From Hubs to Deserts: Urban Cultural Accessibility Patterns with Explainable AI

The recent publication on arXiv introduces a novel framework for assessing cultural accessibility in urban environments, emphasizing the uneven distribution of cultural infrastructures such as libraries, museums, and theaters. The study employs the Cultural Infrastructure Accessibility Score (CIAS), which utilizes exponential distance decay to quantify access disparities. Findings indicate a pronounced core-periphery gradient, where cultural resources are predominantly located near urban cores, while libraries are more accessible in denser, lower-income areas. This research is significant as it not only sheds light on the existing inequalities in cultural access but also utilizes explainable AI techniques, such as SHapley Additive exPlanation (SHAP), to elucidate the relationships between accessibility, income, and racial/ethnic composition. By highlighting these disparities, the study provides valuable insights for policymakers aiming to enhance cultural equity, thereby supporting civ…