HUSIR s a highly interdisciplinary team. We are looking for partnerships in the disciplines of environmental science, urban planning, civil engineering, data science, and so on. The research expertise of our lab centers on watershed and water quality management. Our interested topics include climate and water quality relationships, remote sensing in water quality, green infrastructure justice issue, etc.
Identifying Socio-Environmental Watershed Typologies Based on Stormwater Pollution Using Machine Learning
This project represents the first socio-environmental-technological system (SETS) study of the generation of stormwater pollution in urban watersheds across the United States. Urban stormwater pollution poses a major and growing threat to local waterbodies, yet its study and management has consistently ignored the human activities and behaviors that release pollution. In this project, we will combine data on population (social) and urban form (technological) to model human activities, along with landscape and climate factors (environmental). These four factors interact to drive stormwater pollution, and thus underlie our SETS conceptual framework.
We will analyze the data using machine learning clustering and classification algorithms to identify typologies of urban watersheds based on the stormwater pollution they produce. Then, we will build a regression model to predict stormwater quality based on any given SETS characteristics. This analysis will be conducted first at a broad national level, using data from 10 American metropolitan areas from 1992 to 1996, followed by a detailed analysis of 3 metropolitan areas from 1992 to 2013. By identifying watershed typologies, we will expose relationships between SETS characteristics and stormwater quality.
This project was funded by the National Socio-Envdironmental Synthesis Center (SESYNC). PI is Celina Balderas Guzman
Developing an Interdisciplinary Approach to Studying Urban Stream Water Quality
we will investigate the complex, multidisciplinary drivers of impaired urban stream water quality in order to identify effective and equitable solutions for U.S. cities. We focus specifically on the interactive effects of urban form, decision-making, and policy. Urban form is the composition and spatial configuration of land uses and impervious surface components (i.e., roads, buildings, parking lots); policy refers to the rules, requirements, relationships, and incentives at multiple scales that guide urban development and planning; and decision-making captures the choices made by home- and property-owners about site-specific land use and management. Each on its own plays a role in determining stream water quality. However, the dynamic interaction of the three drivers remains inadequately understood that may present opportunities for novel interventions.
This project was funded by the School for Environment and Sustainability at University of Michigan. PI is Sara Hughes