Don't Let Lead Lead on Environmental Justice
Presentation Type
Poster
Faculty Advisor
Danlin Yu
Access Type
Event
Start Date
26-4-2024 12:45 PM
End Date
26-4-2024 1:44 PM
Description
Despite ongoing efforts to address environmental injustices, institutional shortcomings and historic exclusionary practices continue to perpetuate a climate of inequity across the globe. In seeking to address these inequities, entities frequently rely on state and federal tools designed to identify hotspots of known environmental injustices. However, these tools exhibit limitations in their ability to provide timely, comprehensive understandings of emerging injustices. These challenges stem from a reliance on traditional data sources and methodologies, which may fail to capture the intricate spatial, social, and political dynamics that contribute to injustices in a timely manner. We propose an investigation of alternative methods for environmental injustice detection, capitalizing on big data sources such as remote sensing, search engine, and social media data to identify emerging inequities faster and with greater consideration for urban human dynamics. To this end, we conduct an investigation of lead contamination in Newark, New Jersey with regard to environmental justice. Our analysis employs a system dynamics simulation methodology to model the interactions between lead contamination, Google search frequency, socioeconomic, and relevant environmental characteristics over time. Preliminary results show a strong correlation between blood lead levels and Google derived indexes. The current model has been narrowed down to 18 pivotal factors, but further refinement is required to stabilize the simulation. Once validated, a stabilized simulation can be used to forecast equity and lead contamination levels under a business-as-usual scenario, demonstrating the opportunities and pitfalls of leveraging big data in environmental injustice detection.
Don't Let Lead Lead on Environmental Justice
Despite ongoing efforts to address environmental injustices, institutional shortcomings and historic exclusionary practices continue to perpetuate a climate of inequity across the globe. In seeking to address these inequities, entities frequently rely on state and federal tools designed to identify hotspots of known environmental injustices. However, these tools exhibit limitations in their ability to provide timely, comprehensive understandings of emerging injustices. These challenges stem from a reliance on traditional data sources and methodologies, which may fail to capture the intricate spatial, social, and political dynamics that contribute to injustices in a timely manner. We propose an investigation of alternative methods for environmental injustice detection, capitalizing on big data sources such as remote sensing, search engine, and social media data to identify emerging inequities faster and with greater consideration for urban human dynamics. To this end, we conduct an investigation of lead contamination in Newark, New Jersey with regard to environmental justice. Our analysis employs a system dynamics simulation methodology to model the interactions between lead contamination, Google search frequency, socioeconomic, and relevant environmental characteristics over time. Preliminary results show a strong correlation between blood lead levels and Google derived indexes. The current model has been narrowed down to 18 pivotal factors, but further refinement is required to stabilize the simulation. Once validated, a stabilized simulation can be used to forecast equity and lead contamination levels under a business-as-usual scenario, demonstrating the opportunities and pitfalls of leveraging big data in environmental injustice detection.