This study examined changes in the spatial patterns and determinants of road collisions in Ciudad Juarez, Mexico in 2019 and 2020, encompassing the initial period of COVID-19 mobility restrictions. Kernel density estimation and local indicators of spatial association were used to compare collision distributions and identify significant clusters between years. A geographically weighted negative binomial regression model then generated local coefficients to analyze how demographic, socioeconomic, land use, and road network factors influenced collision probability spatially. Results show collisions decreased 13.18% in 2020 but clustered differently, validating restrictions' impact. Population aged 15–64 and industrial land uses significantly increased risk spatially, whereas commercial uses decreased. Lower socioeconomic conditions also correlated with higher risk. Younger populations presented varying collision likelihoods intra-urbanly. This research thus emphasizes how local contexts shape risk factors’ effects and informs data-driven safety policies accounting for place-specific issues. By adopting an explicitly spatial modeling approach, localized risk patterns were uncovered not detectable through traditional methods.

This study presents the first in-depth analysis of spatial differences and factors influencing wealth distribution among households in India. It uses data from the latest National Family Health Survey, covering 707 districts. Techniques like the Lorenz curve, Gini coefficient, Location Quotient, Morans statistics, and Univariate and Bivariate LISA methods explore inequalities, concentration, and clustering patterns of rich-poor households at the district level. Additionally, spatial regression models such as OLS, GWR, and MGWR help to uncover spatial disparities and variability. Our findings demonstrate significant regional disparities, with the affluent household concentration being notably higher in north-western and southern India, while central, eastern, and northeastern regions exhibit greater inequality. Key factors impacting wealth inequality include rurality, low female literacy rates, educational level of household heads and prevalence of Scheduled Castes/Tribes. This study highlights the spatial dimensions of wealth inequality and provides a nuanced understanding of the factors contributing to these patterns. The GWR and MGWR models prove most effective, explaining more than 90% of the variation in wealth distribution factors. This study sheds light on the spatial dynamics and factors behind wealth disparities in India, offering strategic insights for equitable growth initiatives targeting diverse socio-economic sectors.

Traditional linear models often struggle to capture regional housing markets' complex, non-linear dynamics. This study addresses this gap by developing and applying advanced machine learning algorithms to unlock unique insights into South Australian housing price behavior. Leveraging a comprehensive dataset of over 10,000 regional house sales from 2010 to 2021, we explore the non-linear relationships between housing prices and microeconomic factors (e.g., house size, land area, building quality) and socioeconomic characteristics (e.g., proximity to amenities and income levels). Our analysis employs a multi-step approach, including feature engineering, spatial data integration, correlation tests, multilevel modeling, and non-linear machine learning algorithms including Decision Tree, Random Forest, Gradient-Boosted Tree, and Artificial Neural Network. The key finding is that machine learning models outperform traditional econometric models in predicting regional housing prices, with higher accuracy and greater goodness of fit. Furthermore, we identify specific non-linear relationships, such as the increasing marginal impact of proximity to the sea on house prices as distance decreases. These findings offer valuable insights for policymakers, real estate professionals, and stakeholders, informing regional planning, infrastructure provision, and economic development strategies. This study sheds light on the complex dynamics of South Australian housing markets and lays the foundation for further research.

Over the past several decades, the issue of housing burden has emerged as a critical global challenge, with China serving as a pivotal case study amid its urbanization surge. Previous research has mainly focused on the purchasing aspects of housing burden within isolated urban contexts, often overlooking the significance of rental burden. Employing a panel dataset of 270 Chinese cities from 2014 to 2020, this article analyzes the spatial-temporal patterns of purchasing and rental burden across those cities. Furthermore, based on a proposed analytical framework, this article empirically examines the factors influencing the housing burden. This article finds that the housing burden in China is mainly concentrated in some major cities and city-regions, and the influential factors of the purchasing and rental burden vary. This article contributes to a comprehensive understanding of China's landscape of housing burden, which is critical for designing more efficient and inclusive housing policies globally.

Mobile big data has emerged as an essential tool for various scientific research fields. However, the credibility of mobile big data and the extent to which it can represent the real-world population remain unclear. This study evaluated the representativeness of mobile big data by comparing it to the most recent census data at the county level in China. Using power-law and multiple linear regression models, we aim to determine the accuracy and reliability of mobile big data in reflecting the population dynamics and characteristics of different geographical areas. Our results indicate that disparities among individuals with different socioeconomic statuses, demographic characteristics, or geographic locations may contribute to biased estimations of the actual population density. Higher illiteracy rates and median ages may be associated with underestimating population density. In contrast, higher GDP per capita, elevated urbanization levels, and larger percentages of the 15–64 year age group may be associated with overestimating population density. Our research highlights the importance of cross-validating population estimates and offering practical statistical methods for addressing potential biases and estimating population dynamics in future applications of mobile big data.

Activity spaces characterise an individual's mobility patterns and provide critical insights important to a broad suite of applications. Emergent forms of disaggregate space-time data offer new opportunities to exploit a more granular approach to measuring and visualising activity spaces. Drawing on individual GPS trajectories for 365 participants covering a seven-day period the current paper presents a new measurement and visualisation framework examining the directionality of mobility patterns. This framework moves beyond existing work that measures activity spaces via a simple geometric shape (traditionally a convex hull) to introduce a new metric and associated visual analytic capturing a new dimension of the concept. Results have important consequences for policy and planning, with the hope that the framework can be redeployed across various situational and cultural contexts, leading to the creation of an expanding collection of comparative studies.

Wildfires have been causing negative effects on ecosystems and rural communities. Among rural communities, the agrarian reform settlement projects have registered fires resulting from agricultural management inside and outside their areas. In this context, our objective was to analyze 821 settlement projects in the Matopiba region to explore the spatial-temporal dynamics of burned area occurrences. For this, we used the burned area data from MCD64A1 v006, from 2001 to 2021, and estimated the total burned area and its percentage for each settlement project per month and per year, and the frequency and trend. Based on these characteristics, we classified each settlement project to identify patterns. We identified a temporal pattern, with inter-annual variations, associated with the dry season. Also, the extension of the burned area increased significantly in the years of drought anomaly. Settlement projects with high and low fire frequency coexist in the same region. We also identified a small cluster with a positive trend in the northeast of the Matopiba region related to the surrounding agriculture expansion area. The classification based on burned area, trend and frequency is useful to select priority settlement projects for fire prevention actions.

The incongruous patterns of urban growth often give rise to a myriad of issues, notably urban sprawl and urban shrinkage. These challenges frequently coexist and interact, presenting formidable obstacles to achieving sustainable city development. Therefore, investigations that endeavor to scrutinize both urban expansion and shrinkage in concert from a comprehensive perspective are essential. Present works of defining this trajectory are still vague, in which there is no clear clarification, and the relationship with socioeconomic also tends to be neglected. Thus, we proposed a new framework utilizing characteristic changes over 30 years in population and density to conduct a synthesis of urban growth patterns in 3911 cities worldwide along with their driving factors. We found that the development stage played a crucial role in urban growth pattern. Specifically, the densification cities were mostly found in the early stages of industrialization and urbanization. However, in accelerated industrialization and fast-developing regions, sprawl cities progressively gained dominance. Most cities followed the sprawl pattern and more shrinkage cities began to emerge in regions which in post-industrialization developed at high stages. Factors including industrialization level, urbanization rate, initial population density, terrain, and cultivated land conditions all exerted notable influences revolving around the urban growth process. Our study aims to help gain an overall sense of the global urbanization process as well as guide decision-makers to search for tailor-made management policies and urban planning for cities at various development stages. The patterns of expansion and shrinkage could offer support for a more comprehensive assessment of SDG indicators 11.3.1 and thus inform policies for urban sustainable development.

Spaces for play in children's daily-life are essential for their development. However, planning in most cities is limitedly aware of children's needs for playable-spaces. This study explores a PPGIS-approach to identify the “Playscape-quality” of a city, offering insights for planners. Our approach involved 416 children in Mariwan\\Iran. Using polygons instead of the conventional pinning-points, children digitally mapped their favourite-outdoor-places: two within their neighborhood and two at the city-level, they mapped 1664 polygons. For all places children answered a series of questions like the visit frequency. Furthermore, children were invited to geo-visualize the quality of their places. For measuring the playscape-quality we developed two indicators. Highly-Appreciated-Places Index for Days (HAPiDAYS) and Sparkling Urban Blend index (SUBindex). HAPiDAYS assesses the influence of hotspots, in term of days, on children's daily-routines and SUBindex quantifies overlapping highly-used-places with hotspots. Drawn polygons cover 9.3% of Mariwan, highlighting 9 hotspots, with most of the 120 received Geo-visualizations corresponding to them. HAPiDAYS, representing 29 days-per-year, and SUBindex indicate a 24% overlap, both approved favourite-outdoors extend beyond children's regular-daily-adventures. This emphasizes that besides providing urban spaces for citizens, evaluating the influence of these spaces on users' lives, (in this case children), should be considered from their own perspective.

As population aging has been an issue worldwide, the mobility of older people have attracted the attention of scholars from urban planning, transport geography, and social science. However, few have investigated socio-spatial differentiation among mobility groups, considering their daily needs and activity spaces. To fill this research gap, we conducted a comparative analysis of socio-spatial differentiation, based on individual activity spaces. We used smart card data from Kunming, China, to identify selected individuals’ residential locations and travel patterns, and evaluate their accessed activity space. We performed a disaggregated analysis of the individual activity space, and then aggregated the activity counts on each grid. This study found that the residential locations of older metro travelers are significantly different from those of other metro travelers. In addition, socio-spatial differentiation was found to exist due to different daily requirements. The results were confirmed in three LASSO models with built environment variables. These findings are useful in urban and transportation planning to improve elder-friendly services.