NSF-SNSF: Understanding Human Well-Being through Residential Location

Villanova University, Villanova PA

Investigators

Abstract

This project introduces a novel, data-driven, artificial intelligence (AI)-enhanced framework for evaluating how physical features of cities—such as land use, street network design, and connectivity—shape stress, cognition, and emotional health. As cities become more dense, and technologically complex, understanding how environments affect human well-being has emerged as a key concern. By comparing neighborhoods, the project identifies form elements that consistently support well-being. In collaboration with local stakeholders and students, as a translational aspect, the research generates actionable planning guidelines grounded in experimental data. This work advances national priorities by supporting interdisciplinary research, fostering global collaboration, and training the next generation of scientists. Ultimately, the project contributes to healthier and more resilient communities through evidence-based design. To accomplish these goals, the project proceeds in three phases. First, machine learning techniques group areas by key form characteristics (e.g., land use variation, block size, street network connectivity). These clusters serve as matched environments for comparison. Second, the project conducts controlled experiments within these clusters to assess how different forms impact human well-being. Across three experimental platforms—online surveys, immersive virtual reality simulations, and real-world walking studies—participants engage with environments while researchers collect biosignal data (e.g., heart rate, brain activity, gaze behavior) using smartwatches, eye-tracking glasses, and EEG monitors, as well as standardized well-being assessments. Third, findings are integrated with existing design frameworks and translated into the development of planning guidelines that are sensitive to both global patterns and local needs. The research also generates new educational materials, including a course, and provides interdisciplinary training at the intersection of land planning, mobility, physiological monitoring, and data science. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.