GeoAI and Spatial Data Science for Sustainable Living Environments and Population Well-Being

The growing intersection of GeoAI and spatial data science is transforming how we understand the relationships between people and their surrounding environments. Advances in machine learning, earth observation, spatial modeling, and human mobility data monitoring have created new possibilities for examining urban form, natural landscapes, and the social determinants of well-being. Yet despite rapid methodological progress, key challenges persist in integrating diverse data sources, scaling analyses, and translating geospatial intelligence into actionable insights for healthy and sustainable living environments. Current studies often emphasize technical advances while overlooking social and behavioral dimensions, highlighting the need for a stronger dialogue bridging geospatial analytics, environmental sciences, and population well-being research.This Research Topic aims to advance methodological and empirical contributions at the intersection of GeoAI, spatial data science, and the study of living environments and population well-being. It encourages research that bridges innovative computational methods with meaningful societal questions and builds an evidence base for how environmental and spatial characteristics influence human health, well-being, and equity. Key objectives include fostering reproducible GeoAI and geospatial methodologies, promoting data-driven assessments of built and natural environments, and encouraging comparative and longitudinal insights into the dynamics shaping well-being outcomes across scales and contexts. To gather further insights into the intersection of GeoAI, spatial data science, and the geography of well-being, we welcome contributions addressing, but not limited to, the following themes:• Machine learning, deep learning, and foundation models characterizing built and natural environments (e.g., green/blue spaces, air quality, heat, land use, morphology, human–environment interactions)• Multi-source data fusion integrating remote sensing, street-view imagery, POI data, mobile traces, and social media for neighborhood-level assessment and well-being monitoring• Spatiotemporal modeling of environmental characteristics and their associations with population well-being across urban–rural gradients• Natural language processing and large language models for extracting geospatial or environmental information from unstructured text (e.g., news, social media, administrative sources)• Remote sensing and street-view imagery for environmental monitoring, public health surveillance, and urban intelligence• Geospatial analysis of social and environmental determinants of health, health inequalities, and well-being, such as deprivation, accessibility, and social cohesion• Life-course and longitudinal geospatial approaches to studying environmental exposures and well-being trajectories• Cross-national and comparative analyses linking living environment characteristics and human–environment interactions to disparities in well-being across socioeconomic and geographic contexts Appendix: This Research Topic welcomes original research, methodological papers, data reports, reviews, and policy-oriented perspectives. Topic editors: Yuan Meng, Chunyu Zheng, Zhuolin Pan, Zhiqiang Feng Source: https://www.frontiersin.org/research-topics/80721/geoai-and-spatial-data-science-for-sustainable-living-environments-and-population-well-being