Rapid urbanization poses critical challenges to environmental quality, public health, and emotional well-being. This study presents a machine learning framework integrating longterm environmental pressure, socioeconomic, and health predictors with spatial analysis to model urban emotions and prioritize mental health interventions across Inner London. PM10 concentrations (8.5%), noise pollution (7.8%), and PM2.5 levels (5.3%) were identified as dominant drivers of negative emotions, particularly in eastern boroughs with socioeconomic disparities. Positive emotions, such as joy and trust, were associated with open space accessibility (8.2%) and normalised difference vegetation index (7.2%), indicating that green infrastructure corresponds to areas where more positive emotional expressions are observed. The Mental Health Prioritization Model identified 117 high-priority hexagons in environmentally stressed areas, offering actionable insights for targeted interventions. These findings offer a framework for examining spatial patterns of environmental inequality and emotional expressions, which may support broader discussions on urban sustainability. • Machine learning reveals how urban environments shape collective emotional well-being • Remote sensing metrics serve as robust predictors for localized emotional distress • Geospatial frameworks identify high-priority zones for targeted mental health interventions • Spatial analytics bridge the gap between urban planning and community psychological welfare
Sakti et al. (Tue,) studied this question.