| dc.description.abstract | We are living in a time of extraordinary urban changes. Research has shown that cities can bring economic wealth and improved quality of life by fostering diverse economies, dense knowledge exchanges, and efficient district performance. However, it is also true that scientists have associated cities with crowding, segregation, environmental degradation, and other significant challenges. Sensors, Data, and Artificial Intelligence can lead to a better understanding of urban settings and their challenges by providing opportunities for insight into their social and environmental performance. Many of these sensing initiatives are carried out in a top-down fashion. Top-down sensing generates datasets that capture large-scale patterns across populations. This data could be complemented by bottom-up community-based approaches that capture more granular information emerging from the specific needs of individuals. Through a series of case studies, this thesis illustrates how to use a variety of community-scale sensor and machine intelligence implementations to measure aspects of socio-environmental cycles that emerge in different urban and environmental contexts. These studies explore possibilities for providing communities with access to localized information about socio-environmental systems that, if fully deployed, could enable bottom-up transformation of collective behavior, policies, and infrastructure to address the great challenges that future cities will face. | |
