Database could aid circular economy push in textiles

A database that includes 'fingerprints' of different types of textiles could be used by recycling centres to help sort and repurpose fabrics that would otherwise end up in landfill.

The Near-Infrared Spectra of Origin-defined and Real-world Textiles (NIR-SORT) platform – developed by scientists at the National Institute of Standards and Technology (NIST) in the US – is designed to keep end-of-life textiles in the economy and reduce waste.

According to the Environmental Protection Agency (EPA), in 2018 around 85% of used clothes and textiles end up in landfills and incinerators, wasting resources and polluting the environment.

According to the NIST, one reason is that recycling can be more expensive than landfilling, so companies have little incentive to recycle, while the sheer volume of textile waste has been exacerbated by the rise of 'fast fashion' brands like Zara, H&M, Forever 21, Uniqlo, Shein, Mango, and ASOS.

Amanda Forster, a NIST materials research engineer, noted that the NIR-SORT reference data – which is free and available to download at the NIST Public Data Repository – "will help improve sorting algorithms and unlock the potential for high-throughput sorting, which requires less manual labour."

She added that that should reduce costs and increase efficiency, making textile recycling more economically viable. The database currently features NIR fingerprints for 64 different fabric types including: cotton and polyester; blended fibre types, such as spandex blends; and real-world fabrics taken from thrift stores, and NIST has developed an AI algorithm to help differentiate between them.

Manufacturers of NIR scanner systems can use this database to train and test their own sorting algorithms and improve the performance of their products.

"The difficulty comes in when fibres are similar, like cotton or hemp. That means that the near-infrared signal is similar. The same is true with a cotton and polyester blend. Is this a new fibre or a blend of two or more fibres?" said NIST research chemist Katarina Goodge, who led the development of the database. "AI can help make the decision-making process more accurate."

The project is part of IST's Circular Economy Programme, which develops measurement science and methods to support an economy where materials are designed to retain their value through repeated reuse, repair and recycling, with disposal as a last resort.

The technology could also help to facilitate the EU's plans to introduce a digital product passport (DPP) for the textile and clothing category by 2030.

The goal of the DPP is to encourage sustainable production, enable the transition to a circular economy, and help consumers make more sustainable choices. Meanwhile, there is an existing obligation for EU member states to have started collecting textiles separately for recycling schemes by January 1 this year.

Image credit: A. Boss/NIST