![Decorative image of a simple terrain map](/sites/g/files/omnuum10826/files/styles/hwp_21_9__1920x825/public/datasmart/files/random_images_-_generated_6.png?itok=xEhG4Cbl) # How Localized Spatial Data can Inform Decision-Making About the Community Data Health Initiative July 29, 2024 [ Coco Plasencia ](#cocoplasencia) [ Kristianny Ruelas-Vargas ](#kristiannyruelasvargas) The COVID-19 pandemic changed not only the lives of millions across the globe, but also how policymakers use [spatial tools for decision-making.](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7725052/) Health officials at the federal, state, and local level used geographic information systems (GIS) to track infection patterns, predict outbreaks, and optimize public health responses, providing a compelling case study for the utility of localized spatial data for both real-time decisions and long-term planning. Localized spatial data are geographically tagged and can include information on physical features, demographic details, land use patterns, infrastructure, and environmental conditions. The data are often collected through GIS, remote sensing technologies, Global Positioning System (GPS) devices, and, increasingly, Internet of Things (IoT) sensors. As environmental and public health efforts become more intersectional and justice-oriented, the importance of using technologies and designing data-driven solutions has grown in equal measure. This modernized approach requires more sophisticated data to address the complex nature of systemic environmental health inequities. Spatial data provides the necessary precision to track and address health disparities and environmental burdens in real time across sectors. It also enables governments to visualize environmental conditions, health outcomes, and access to resources, which can be used to develop more targeted interventions, promote equity in policy decisions, monitor progress, and identify areas for improvement. This article highlights successful applications of localized spatial data to accomplish goals within environmental work of preservation, adaptation, mitigation, and prediction. ## Preservation: Protecting Farmland in Indiana and Illinois [In Indiana and Illinois, spatial analysis has been critical in safeguarding agricultural areas.](https://www.researchgate.net/profile/Aaron-Thompson-8/publication/223510339_Tracking_urban_sprawl_Using_spatial_data_to_inform_farmland_preservation_policy/links/601c31a6a6fdcc37a8024420/Tracking-urban-sprawl-Using-spatial-data-to-inform-farmland-preservation-policy.pdf) Urban sprawl often leads to the loss of valuable farmland, impacting food security, environmental quality, rural economies and, ultimately, health outcomes. Urbanization can increase levels of air pollution and jeopardize access to affordable goods for neighboring communities, both of which can have consequences for public health. Previous approaches to agricultural preservation lacked effective methods for measuring the direct conversion of farmland into urban areas. GIS and satellite imagery can fill this gap by providing information on land use patterns, land cover changes, and the extent of urban sprawl. These technologies enhance policymaking by providing data-driven insights into land use trends and the impacts of urbanization. Policymakers can leverage spatial analysis to develop targeted preservation strategies, allocate resources efficiently, and incorporate public health considerations. This ensures a balance between urban planning, environmental sustainability, and public health promotion. ## Adaptation: Enhancing Flood Resilience in Boston, MA The city of Boston’s [“Climate Ready Boston”](https://www.boston.gov/environment-and-energy/climate-ready-boston) initiative uses spatial data to assess rising temperatures and prepare for coastal flooding due to sea-level rise. It [utilizes ArcGIS to simulate areas at risk of flooding hazards and predict the impacts on coastal communities.](https://www.sasaki.com/projects/climate-ready-boston/) Forecasting these risks allows the city to plan for and prevent health issues such as [waterborne diseases](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6119235/), [heat stress](https://www.who.int/news-room/fact-sheets/detail/climate-change-heat-and-health), and other weather-related injuries. Through leveraging precise geographic information, “Climate Ready Boston” can assess and predict environmental risk to prevent climate-related illness and death with heightened accuracy. It also aids in developing neighborhood-specific resilience strategies and engaging communities in policy development through feedback from residents and private landowners. The integration of spatial data in the city’s decision-making processes enhances its ability to adapt to intensifying climate change and protect populations at risk. ## Mitigation: Exploring Redlining Effects and Heat Islands in Portland, OR In Portland, Oregon, Dr. Vivek Shandas and his team at Portland State University have been using satellite data to map heat at a granular level across the city. Their spatial research visualizes how urban heat islands, areas that retain and absorb heat due to a lack of natural land cover, affect different communities. They found that, on average, previously redlined areas [faced 10.4°Fahrenheit higher](http://www.climatehubs.usda.gov/hubs/northwest/topic/urban-heat-islands-northwest#:~:text=To%20this%20day,%20many%20formerly,warmer%20than%20the%20city's%20average.) temperatures than the rest of the city. This inequitable risk for heat exposure also directly correlates with stark health disparities among people of color and low-income residents. The city of Portland used Shandas’s research to inform strategies to reduce heat by as much as [25 degrees through planting trees and vegetation, installing green roofs, and using reflective material ](https://www.capastrategies.com/building-on-the-results-of-community-heat-mapping-efforts)in underserved areas. In this case, spatial analytics not only helped identify and address urban heat disparities in overburdened communities, but also served to guide local government officials and community organizations in using localized interventions that accounts for historical harm. ## Prediction: Identifying Housing-Related Public Health Issues in Chelsea, MA In 2020, Dr. Katherine Robb conducted a case study on housing code violations in Chelsea, Massachusetts, assessing minimum health and safety standards. Through merging housing code violation data with administrative city data, researchers used machine learning to reveal potential public health risks like overcrowding and mold or insect infestations. The spatial distribution of predicted high-risk violations and overcrowding can help cities identify critical public health information. These spatial predictions can be used to better inform current programs and systems resource allocation. Spatial data can also enable cities to [prioritize inspections of properties with elevated predicted risk levels](/news/article/can-we-predict-where-housing-related-public-health-problems-exist-using-city-data "Can We Predict Where Housing-related Public Health Problems Exist Using City Data?"), thereby reducing health risks for residents. By leveraging machine learning and spatial analysis, cities can [enforce housing codes as a strategy to combat inadequate housing and poor health](https://nchh.org/tools-and-data/housing-code-tools/national-healthy-housing-standard/) more effectively. In a [recent podcast with the Data-Smart City Solutions](/leveraging-data-healthier-neighborhoods-kate-robb "Leveraging Data for Healthier Neighborhoods with Kate Robb"), Robb discussed the link between residential housing and health data. Her research explores the relationship between COVID-19 and living conditions during the first year of the pandemic, finding that even when taking other factors such as age, sex, income into account, people living in substandard housing were 48% more likely to test positive during the lockdown period. This stark finding sheds light on the ways in which densely populated, underserved communities are more at risk during a pandemic; it also highlights the need for using multidisciplinary data to advocate for and invest in safe and affordable housing. Ultimately, spatial data has the power to better prepare local officials to distribute resources [“before, during, and after a public health crisis.”](/leveraging-data-healthier-neighborhoods-kate-robb "Leveraging Data for Healthier Neighborhoods with Kate Robb") ## Advancing Environmental Justice Using Localized Spatial Data The EPA defines [environmental justice](https://www.epa.gov/environmentaljustice) as the fair treatment and meaningful involvement of all communities regardless of nationality, race, income, or disability in the development, implementation, and enforcement of environmental regulations and policies. Health equity is inextricably linked to environmental justice, which is why it is critical to ensure that [everyone has equitable access to a healthy, sustainable, resilient environment](https://www.epa.gov/environmentaljustice). As cities incorporate spatial analysis into decision-making processes, it is vital to identify and visualize environmental health disparities to build equitable solutions that reach underserved neighborhoods. Spatial data enables cities to work toward remediating environmental risks and improving health outcomes through data-driven, place-based solutions. A localized data-driven approach allows for more accurate risk assessments, targeted interventions, and efficient resource allocation. As demonstrated with the COVID-19 pandemic and the referenced case studies, spatial tools enable policymakers to improve decision-making in the face of complex and evolving challenges. Through collecting data across various agencies and levels of government, combined with community input, cities can use spatial analysis to envision and implement a more equitable and just future. ## About the Author ![Headshot of Coco Placencia](/sites/g/files/omnuum10826/files/styles/hwp_1_1__100x100_scale/public/datasmart/files/coco_placencia_itgh.jpg?itok=YP133zZ5) ### Coco Plasencia Coco Plasencia is a recent graduate of Wellesley College and a participant in the Health, Technology, & Society Summer Education Program at the Institute for Technology and Global Health. Her research interests lie at the intersection between reproductive health, medical technology, and AI ethics. Previously, Coco served as a research assistant in a Neuroscience lab, where she utilized machine learning to identify microbial biomarkers for gynecologic and obstetric risk. Coco is from Miami, Florida and holds a bachelor’s degree in Biological Sciences and Anthropology. --- ## About the Author ![Headshot of Kristianny Ruelas-Vargas ](/sites/g/files/omnuum10826/files/styles/hwp_1_1__100x100_scale/public/datasmart/files/ruelas_headshot_itgh.jpg?itok=-DBMRz0w) ### Kristianny Ruelas-Vargas Kristianny Ruelas-Vargas is a graduate student of Wellesley College and a participant in the Health, Technology, & Society 2024 Summer Education Program at the Institute for Technology and Global Health. Her academic research interest lies in exploring how technology and policy can be utilized to address health disparities faced by marginalized communities through an intersectional lens. Previously, she worked as a research assistant in a language and cognitive development laboratory at Wellesley and analyzed the role of trust during COVID-19 at the University of Southern California. Kristianny resides in Mesa, Arizona and holds a bachelor’s degree in Data Science and Women’s & Gender Studies. See also:- [ Environment ](/topics/environment) - [ Equity ](/topics/equity) - [ Public Health ](/topics/public-health) Share on:- [ Facebook ](#) - [ Twitter ](#) - [ Linkedin ](#)