Machine Learning-enabled Screening LCA method and Tool (M-SLCA) - A Chatbot Solution for Sustainable Manufacturing

University Of Notre Dame, Notre Dame IN

Investigators

Abstract

Many small- and medium-sized companies that manufacture construction materials face growing pressure to improve environmental performance and meet new sustainability requirements. However, they often lack the technical capacity or financial resources to do so. This research addresses a critical need by developing a low-cost, easy-to-use method for estimating the environmental impacts of building materials. By combining artificial intelligence with life cycle science, the project will enable manufacturers to evaluate and improve their production practices without relying on expensive consultants or specialized software. The screening tool developed through this research will support participation in emerging procurement policies that favor environmentally responsible products. In addition to its industrial applications, the research will contribute to workforce development and education by offering open-access instructional materials and research opportunities. The broader significance lies in making environmental performance assessment more accessible and affordable, thus supporting improved practices across the manufacturing sector. This research advances the science of environmental assessment in the construction industry by addressing major limitations in data quality, modeling methods, and practical usability. Life cycle assessment is a widely used method for evaluating the environmental effects of materials and products over their full lifespan, but existing tools often rely on incomplete data and require expert knowledge to operate. This research will develop a new screening method that integrates machine learning with public data sources to automate environmental impact analysis for building products. A pilot study with a wood product manufacturer will demonstrate and refine the method. A key outcome will be the creation of an interactive interface that enables users to enter product information and receive real-time environmental assessments. The research will also expand public life cycle inventory databases and demonstrate a scalable optimization framework for manufacturing assessment. Through partnerships with policy and industry groups, the work will contribute to evidence-based decision-making and broader adoption of sustainability practices in construction material production. 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.