A research project at Stony Brook University, supported by the university’s AI Innovation Seed Grant, is seeking to address the problem of contamination in recycling streams through artificial intelligence. The initiative aims to automate the analysis of recycling materials using video technology and machine learning, with a focus on making waste management more efficient and sustainable.
The Environmental Protection Agency estimates that while about 75% of waste generated in the United States is recyclable, only 35% is actually recycled. This gap leads to approximately 68 million tons of recyclables being sent to landfills or incinerators each year. Additionally, about 25% of recycling materials are contaminated by non-recyclable items, resulting in millions of tons being rejected from recycling facilities annually.
Researchers at Stony Brook are working on an AI-assisted system that uses sensors and machine learning algorithms to identify, track, and count waste as it moves through sorting facilities. The goal is to reduce contamination rates and improve efficiency within recycling operations.
“We’re not just building tools in isolation, we’re collecting data at multiple stages of the sorting process, engaging with recycling workers to understand the pain points, and using those insights to help them work faster, safer, and with greater insight,” said Ruwen Qin, associate professor in the Department of Civil Engineering.
The team is collaborating with municipalities and the Waste Data and Analysis Center located within Stony Brook’s Department of Technology, AI, and Society. This center receives funding from the New York State Department of Environmental Conservation (NYSDEC). High-resolution video data is being gathered from several points along local material recovery facility (MRF) sorting lines in Long Island.
“We’re not just studying the problem. We’re building tools that can make a measurable difference,” Qin said.
Further details about this project can be found on the AI Innovation Institute website in an article by Ankita Nagpal.
