A recent study from North Carolina State University demonstrates how hyperspectral imaging can be used to improve the identification and sorting of materials in municipal solid waste. This technology captures light across a much wider range of wavelengths than the human eye or standard cameras, allowing researchers to identify different materials with high precision.
Lokendra Pal, E.J. Woody Rice Professor and University Faculty Scholar in the Department of Forest Biomaterials at NC State and co-author of the study, said, “Hyperspectral imaging is a powerful tool that allows us to see what human eyes or standard cameras can’t. With this technology, we can capture real-time images of large quantities of waste, down to the pixel level of data. By doing that, we can identify different materials based on variations in light reflection that we could not normally see.”
Pal also noted that this method enables scientists to determine not only what material is present but also its quantity and whether it has been contaminated. This information supports more efficient recycling operations.
While humans perceive color through red, green, and blue wavelengths between 400-700 nanometers, hyperspectral imaging collects data up to 2,500 nanometers—covering near-infrared and shortwave infrared ranges. The vast amount of data generated can be analyzed using machine learning to sort waste for recycling or energy production.
Mariangeles Salas, lead author and Ph.D. student in NC State’s Department of Forest Biomaterials, provided an example: “For example, coffee cups are made from plastic and paper. Millions of these cups are thrown away each year with less than 1% recycled.”
She explained how their process works: “With hyperspectral imaging, we create what is known as a data cube. This is a visual representation which describes a pixel’s unique light reflection characteristics in three dimensions. This allows us to identify subtle differences between materials, such as two types of paper in the same coffee cup. Both contain cellulose, but their chemistry and composition differ, meaning they are better suited for different recycling pathways.”
The research team plans to expand their efforts by building one of the largest open-access libraries containing visual and hyperspectral images—with detailed metadata—of municipal solid-waste materials. Their database already includes over a billion spectral pixels and aims to support municipalities, recovery facilities, and researchers in improving automated recycling systems.
This work could make automated recycling faster and more accurate while reducing recyclable material lost to landfills.
The study appears in Matter under the title “Hyperspectral imaging for real-time waste materials characterization and recovery using endmember extraction and abundance detection.” Co-authors include Mariangeles Salas, Simran Singh, Raman Rao, Raghul Thiyagarajan and Lucian Lucia from NC State; Ashutosh Mittal and John Yarborough from the National Renewable Energy Laboratory; and Anand Singh from IBM.
Funding was provided by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) through its Bioenergy Technologies Office (BETO) award number DE-EE0009669.
