Exploring Spatial Inequities and Livability: A Mixed-Methods Study Using Artificial Intelligence and Community Insights

Why It Matters

The findings reveal how spatial inequities directly limit mobility and safety for disadvantaged communities, urging planners to prioritize universal‑design investments and data‑driven equity assessments.

Key Takeaways

• AI identified only 9.7% curb ramps across streets
• Deficits linked to lower incomes and higher Black populations
• Community interviews validated AI‑detected inequities
• Method merges scalable AI with local narratives
• Framework offers replicable equity‑centered urban audits

Pulse Analysis

The integration of vision‑language models with large language models marks a turning point for urban audits, allowing researchers to process thousands of street‑level images quickly while preserving contextual nuance. By training the AI on Google Street View data, the study generated granular metrics on lighting, pavement continuity, and universal‑design features—variables traditionally gathered through costly field surveys. This technological leap not only accelerates data collection but also creates a consistent baseline for comparing neighborhoods over time, supporting evidence‑based decision making in municipal agencies.

Beyond the numbers, the research underscores the lived reality of spatial inequity in historically disinvested areas. The low prevalence of curb ramps, pedestrian crossings, and walk signals aligns with patterns of redlining that have concentrated poverty and minority populations in under‑served districts. Residents’ testimonies highlighted everyday barriers—dangerous crossings, inaccessible sidewalks, and limited mobility—that compound socioeconomic challenges. By marrying AI‑derived visual evidence with qualitative insights, the study offers a holistic picture that can inform targeted interventions, such as retrofitting streetscapes to meet universal‑design standards and reallocating resources to the most affected blocks.

For policymakers and planners, the study provides a replicable blueprint for equity‑centered urban planning. The AI pipeline can be adapted to other cities, enabling rapid, city‑wide assessments of infrastructure gaps without extensive on‑ground labor. Coupled with community engagement, this approach ensures that data-driven strategies remain grounded in local experience, fostering trust and more effective implementation. As municipalities grapple with climate resilience, public health, and social justice, such integrated methodologies become essential tools for building inclusive, livable urban environments.