A direct observation method for auditing large urban centers using stratified sampling, mobile GIS technology and virtual environments

A spatial obesity risk score for describing the obesogenic environment using kernel density estimation: development and parameter variation

BACKGROUND

Overweight and obesity are severe public health problems worldwide. Obesity can lead to chronic diseases such as type 2 diabetes mellitus. Environmental factors may affect lifestyle aspects and are therefore expected to influence people's weight status. To assess environmental risks, several methods have been tested using geographic information systems. Freely available data from online geocoding services such as OpenStreetMap (OSM) can be used to determine the spatial distribution of these obesogenic factors. The aim of our study was to develop and test a spatial obesity risk score (SORS) based on data from OSM and using kernel density estimation (KDE).

METHODS

Obesity-related factors were downloaded from OSM for two municipalities in Bavaria, Germany. We visualized obesogenic and protective risk factors on maps and tested the spatial heterogeneity via Ripley's K function. Subsequently, we developed the SORS based on positive and negative KDE surfaces. Risk score values were estimated at 50 random spatial data points. We examined the bandwidth, edge correction, weighting, interpolation method, and numbers of grid points. To account for uncertainty, a spatial bootstrap (1000 samples) was integrated, which was used to evaluate the parameter selection via the ANOVA F statistic.

RESULTS

We found significantly clustered patterns of the obesogenic and protective environmental factors according to Ripley's K function. Separate density maps enabled ex ante visualization of the positive and negative density layers. Furthermore, visual inspection of the final risk score values made it possible to identify overall high- and low-risk areas within our two study areas. Parameter choice for the bandwidth and the edge correction had the highest impact on the SORS results.

DISCUSSION

The SORS made it possible to visualize risk patterns across our study areas. Our score and parameter testing approach has been proven to be geographically scalable and can be applied to other geographic areas and in other contexts. Parameter choice played a major role in the score results and therefore needs careful consideration in future applications.

GeoAI for Large-Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography

GeoAI, or geospatial artificial intelligence, has become a trending topic and the frontier for spatial analytics in Geography. Although much progress has been made in exploring the integration of AI and Geography, there is yet no clear definition of GeoAI, its scope of research, or a broad discussion of how it enables new ways of problem solving across social and environmental sciences. This paper provides a comprehensive overview of GeoAI research used in large-scale image analysis, and its methodological foundation, most recent progress in geospatial applications, and comparative advantages over traditional methods. We organize this review of GeoAI research according to different kinds of image or structured data, including satellite and drone images, street views, and geo-scientific data, as well as their applications in a variety of image analysis and machine vision tasks. While different applications tend to use diverse types of data and models, we summarized six major strengths of GeoAI research, including (1) enablement of large-scale analytics; (2) automation; (3) high accuracy; (4) sensitivity in detecting subtle changes; (5) tolerance of noise in data; and (6) rapid technological advancement. As GeoAI remains a rapidly evolving field, we also describe current knowledge gaps and discuss future research directions.

Area based stratified random sampling using geospatial technology in a community-based survey

BACKGROUND

Most studies among Hispanics have focused on individual risk factors of obesity, with less attention on interpersonal, community and environmental determinants. Conducting community based surveys to study these determinants must ensure representativeness of disparate populations. We describe the use of a novel Geographic Information System (GIS)-based population based sampling to minimize selection bias in a rural community based study.

METHODS

We conducted a community based survey to collect and examine social determinants of health and their association with obesity prevalence among a sample of Hispanics and non-Hispanic whites living in a rural community in the Southeastern United States. To ensure a balanced sample of both ethnic groups, we designed an area stratified random sampling procedure involving three stages: (1) division of the sampling area into non-overlapping strata based on Hispanic household proportion using GIS software; (2) random selection of the designated number of Census blocks from each stratum; and (3) random selection of the designated number of housing units (i.e., survey participants) from each Census block.

RESULTS

The proposed sample included 109 Hispanic and 107 non-Hispanic participants to be recruited from 44 Census blocks. The final sample included 106 Hispanic and 111 non-Hispanic participants. The proportion of Hispanic surveys completed per strata matched our proposed distribution: 7% for strata 1, 30% for strata 2, 58% for strata 3 and 83% for strata 4.

CONCLUSION

Utilizing a standardized area based randomized sampling approach allowed us to successfully recruit an ethnically balanced sample while conducting door to door surveys in a rural, community based study. The integration of area based randomized sampling using tools such as GIS in future community-based research should be considered, particularly when trying to reach disparate populations.

Moving to policy-amenable options for built environment research: The role of micro-scale neighborhood environment in promoting walking

BACKGROUND

Altering micro-scale features of neighborhoods (e.g., the presence and condition of benches, sidewalks, trees, crossing signals, walking paths) could be a relatively cost-effective method of creating environments that are conducive to physical activity. The Virtual Systematic Tool for Evaluating Pedestrian Streetscapes (Virtual-STEPS) was created to virtually audit the microscale environment of cities using Google Street View (GSV). The objective of this study was to evaluate the collective influence of items from the Virtual-STEPS tool on walking outcomes (utilitarian walking and walking for leisure), while accounting for self-selection of walkers into walking-friendly neighborhoods.

METHODS

Adults (N = 1403) were recruited from Montreal and Toronto from neighborhoods stratified by their level of macro-scale walking-friendliness and walking rates. The micro-scale environment of 5% of street segments from the selected neighborhoods was audited using the Virtual-STEPS tool and a micro-scale environment score was assigned. The scores were then linked to each respondent from the survey. A multilevel logistic regression analysis was used to model the relationship between the micro-scale environment score and odds of both utilitarian walking (i.e., walking for purpose such as to go shopping or go to work or school) and walking for leisure for at least 150 min per week, while accounting for environmental and demographic covariates as well as self-selection.

RESULTS

Micro-scale neighborhood features were associated with elevated odds of walking for leisure (OR: 1.14, CI: 1.04-1.25). The association between micro-scale neighborhood features and walking for utilitarian purposes was, however, inconclusive (OR: 1.01, CI: 0.90-1.13). On the other hand, macro-scale walk-friendliness was associated with elevated odds of walking for utilitarian purposes (OR: 2.01, CI:1.42-2.84) and the association between macro-scale features and leisure walking was inconclusive (OR: 1.02, CI: 0.78-1.34).

CONCLUSIONS

Our results imply that micro-scale features of neighborhoods collectively promote leisure walking but not necessarily utilitarian walking, even after accounting for self-selection. In contrast, macro-scale features may collectively promote utilitarian walking, but not leisure walking. Micro scale features of neighborhoods fall within the budget of local jurisdictions and our results suggest that jurisdictions that improve micro-scale features may expect increased leisure walking in populations.

Assessing the micro-scale environment using Google Street View: the Virtual Systematic Tool for Evaluating Pedestrian Streetscapes (Virtual-STEPS)

Background

Altering micro-scale features of neighborhood walkability (e.g., benches, sidewalks, and cues of social disorganization or crime) could be a relatively cost-effective method of creating environments that are conducive to active living. Traditionally, measuring the micro-scale environment has required researchers to perform observational audits. Technological advances have led to the development of virtual audits as alternatives to observational field audits with the enviable properties of cost-efficiency from elimination of travel time and increased safety for auditors. This study examined the reliability of the Virtual Systematic Tool for Evaluating Pedestrian Streetscapes (Virtual-STEPS), a Google Street View-based auditing tool specifically designed to remotely assess micro-scale characteristics of the built environment.

Methods

We created Virtual-STEPS, a tool with 40 items categorized into 6 domains (pedestrian infrastructure, traffic calming and streets, building characteristics, bicycling infrastructure, transit, and aesthetics). Items were selected based on their past abilities to predict active living and on their feasibility for a virtual auditing tool. Two raters performed virtual and field audits of street segments in Montreal neighborhoods stratified by the Walkscore that was used to determine the ‘walking-friendliness’ of a neighborhood. The reliability between virtual and field audits (n = 40), as well as inter-rater reliability (n = 60) were assessed using percent agreement, Cohen’s Kappa statistic, and the Intra-class Correlation Coefficient.

Results

Virtual audits and field audits (excluding travel time) took similar amounts of time to perform (9.8 versus 8.2 min). Percentage agreement between virtual and field audits, and for inter-rater agreement was 80% or more for the majority of items included in the Virtual-STEPS tool. There was high reliability between virtual and field audits with Kappa and ICC statistics indicating that 20 out of 40 (50.0%) items had almost perfect agreement and 13 (32.5%) items had substantial agreement. Inter-rater reliability was also high with 17 items (42.5%) with almost perfect agreement and 11 (27.5%) items with substantial agreement.

Conclusions

Virtual-STEPS is a reliable tool. Tools that measure the micro-scale environment are important because changing this environment could be a relatively cost-effective method of creating environments that are conducive to active living.

Electronic supplementary material

The online version of this article (10.1186/s12889-019-7460-3) contains supplementary material, which is available to authorized users.

Deep mapping gentrification in a large Canadian city using deep learning and Google Street View

Gentrification is multidimensional and complex, but there is general agreement that visible changes to neighbourhoods are a clear manifestation of the process. Recent advances in computer vision and deep learning provide a unique opportunity to support automated mapping or ‘deep mapping’ of perceptual environmental attributes. We present a Siamese convolutional neural network (SCNN) that automatically detects gentrification-like visual changes in temporal sequences of Google Street View (GSV) images. Our SCNN achieves 95.6% test accuracy and is subsequently applied to GSV sequences at 86110 individual properties over a 9-year period in Ottawa, Canada. We use Kernel Density Estimation (KDE) to produce maps that illustrate where the spatial concentration of visual property improvements was highest within the study area at different times from 2007–2016. We find strong concordance between the mapped SCNN results and the spatial distribution of building permits in the City of Ottawa from 2011 to 2016. Our mapped results confirm those urban areas that are known to be undergoing gentrification as well as revealing areas undergoing gentrification that were previously unknown. Our approach differs from previous works because we examine the atomic unit of gentrification, namely, the individual property, for visual property improvements over time and we rely on KDE to describe regions of high spatial intensity that are indicative of gentrification processes.

Systematic review of the use of Google Street View in health research: Major themes, strengths, weaknesses and possibilities for future research

We systematically reviewed the current use of Google Street View (GSV) in health research and characterized major themes, strengths and weaknesses in order to highlight possibilities for future research. Of 54 qualifying studies, we found that most used GSV to assess the neighborhood built environment, followed by health policy compliance, study site selection, and disaster preparedness. Most studies were conducted in urban areas of North America, Europe, or New Zealand, with few studies from South America or Asia and none from Africa or rural areas. Health behaviors and outcomes of interest in these studies included injury, alcohol and tobacco use, physical activity and mental health. Major strengths of using GSV imagery included low cost, ease of use, and time saved. Identified weaknesses were image resolution and spatial and temporal availability, largely in developing regions of the world. Despite important limitations, GSV is a promising tool for automated environmental assessment for health research. Currently untapped areas of health research using GSV include identification of sources of air, soil or water pollution, park design and usage, amenity design and longitudinal research on neighborhood conditions.

Environmental Influences on Physical Activity among Rural Adults in Montana, United States: Views from Built Environment Audits, Resident Focus Groups, and Key Informant Interviews

Rural populations in the United States have lower physical activity levels and are at a higher risk of being overweight and suffering from obesity than their urban counterparts. This paper aimed to understand the environmental factors that influence physical activity among rural adults in Montana. Eight built environment audits, 15 resident focus groups, and 24 key informant interviews were conducted between August and December 2014. Themes were triangulated and summarized into five categories of environmental factors: built, social, organizational, policy, and natural environments. Although the existence of active living features was documented by environmental audits, residents and key informants agreed that additional indoor recreation facilities and more well-maintained and conveniently located options were needed. Residents and key informants also agreed on the importance of age-specific, well-promoted, and structured physical activity programs, offered in socially supportive environments, as facilitators to physical activity. Key informants, however, noted that funding constraints and limited political will were barriers to developing these opportunities. Since building new recreational facilities and structures to support active transportation pose resource challenges, especially for rural communities, our results suggest that enhancing existing features, making small improvements, and involving stakeholders in the city planning process would be more fruitful to build momentum towards larger changes.