
Machine Learning Insights for Better Waste Diversion
Stanford uses machine learning to translate routine waste-handling photos into information campus teams can act on.
Amidst the busy day-to-day work in the facilities operations department, staff member Shalini Singh showcased her passion for sustainability by spearheading a new study around embodied carbon in construction materials over the past year.
She and the team narrowed the top common materials for construction projects and created a new embodied carbon and design guidelines report. The report was shared in a final presentation meeting this spring to bring partners and stakeholders along on the journey, with the goal of incorporating these new guidelines into capital improvement projects. Another goal was to connect this embodied carbon study to the broader university goal of achieving net zero emissions by 2050, an integral part of Stanford’s Climate Action Plan.
Shalini and the team displayed remarkable leadership in moving the university’s operations key toward sustainability goals. When asked what prompted Shalini to lead this study, she remarked, “I feel like every role has a sustainability angle to it. I’m just a change agent and helping my peers to see they are also agents of change. Everybody has a role to play.”

Stanford uses machine learning to translate routine waste-handling photos into information campus teams can act on.

Info about the wide range of goods and services is spread across a number of sources, and machine learning helps Stanford make sense of this data.

Stanford is testing whether machine learning can close the gap on making lower-carbon design decisions during initial planning stages.