City of South Bend, IN
BUILT2AFFORD
Organization: University of Notre Dame
Primary Investigator: Ming Hu
Research Track: Resource and Service Equity
NSF Abstract
The United States faces a severe shortage of affordable housing, particularly for communities with extremely low incomes. This crisis is compounded by the outdated infrastructure of existing housing, which results in high energy costs and inadequate living conditions. This project, BUILT2AFFORD, aims to address this dual challenge by leveraging advanced technology and strong community partnerships to enhance the energy efficiency of affordable housing. By focusing on low-cost passive design strategies, such as improved ventilation and shading, this project seeks to reduce the energy burden on low-income households and improve their living conditions. This project is significant because it tackles the pressing need for affordable, energy-efficient housing in the Midwest, particularly in South Bend, Indiana. By developing a framework to pre-identify housing units suitable for retrofits, our research will enable more targeted and effective interventions. The broader impact of this work includes reducing energy costs for low-income families, mitigating heat-related health risks, and contributing to the sustainability goals of local communities. The successful implementation of this project could serve as a model for other regions, demonstrating how affordable housing can be preserved and improved through innovative, data-driven approaches.
The BUILT2AFFORD project aims to enhance the energy efficiency of affordable housing by developing, testing, and validating a tool that uses machine learning algorithms and Google Street View images. This tool will automate the identification of housing units suitable for low-cost passive retrofits. In Stage 1, we will collaborate with the City of South Bend and Near Northwest Neighborhood to conduct audits of 10-20 houses to create archetype layouts for thermal comfort simulations. We will develop computer vision algorithms to extract passive design indicators from Street View images, combining this with property data to build the BUILT2AFFORD model. In Stage 2, the model will be validated by retrofitting two testbed buildings with passive design strategies. Sensors will monitor energy usage and indoor environmental conditions over eight months. The data will refine and calibrate the model for accuracy and reliability. The project will produce the BUILT2AFFORD tool, a dashboard pre-identifying affordable housing units for retrofits. It will visualize data on design indicators, energy efficiency, and health risks, aiding homeowners, policymakers, and public health officials. This project supports energy efficiency, improved home comfort, and equitable health outcomes, contributing to broader climate resilience efforts.
This project is in response to the Civic Innovation Challenge program?s Track A. Climate and Environmental Instability - Building Resilient Communities through Co-Design, Adaption, and Mitigation and is a collaboration between NSF, the Department of Homeland Security, and the Department of Energy.
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.