to improve healthcare equality and patient outcomes.

Floods are one of the most prevalent and costliest natural hazards globally. The safe transit of people and goods during a flood event requires fast and reliable access to flood depth information with spatial granularity comparable to the road network. In this research, we propose to use crowdsourced photos of submerged traffic signs for street-level flood depth estimation and mapping. To this end, a deep convolutional neural network (CNN) is utilized to detect traffic signs in user-contributed photos, followed by comparing the lengths of the visible part of detected sign poles before and after the flood event. A tilt correction approach is also designed and implemented to rectify potential inaccuracy in pole length estimation caused by tilted stop signs in floodwaters. The mean absolute error (MAE) achieved for pole length estimation in pre- and post-flood photos is 1.723 and 2.846 in., respectively, leading to an MAE of 4.710 in. for flood depth estimation. The presented approach provides people and first responders with a reliable and geographically scalable solution for estimating and communicating real-time flood depth data at their locations.

The High Line park (HLP) in New York City is one of the most successful contemporary greenway parks, inspiring urban planners, designers, artists, and administrators worldwide. This study provides a comprehensive understanding of user experiences in a long-term time frame (2011–2018) through the lens of online reviews. Using a mixed-methods approach, we conducted Latent Dirichlet Allocation (LDA) topic modeling to quantitatively identify the key topics that represent 34,060 reviews and 30,285 users, followed by qualitative analysis to inductively interpret the LDA topics. The results identified experiential, programmatic and physical elements of the HLP that are meaningful to users. Three primary components were found that make HLP successful according to users: spectacular visual and activity-related experiences, the historical transformation and cultural exploration, and the added value from park services ranging from amenities to on-site living performance. The article helps inform future decision-making and planning & design practices for future greenway projects.

Most types of crimes show seasonal fluctuations but the difference and similarity of the periodicity between different crimes are understudied. Interpreting the seasonality of different crime types and formulating clusters of crimes that share similar seasonal characteristics would help identify the common underlying factors and revise the patterns of patrolling and monitoring to enable sustained management of the control strategies. This study proposes a new methodological framework for measuring similarities and differences in the timing of peaks and troughs, as well as the waveforms of different crimes. The method combines a Poisson state-space model with cluster analysis and multi-dimensional scaling. A case study using twelve types of crimes in London (2013–2020) demonstrated that the amplitude of the seasonal fluctuation identified by this method explained 95.2% of the similarity in their waveforms, while the timing of the peaks covered 87.5% of the variance in their seasonal fluctuation. The high predictability of the seasonal patterns of crimes as well as the stable categorisation of crimes with similar seasonal characteristics enable sustainable and measured planning of police resource allocation and, thereby, facilitates a more efficient management of the urban environment.

The COVID-19 pandemic caused lifestyle changes and has led to the new electricity demand patterns in the presence of non-pharmaceutical interventions such as work-from-home policy and lockdown. Quantifying the effect on electricity demand is critical for future electricity market planning yet challenging in the context of limited smart metered buildings, which leads to limited understanding of the temporal and spatial variations in building energy use. This study uses a large scale private smart meter electricity demand data from the City of Austin, combined with publicly available environmental data, and develops an ensemble regression model for long term daily electricity demand prediction. Using 15-min resolution data from over 400,000 smart meters from 2018 to 2020 aggregated by building type and zip code, our proposed model precisely formalizes the counterfactual universe in the without COVID-19 scenario. The model is used to understand building electricity demand changes during the pandemic and to identify relationships between such changes and socioeconomic patterns. Results indicate the increase in residential usage , demonstrating the spatial redistribution of energy consumption during the work-from-home period. Our experiments demonstrate the effectiveness of our proposed framework by assessing multiple socioeconomic impacts with the comparison between the counterfactual universe and observations.

Recent advancements in artificial intelligence (AI) have seen the emergence of smart video surveillance (SVS) in many practical applications, particularly for building safer and more secure communities in our urban environments. Cognitive tasks, such as identifying objects, recognizing actions, and detecting anomalous behaviors, can produce data capable of providing valuable insights to the community through statistical and analytical tools. However, artificially intelligent surveillance systems design requires special considerations for ethical challenges and concerns. The use and storage of personally identifiable information (PII) commonly pose an increased risk to personal privacy. To address these issues, this paper identifies the privacy concerns and requirements needed to address when designing AI-enabled smart video surveillance. Further, we propose the first end-to-end AI-enabled privacy-preserving smart video surveillance system that holistically combines computer vision analytics, statistical data analytics, cloud-native services, and end-user applications. Finally, we propose quantitative and qualitative metrics to evaluate intelligent video surveillance systems. The system shows the 17.8 frame-per-second (FPS) processing in extreme video scenes. However, considering privacy in designing such a system results in preferring the pose-based algorithm to the pixel-based one. This choice resulted in dropping accuracy in both action and anomaly detection tasks. The results drop from 97.48% to 73.72% in anomaly detection and 96% to 83.07% in the action detection task. On average, the latency of the end-to-end system is 36.1 seconds.

Cities need climate information to develop resilient infrastructure and for adaptation decisions. The information desired is at the order of magnitudes finer scales relative to what is typically available from climate analysis and future projections. Urban downscaling refers to developing such climate information at the city (order of 1 – 10 km) and neighborhood (order of 0.1 – 1 km) resolutions from coarser climate products. Developing these higher resolution (finer grid spacing) data needed for assessments typically covering multiyear climatology of past data and future projections is complex and computationally expensive for traditional physics-based dynamical models. In this study, we develop and adopt a novel approach for urban downscaling by generating a general-purpose operator using deep learning. This ‘DownScaleBench’ tool can aid the process of downscaling to any location. The DownScaleBench has been generalized for both in situ (ground- based) and satellite or reanalysis gridded data. The algorithm employs an iterative super-resolution convolutional neural network (Iterative SRCNN) over the city. We apply this for the development of a high-resolution gridded precipitation product (300 m) from a relatively coarse (10 km) satellite-based product (JAXA GsMAP). The high-resolution gridded precipitation datasets is compared against insitu observations for past heavy rain events over Austin, Texas, and shows marked improvement relative to the coarser datasets relative to cubic interpolation as a baseline. The creation of this Downscaling Bench has implications for generating high-resolution gridded urban meteorological datasets and aiding the planning process for climate-ready cities.

Temporal data series of stable Artificial Lights At Night (ALAN) obtained from sources such as DMSP/OLS and VIIRS/DNB provide valuable insights into the dynamics of urban expansion. This study introduces a novel methodology for characterizing urban boundaries, which combines textural analysis utilizing the Co-occurrence matrix and urban surface delineation employing the Wombling contour detection algorithm. Applying this method to the city of Korhogo in northern Côte d'Ivoire, the findings reveal an irregular and gradual evolution of urban surfaces between 1992 and 2012, with a rate of change of 35 km². However, starting from 2012, a rapid urbanization process is observed, continuing until 2020, characterized by an evolution rate of approximately 45 km². Considering the significant urban expansion witnessed in the city of Korhogo, it is imperative to implement appropriate urban management strategies and measures for ecosystem protection.

Intersection markings play a vital role in providing road users with guidance and information. The conditions of intersection markings will be gradually degrading due to vehicular traffic, rain, and/or snowplowing. Degraded markings can confuse drivers, leading to increased risk of traffic crashes. Timely obtaining high-quality information of intersection markings lays a foundation for making informed decisions in safety management and maintenance prioritization. However, current labor-intensive and high-cost data collection practices make it very challenging to gather intersection data on a large scale. This paper develops an automated system to intelligently detect intersection markings and to assess their degradation conditions with existing roadway Geographic information systems (GIS) data and aerial images. The system harnesses emerging artificial intelligence (AI) techniques such as deep learning and multi-task learning to enhance its robustness, accuracy, and computational efficiency. AI models were developed to detect lane-use arrows (85% mean average precision) and crosswalks (89% mean average precision) and to assess the degradation conditions of markings (91% overall accuracy for lane-use arrows and 83% for crosswalks). Data acquisition and computer vision modules developed were integrated and a graphical user interface (GUI) was built for the system. The proposed system can fully automate the processes of marking data collection and condition assessment on a large scale with almost zero cost and short processing time. The developed system has great potential to propel urban science forward by providing fundamental urban infrastructure data for analysis and decision-making across various critical areas such as data-driven safety management and prioritization of infrastructure maintenance.

Climate change is one of the most pressing global challenges we face today. The impacts of rising temperatures, sea levels, and extreme weather events are already being felt around the world and are only expected to worsen in the coming years. To mitigate and adapt to these impacts, we need innovative, data-driven solutions. Artificial intelligence (AI) has emerged as a promising tool for climate change adaptation, offering a range of capabilities that can help identify vulnerable areas, simulate future climate scenarios, and assess risks and opportunities for businesses and infrastructure. With the ability to analyze large volumes of data from climate models, satellite imagery, and other sources, AI can provide valuable insights that can inform decision-making and help us prepare for the impacts of climate change. However, the use of AI in climate change adaptation also raises important ethical considerations and potential biases that must be addressed. As we continue to develop and deploy these solutions, it is crucial to ensure that they are transparent, fair, and equitable. In this context, this article explores the latest innovations and future directions in AI-enabled climate change adaptation strategies, highlighting both the potential benefits and the ethical considerations that must be considered. By harnessing the power of AI for climate change adaptation, we can work towards a more resilient, sustainable, and equitable future for all.

Cool materials and rooftop vegetation help achieve urban heating mitigation as they can reduce building cooling demands. This study assesses the cooling potential of different mitigation technologies using Weather Research and Forecasting (WRF)- taking case of a tropical coastal climate in the Kolkata Metropolitan Area. The model was validated using data from six meteorological sites. The cooling potential of eight mitigation scenarios was evaluated for: three cool roofs, four green roofs, and their combination (cool-city). The sensible heat, latent heat, heat storage, 2-m ambient temperature, surface temperature, air temperature, roof temperature, and urban canopy temperature was calculated. The effects on the urban boundary layer were also investigated.

The different scenarios reduced the daytime temperature of various urban components, and the effect varied nearly linearly with increasing albedo and green roof fractions. For example, the maximum ambient temperature decreased by 3.6 °C, 0.9 °C, and 1.4 °C for a cool roof with 85% albedo, 100% rooftop vegetation, and their combination.

The cost of different mitigation scenarios was assumed to depend on the construction options, location, and market prices. The potential for price per square meter and corresponding temperature decreased was related to one another. Recognizing the complex relationship between scenarios and construction options, the reduction in the maximum and minimum temperature across different cool and green roof cases were used for developing the cost estimates. This estimate thus attempted a summary of the price per degree of cooling for the different potential technologies.

Higher green fraction, cool materials, and their combination generally reduced winds and enhanced buoyancy. The surface changes alter the lower atmospheric dynamics such as low-level vertical mixing and a shallower boundary layer and weakened horizontal convective rolls during afternoon hours. Although cool materials offer the highest temperature reductions, the cooling resulting from its combination and a green roof strategy could mitigate or reverse the summertime heat island effect. The results highlight the possibilities for heat mitigation and offer insight into the different strategies and costs for mitigating the urban heating and cooling demands.

The Southeast Tunisian cave dwellings of Matmata are a well-known historical model which amazingly adapt with cultural, environmental and climatic features of its surrounding. Many studies have discussed the sustainability of these dwellings but none has thoroughly discussed its performance on light of health and wellbeing of its dwellers. The WELL_V1 rating system, established in 2016, is a first of a kind certification system that solely focus on the health performance of the built environment. It gives credit to designs that enhance and promote physical and psychological health of the users. The study examines the health performance of Matmata cave dwellings in the light of WELL_V1 recommendations and features. The study revealed that these subterranean historical dwellings have proven good performance in relation to daylight saturation, indoor thermal relief, solar glare control, physical activity enhancement, exterior noise reduction, biophilic design and cultural enrichment. On the other hand, they lack sufficient performance in relation to air purification, social interaction, clean water supply, and altruism encouragement. Considering the scientific background, materials and technologies available for those who designed and built these dwellings, the health-related performance of their work seems unique and impressive.

In smart cities, ensuring road safety and optimizing transportation efficiency heavily relies on streamlined road condition monitoring. The application of Artificial Intelligence (AI) has notably enhanced the capability to detect road surfaces effectively. This study presents a novel approach to road condition monitoring in smart cities through the development of an acoustic data processing and analysis module. It focuses on four types of road conditions: smooth, slippery, grassy, and rough roads. To assess road conditions, a microphone integrated road surface detector unit is designed to collect audio signals, and an ultrasonic module is used to observe the road depth information. The whole hardware unit is installed in the wheel rim of the vehicles. The data collected from the road surfaces are then analyzed using machine learning algorithms, such as Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), and Random Forest (RF). The results demonstrate the effectiveness of the proposed method in accurately identifying different road conditions. From these results, it was observed that the MLP provides better accuracy of 98.98% in assessing road conditions. The study provides valuable insights into the development of a more efficient and reliable road condition monitoring system for delivering secure transportation services in smart cities.

The online and in-store shopping landscape underwent transformative shifts due to the Covid-19 pandemic, potentially leading to novel hybrid shopping behaviors following the availability of Covid-19 vaccines. However, these new dynamics, especially for non-essential experience goods which were heavily impacted by lockdowns, remain relatively unexplored. Moreover, variations in such dynamics within the same product class are not well understood. This study investigates the interactions between online and in-store shopping behaviors across four categories of non-essential experience goods: clothing, shoes, watches, and jewelry (CSWJ); beauty and health products (BH); toys, kids, and baby supplies (TKB); and home, garden, and tools (HGT). Data from over 2,000 Florida residents collected in early 2021, encompassing purchase frequencies, attitudes, and socio-demographic attributes, were analyzed using separate bidirectional structural equation models. Findings indicate that the relationship between online and in-store shopping for CSWJ and TKB exhibited reciprocal complementarity effects. In contrast, BH and HGT displayed an asymmetric reciprocal relationship, with in-store shopping showing no significant influence on online shopping. Results on the mediating influence of attitudes on shopping behaviors showed that a pro-online shopping attitude and preference for alternative travel modes positively influenced online shopping frequency, while the joy of shopping and data privacy/security concerns emerged as drivers of in-store shopping across all product categories. In sum, this study underscores the presence of product-specific heterogeneity even within the experience goods class, contributing to the complex interactions between online and in-store shopping behaviors.

Evacuation destination choice modeling is an integral aspect of evacuation planning. Outputs from such models are required to estimate the clearance times on which evacuation orders are based. The number of evacuees arriving at each destination also informs allocation of resources and shelter planning. Despite its importance, evacuee destination modeling has not received as much attention as identifying who evacuates and when. In this study, we present a new approach to identify evacuees and determine where they go and when using privacy-enhanced smartphone location data. We demonstrate the method using data from four recent U.S. hurricanes affecting multiple geographies (Florence 2018, Michael 2018, Dorian 2019, and Ida 2021). We then build on those results to develop a new machine learning model that predicts the number of evacuees that move between pairs of metropolitan statistical areas. The machine learning model incorporates hurricane characteristics, which have not been thoroughly exploited by existing methods. The model’s predictive power is comprehensively evaluated through a tenfold cross validation, holdout validation using Hurricane Ida (2021), and comparison with the traditional gravity model. Results suggest that the new model substantially outperforms the traditional gravity model across all performance indicators. Analysis of feature importance in the machine learning model indicates that in addition to distance and population, hurricane characteristics are important in evacuee destination choices.

This phenomenon of slums represents one of the most serious problems that Iraqi cities suffer from, especially the city of Baghdad, which has become teeming with a lot of slum buildings that have distorted most of its areas and neighborhoods. Most of the slums are in the form of scattered construction and chaotic gatherings that do not follow any planning standards. This paper aims to present and analyze the mechanisms of urban upgrading of two models of slums in the city of Baghdad and London. The treatment was through the urban development of these slums and the provision and improvement of services to reduce the phenomenon of total removal. The GIS program was used to calculate the urban variables and requirements, the optimal locations for services, and the total and partial removal percentages. The research achieved the lowest percentage of total and partial removal of the actual areas, which amounted to 7.31% in the first model and 14.26% in the second model. The slum area was also provided with all the necessary services in accordance with the urban housing standards specific to each city, to turn it into a residential neighborhood instead of calling it a slum region.

Cities are information systems by its social and physical components. The data of these components create a wider picture in urban texture than it was designed by planners and designer in urban practices. The idea of collecting the data and composing models of spontaneous actions in urban simulations can add different dimensions to planning ideas in social terms and spatial texture. The issue is to find out how these components can be better related with each other to let citizens be urban planners as well up to some level, and what level that would be. The aim of the project is to bring back the social impact of the whole city as linking the hubs of Karaköy and Kabataş through the waterfront, also reawakening the collective memory of the port, by preserving the texture of warehouses form Ottoman Empire. The final outcome would be understanding how effectively project would be able to create the dynamics that have been proposed, and whether there have been other spontaneous actions thought the designed area.

The development of high-precision location tracking devices and advancements in data collection, storage, transmission technologies, and data mining algorithms have led to the availability of large datasets with high spatiotemporal resolution. These geospatial big data can be used to identify human movement patterns in urban areas. However, identifying human movement patterns may yield different results depending on the scale size used. In this paper, we employed first and second order texture analysis algorithms to identify spatial patterns of human movement for various scale sizes based on taxi trajectory data from Nanjing, China. The results demonstrated that texture analysis can quantify changes in human movement patterns for different scale sizes in an urban area. Furthermore, the results may differ based on the location of the study area. This study contributed both methodologically and empirically. Methodologically, we used texture analysis to examine the impact of different scale sizes on the extraction of aggregated human travel patterns. Empirically, we quantified the effects of different scale sizes on extracting aggregated travel patterns of an urban area. Overall, the findings of this study can have significant implications for urban planning and policy-making, as understanding human movement patterns at different scales can provide valuable insights for optimizing transportation systems and enhancing overall urban mobility.

Connected and Autonomous Vehicles (CAVs) are reshaping urban systems, demanding substantial computational support. While existing research emphasizes the significance of establishing physical and virtual infrastructure to facilitate CAV integration, a comprehensive framework for designing CAV-related infrastructure principles remains largely absent. This paper introduces a holistic framework that addresses gaps in current literature by presenting principles for the design of CAV-related infrastructure. We identify diverse urban infrastructure types crucial for CAVs, each characterized by intricate considerations. Deriving from existing literature, we introduce five principles to guide investments in physical infrastructure, complemented by four principles specific to virtual infrastructure. These principles are expected to evolve with CAV development and associated technology advancements. Furthermore, we exemplify the application of these principles through a case study in Oxford, UK. In doing so, we assess urban conditions, identify representative streets, and craft CAV-related urban infrastructure tailored to distinct street characteristics. This framework stands as a valuable reference for cities worldwide as they prepare for the increasing adoption of CAVs.

Spatial colocation has been studied in many contexts including locations of urban facilities, industry entities and businesses. However, identifying colocations among a small number of facilities and establishments holds the risk of introducing false positive in that such a spatial arrangement may have occurred by chance. To account for the association between a group of facilities that frequently colocate with each other, this study proposes a two-step approach consisting of identifying statistically significant clusters of each facility type using the False Discovery Rate (FDR) controlling procedure, and subsequently measuring the colocation of those clusters with the frequent-pattern-growth (FP-growth) algorithm. Empirical analysis of 6 million business and industrial establishments across Japan suggests that 10 out of 86 industry types form clear colocations and their colocations form a multi-layered, cascading structure. The number of layers in the multi-layered structure reflect the city size and the strength of the association between the colocated clusters of industries. These patterns illustrate the utility of detecting colocation of clusters towards understanding the agglomeration of different businesses. The proposed method can be applied to other contexts that would benefit from investigations into how different types of spatial features can be linked with each other and how they form colocations.

Urban areas experience significant alterations in their local surface energy balance due to changes in the thermal properties of impervious surfaces, albedo, land use, and land cover. In addition, the embedded influence of urbanization and heat-trapping in the urban canopy cause city temperature warmer compared to its surroundings peri-urban regions. However, the influence of urbanization on winter surface temperatures remains unclear. In this study, the urbanization influence on winter surface temperature in Bhubaneswar, a tropical two-tier city in India, is assessed using a high-resolution (4 km × 4 km) urban canopy model coupled with the Weather Research and Forecasting model. Numerical experiments are conducted with no urban coupling (CTL) and with coupling of a single-layer urban canopy model (UCM) for the winters of 2004 and 2015. The study suggests that both model simulations exhibit a similar warm bias in mean surface temperature (~ 2.2 °C), but UCM’s surface temperature better agrees with the observations compared to CTL. The warm bias in both experiments is primarily contributed by a higher nighttime warm bias (~ 3.2 °C). The study reveals that urbanization contributes to ~ 0.4 °C increase in surface temperature in 2015, especially in the eastern lowland regions of the city, while the impact is minimal in 2004. In the western region, the influence is nullified, possibly due to lower surface specific humidity affecting longwave radiation in a higher terrain setting. This study underscores the significance of terrain and local microclimate conditions in shaping winter urban surface temperatures, shedding light on the complex interplay between urbanization and climate.