Amazon is tackling packaging sustainability at scale with several artificial intelligence (AI) technologies. In a corporate blog post, Amazon described how it is using machine learning (ML) approaches and a combination of natural language processing and computer vision to determine how to use the right amount of packaging for the hundreds of millions of products it ships. According to Amazon, these tools have helped it reduce per-shipment packaging weight by 36% and eliminating more than a million tons of packaging, equivalent to more than 2 billion shipping boxes, over the past six years. To make a prediction about whether a given product could be safely shipped in a particular package type, Amazon built an ML model based largely on text-based data from online product listings such as item name, description, price, and package dimensions.
The first HolyGrail 2.0 sorting prototype was successfully validated in March this year following semi-industrial trials, using NIR and digital watermarks detection to sort packaging waste with a 99 percent detection rate and the potential to develop new, more granular post-consumer recycling streams.
The Digital Watermarks Initiative HolyGrail 2.0, driven by AIM – European Brands Association, and powered by the Alliance to End Plastic Waste, has the goal of assessing whether the digital watermarks technology can enable better sorting and higher-quality recycling rates for packaging in the EU. Today, more than 160 partners across the value chain are working together to refine and commercialize this concept. Sonoco, one of the largest global sustainable packaging companies, is a member of the HolyGrail 2.0 initiative to prove the viability of digital watermarking for sorting packaging waste and the business case at scale, likely with global implications.
Trials in Copenhagen found that using digital watermarks on packaging resulted in 98 – 100 percent being correctly detected, with a subsequent total ejection rate of 90 – 100 percent. During the live trial in a mix of five different packaging types of various brands, 96 percent of Sonoco’s rigid paper containers were correctly detected and ejected. This demonstrates an additional approach to sort Sonoco’s EnviroCan™ rigid paper containers into the paper recycling stream.
“At Sonoco, we recognize the critical importance of developing sustainable packaging solutions that will protect and preserve our planet for future generations,” said Jeff Schuetz, Staff Vice President, Consumer Technology. “We are proud to be a member of the HolyGrail 2.0 initiative and are pleased with this successful trial to further our sustainable packaging portfolio. We are committed to advancing sortation and recycling of packaging of all types.”
Imperceptible postage stamp sized, digital watermarks on packaging aim to make it possible to effectively sort the material into specific waste streams. Conventional sorting technologies are not able to reliably identify multi-material packaging, so they can end up in the wrong recycling streams or drop to the refuse stream all together. With this new digital watermarking technology, it becomes possible to separate materials more accurately into distinct streams, even in cases of multi-material packaging. It is even possible to distinguish between packaging coming from food and non-food applications, which becomes increasingly important for the use of recycled material in new packaging. With the trials in Copenhagen, Sonoco can show high compatibility of its rigid paper containers using this technology across all sizes and material specifications.