Journal
URBAN CLIMATE
Volume 48, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.uclim.2023.101430
Keywords
Coastal vulnerability; Climate change; Climate gentrification; Machine learning; Housing
Ask authors/readers for more resources
Climate change is expected to have complex implications for vulnerable populations, and the theory of climate gentrification provides a lens to understand its interaction with community dynamics. Using machine learning, this study identifies four clusters of vulnerability related to social, housing, and environmental variables in coastal communities along the US East Coast. The findings suggest different pathways of climate gentrification, emphasizing the need for proactive adaptation planning to mitigate disproportionate impacts on the most vulnerable.
Climate change is expected to alter community dynamics and characteristics in complex ways, with the most severe implications for already vulnerable populations. The theory of climate gentrification provides a lens for investigating the ways in which climate change interacts with community demographics, housing, and socioeconomic characteristics in coastal communities. Here we apply unsupervised machine learning to 51 counties along the United States East Coast to identify four distinct clusters of multifaceted vulnerability related to social, housing, and environmental variables. Two of the four clusters, interpreted as superior investment and disinvestment, may be indicative of different pathways of climate gentrification. We also demonstrate the applicability of our methodology at finer spatial scales using a case study within North Carolina. As coastal climate impacts increase, this work demonstrates the need for adaptation planning that proactively considers compounding vulnerabilities to avoid disproportionate impacts on the most vulnerable.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available