Authors: Donghee Koh*, University of Tennessee
Topics: Medical and Health Geography, Human-Environment Geography, Urban Geography
Keywords: neighborhood, mental health, vulnerability, geo-visualization, self-organizing map, Los Angeles
Session Type: Paper
Presentation File: No File Uploaded
Using Los Angeles County as a case study, this research aims to (1) develop neighborhood-level mental health vulnerability typologies and (2) examine their spatial distribution and its associations to racial/ethnic residential segregation patterns. The whole process of developing mental health vulnerability typologies was driven by consultations with the existing theoretical frameworks. A total of 16 variables was identified, and they can be divided into five neighborhood domains: socioeconomic structure, residential stability, disorder, physical environmental quality, and pollution burden. Using a Self-organizing map (SOM), an approach combining computational and geo-visualization techniques, the component planes were derived which were then used to systematically examine relationships among the variables. Next, a k-means clustering algorithm was employed to segment the multi-dimensional SOM output space into sub-typologies that neatly capture the neighborhood-level mental health vulnerability. Finally, the results were mapped in order to examine their spatial distribution patterns. By and large, the findings indicated that centrally-located and minority-concentrated neighborhoods tend to display a higher level of mental health vulnerability compared to suburban White-dominant neighborhoods. It was also found that there exist interesting partial and non-linear relationships among the variables. The findings of this study, we believe, offer useful insights that can help local governments devise more effective and efficient intervention plans.