H178-02
Incorporating Urban Form Dynamics into Water Demand Management
Abstract:
In this study, we explore the interlinks between urban form, water use behavior and drought-related conservation patterns through a clustering approach. Rather than conventional approaches to studying water use behavior that only rely on sociodemographic data, we coupled social and built environment features to generate neighborhood typologies and community clusters via a sequence of unsupervised learning methods. In particular, we unfold dynamic feedback loops by leveraging emerging high-resolution built environment data from real estate data aggregator platform, Zillow. The study period covered the recent historic drought in California between 2012-2016, with distinct policy regimes that provide insights into conservation and water use rebound across diverse populations and developments. The results demonstrated that new compact and water efficient urban forms can decouple conventional income and water use links. We found that accounting for the built environment features in the clustering process led to significant improvements in cluster water use and conservation cohesion. These analyses demonstrate the importance of smart development across rapidly urbanizing areas in water-scarce regions across the globe. The results also help utilities make informed decisions about demand management strategies and tailor solutions and programs according to the broader set of factors.