Measuring changes in neighborhood disorder using Google Street View longitudinal imagery: a feasibility study

Area of Science:

• Urban Health
• Environmental Science
• Geospatial Analysis

Background:

• Neighborhood disorder is linked to adverse health outcomes.
• Longitudinal data is crucial for understanding urban environmental changes.
• Google Street View (GSV) offers potential for tracking urban changes over time.

Purpose of the Study:

• To assess the feasibility of using longitudinal GSV imagery for urban health research.
• To measure changes in neighborhood disorder in the Philadelphia metropolitan region between 2009 and 2019.

Main Methods:

• Audited GSV images from 192 street segments in Philadelphia.
• Assessed image availability across 2009, 2014, and 2019.
• Collected 8 neighborhood disorder indicators at each time point for segments with available imagery.

Main Results:

• Over 70% of street segments had at least one GSV image available.
• Neighborhood disorder significantly increased from 2009 to 2019.
• Longitudinal GSV data captured temporal changes in urban streetscapes.

Conclusions:

• Longitudinal GSV imagery is a feasible tool for monitoring urban neighborhood disorder.
• Findings highlight a concerning trend of increasing neighborhood disorder.
• Future research should explore the drivers of these observed changes.