BIR Convention: Technology continues to influence processing, trading

The role of emerging technologies in steel recycling, including machine learning and artificial intelligence (AI), took center stage at the Bureau of International Recycling (BIR) Ferrous Division meeting in Bangkok in late October. The growing role of technology also was mentioned in other meetings at the event.

Ferrous Division President Shane Mellor of United Kingdom-based Mellor Metals said AI is fast becoming a critical tool for recyclers.

“AI can help us detect hazards like lithium-ion batteries before they cause damage, improve operational efficiency, raise safety standards and support circular economy strategies," he said.

Offering their perspectives on those emerging technologies were Sean Davidson of Toronto-based Davis Index and Jules AI and Raghav Mecheri of New York-based Visia.

Much of what both speakers spelled out pertained to optical and sensor-based identification and sorting techniques that increasingly include machine learning aspects sometimes labeled as AI.

Visia helps design and set up systems that combine X-ray technology with machine learning to identify materials.

“Feedstock volatility, or the unpredictability in raw materials coming into yards, is really, really hampering yard operations,” Mecheri said, adding that fires caused by batteries was a high-profile and costly culprit. “Beyond that, we also see feedstock unpredictability and dirt coming into yards. How do we know how much of a load of ferrous metal is truly iron?”

Beyond traditional manual inspection, he recommended equipment that can meet the specific needs of a sorting and recycling plant, including cameras to identify value in fines or to spot hazardous items.

As one example, X-ray technology can be used to see through loads to assess contamination or to spot lithium-ion batteries hidden within metal products. The same technology can identify the chemistry of 65 different battery types and also is being used at a battery recycling facility in Europe.

Ben László of Finland-based Kuusakoski Recycling described how that firm Kuusakoski has a sorting system equipped with two X-ray cameras.

“One is on the line and one is after it,” László said. “The one on the line is telling the ejector there is a battery, so it shoots it out to a box with sand so we can contain it instantly, making sure it doesn't blow up if is critically damaged.

“The other camera that's after the line is feeding back all the time the data on how well the ejection is working. It is self-learning.” He said the system may require manual adjustments if it misses something, in which case “a person goes and reprograms it; it’s a human-machine interaction.”

Mecheri said combining sensors with machine learning in an optimal pattern can deliver up to 97 percent accuracy in spotting batteries, meaning some training and safety protocols are still needed.

“No one can eliminate catastrophic events entirely,” he said.

Davidson also said optical scanning, robot arms and machine learning are combining to produce a “measurable commercial win” for shredding plant operators and other recyclers of mixed materials.

He also pointed to the Jules AI natural language processor (NLP) as a feature that can be of use to back office operations at recycling and trading companies, such as reviewing and proofreading bills of lading and letters of credit for discrepancies.

Jules AI as offers software for the recycled materials industry with an emphasis on international trade containing aspects of automation, risk management and market intelligence.

At an earlier BIR Non-Ferrous Division meeting in Bangkok, Stuart Kagan of the New Zealand-based Buddy online recycled materials trading platform said that sector risked being left behind by the new wave of technology.

Calling relationships between traders the sector’s “life blood and oxygen,” Kagan said such relationships and new trading technologies can be compatible.

“Relationships and technology are not mutually exclusive; they can work beautifully together,” he remarked. “It’s helping buyers and sellers find better partners—faster and with more trust,” he said of Buddy.

Kagan called nonferrous recycling a complex, cautious industry that can entail discrepancies, claims and late shipments, but said digital platforms such as Buddy deal can deal with some of those issues and can offer expanded opportunities.

At a later Paper Division meeting, Francisco Donoso of Dolaf Servicios Verdes S.L. offered a presentation on the Global Auction for Recovered Paper for Recycling (GARP), a new platform set to launch by the end of this year.

According to Donoso, GARP will host weekly 30-minute auctions for recovered paper and board and will feature what he called live pricing, anonymous identities on a trading platform designed to connect suppliers, customers and brokers from around the world.

The BIR October 2025 World Recycling Convention & Exhibition was at the Centara Grand Convention Centre at Centralworld in Bangkok from Oct. 26-28.