Examining the non-linear relationship between the residential environment and birth rate in Seoul, South Korea

South Korea recorded the world's lowest total fertility rate of 0.72 in 2023, highlighting an urgent socio-economic challenge with far-reaching implications such as labor shortages, population aging, and economic stagnation. While numerous studies have examined how the residential environment is related to fertility, most have relied on linear assumptions that limit real-world applicability. This study adopts a non-linear, machine-learning-based approach to investigate how residential environmental factors—measured through the “N-minute city” framework—are associated with fertility rates in Seoul. Using XGBoost, SHAP, and Geographically Weighted Regression (GWR), the study evaluates the associations between spatial proximity to key urban functions—including childcare, education, healthcare, and transportation—and birth counts, based on 5523 fine-grained 250 m × 250 m grid cells. The results reveal several threshold effects: birth counts are significantly lower when commuting times exceed 65 min. Walkable access to essential child-rearing infrastructure—such as public daycare centers within 400 m, clinics within 200 m, elementary schools within 820 m, and private academies within 200 m—is associated with higher fertility rates. In contrast, proximity to hospitals and cultural facilities is associated with lower birth counts. Socioeconomic and demographic characteristics also exhibit significant patterns, with higher incomes and age-diverse neighborhood compositions linked to increased fertility rates. By identifying non-linear thresholds and spatial dependencies in fertility-related behaviors, this study provides actionable insights for urban planning and residential policy. It suggests that policies aiming to promote childbearing should prioritize enhancing physical accessibility to essential services within walkable distances and consider both spatial equity and behavioral thresholds.