by In the United States, low-income households are facing an energy burden that is three times higher than the national average, as highlighted by the U.S. Department of Energy. A staggering number of over 46 million households in the U.S. are grappling with the weight of significant energy expenses, spending more than 6% of their gross income on essentials like home cooling and heating.
Passive design elements, such as natural ventilation, hold the key to reducing energy consumption. By leveraging natural energy sources like sunlight and wind, these elements can enhance comfort levels in homes without incurring substantial costs. However, the lack of data on passive design has made it challenging to evaluate energy savings on a larger scale.
To address this gap, an interdisciplinary team of experts from the University of Notre Dame, in collaboration with faculty from the University of Maryland and University of Utah, have devised a method to employ artificial intelligence in analyzing a household’s passive design features to predict its energy expenses with over 74% accuracy.
Incorporating demographic data including poverty rates, the researchers have developed a comprehensive model to forecast energy burdens across 1,402 census tracts and nearly 300,000 households in the Chicago metropolitan area. Their research findings were recently published in the journal Building and Environment.
The insights gleaned from this study offer invaluable guidance for policymakers and urban planners in identifying the most vulnerable neighborhoods, thereby paving the way for the development of smart and sustainable cities, as stated by Ming Hu, associate dean for research, scholarship, and creative work in the School of Architecture.
Hu emphasized the critical health risks faced by families unable to afford adequate heating or cooling, a situation exacerbated by the anticipated rise in extreme temperature events due to climate change. There is an urgent need for cost-effective solutions to alleviate energy burdens and assist families in adapting to a changing climate landscape.
Through the utilization of a convolutional neural network and Google Street View imagery of residential buildings in Chicago, the research team focused on three key factors in passive design: window size, types, and shading. The outcomes demonstrated the significant association of passive design characteristics with average energy burdens, underscoring their importance in prediction models.
The researchers highlighted the scalability and efficiency of their model compared to traditional energy auditing methods, which necessitated a laborious building-by-building approach in assessments.
Moving forward, the team plans to collaborate with Notre Dame’s Center for Civic Innovation to evaluate residences in South Bend and Elkhart communities, emphasizing the potential of the model to swiftly provide information to organizations aiding local families.
The study also aims to include additional passive design elements in the analysis, such as insulation and cool roofs, with aspirations of expanding the project to address energy burden disparities nationally.
For the researchers, this project embodies Notre Dame’s commitment to sustainability and aiding communities in need, particularly in the realm of environmental justice. The integration of AI and machine learning technologies in this endeavor reflects a dedication to advancing solutions for the collective good.
*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it
