AI and Automation in Recycling: Better Sorting, Higher Efficiency, Optimization, Improved Materials Recovery, Better Black Plastic Detection, and of Reclaiming PET Plastic Contamination

   

      Municipal Recycling Facilities (MRFs) can benefit from AI-enabled technology. AI has several applications in recycling, waste management, and materials processing and recovery. These include real-time mass balance accounting and assessing the value of missorted materials. An AI-enabled system can map, analyze, and sort different materials coming down the line.

     Vision AI systems can “see” what is going down the line for accurate materials estimates. Sensors can be put in many places on the line. These systems can be installed quickly. One is Everest Labs’ RecycleOS, which is designed for recycling plants.

     One thing that needs to be known is how much of each material comes in and goes out. This is known as mass balancing.

      The MRF Operations Forum session Emerging Technology and Approaches in October 2024 brought together recycling engineers and executives, and AI platform providers. AI Vision systems utilize AI-powered X-ray and camera equipment to analyze material coming into recycling facilities to identify nonconforming items, such as lithium batteries. One goal of the forum was to discuss what data should be collected and analyzed. Estimates indicate that recoverable materials are being missed, which, if recovered, could increase revenue. Modularity of technology and robotics is being pursued to enable plug-and-play advantages. Companies in recycling AI include Everest Labs, Glacier, and Greyparrot. Recycling is a tough business, and increasing recovery rates can be helpful. Facilities are also being oriented to aid in improving extended producer responsibility (EPR) programs. Increasing “waste intelligence” with data analysis enables materials recovery optimization and retention of undesirables.

     An article in Sorted Tech gives five ways AI is aiding MRFs: 1) Improved recycling efficiency - faster, more precise sorting, leading to higher recovery rates and improved material purity, 2) improved material type recognition – this improves recovery value, 3) Better detection of black plastic, which is hard to detect, 4) AI systems are adaptable to changes in the waste stream, markets, and regulations, and 5) AI systems are the best way to optimize processes in an MRF, including sorting.

     In an article in Resource Recycling, Inc., Everest Labs notes that AI-enabled data analytics can help MRF operators modify equipment settings to improve commodity recovery. Improved recovery of aluminum cans, known as used beverage cans, or UBCs, for instance, can increase facility revenue. One facility was able to catch $28,300 per month, or $336,000 per year, of $43,300 per month of lost UBCs, with AI-enabled robotics in a pilot, and another to catch 600,000 extra UBCs per quarter.

     Below, Everest Labs' Nellis and Pradhan give the seven steps to transforming to an AI-enabled facility through its RecycleOS system. 

     Automating MRFs also cuts down on labor costs, which can be significant for the low-profit facilities. In facilities that handle plastic, robotic arms are used to reclaim PET plastic contamination. Everest Labs’ Katherine Nellis noted:

“In a plastics recycling plant, they’re all about having a high throughput, which is how much material they’re processing, but at the same time, it’s important that they maintain a high yield on the output of the PET flakes and recycled content that then they are sending out to their customers,” Nellis said.

     MRFs will likely refine their AI-enabled technologies in the future, which hopefully will aid them in efficiency and profitability.

 

     

References:

 

Supercharging Your Recycling Facility with AI: A Practical Guide: Proven use cases & implementation  roadmap to operational excellence. Everest Labs. Waste Dive. wastemanagementdive.tradepub.com/?p=w_defa9741&w=d&email=b09ff1e64348033f5e5154e78f3b49f8&key=EDj3AfNbxXUUKDJn6jqb&ts=1597&u=1661982511161766801484&e=Ymx1ZWRyYWdvbmdlb0BnbWFpbC5jb20=&secure=1&_afn=0

5 ways AI is revolutionising MRF's operations. Sorted. February 13, 2025. 5 ways AI is revolutionising MRF's operations

How AI imaging is helping MRFs and a reclaimer. Colin Staub. Resource Recycling.  April 8, 2025. How AI imaging is helping MRFs and a reclaimer - Resource Recycling

Actionable insights with AI. DeAnne Toto. Waste Today. Published November 27, 2024 | Updated March 31, 2025. Actionable insights with AI - Waste Today