University uses AI to accelerate solar panel recycling

University of New England (UNE)researchers have found early promise in using AI to accelerate the recycling of solar panels.

While up to 95% of a panel’s mass can already be recovered using standard mechanical methods, the silicon wafers cannot currently be recycled. These wafers absorb photons from sunlight, releasing electrons and producing electric current.

To be able to survive at least 25 years in sunlight and weather, the wafers are bonded to their substrate using special compounds that can’t be effectively degraded in a way that allows clean separation of the silicon.

The UNE team — part of the university’s new Australian Institute for Strategic Artificial Intelligence (ISA) — is using AI and supercomputers to assess potential solvents that enable the silicon to be separated from its substrate with minimal contamination.

The researchers said the approach represents a fundamental shift in how chemical solutions are discovered. Rather than developing and testing potential compounds in a laboratory — a process that might take years without success — AI-driven quantum chemical simulations can propose potentially useful molecular formulations, evaluate their chemical efficacy, flag new pathways, and then move onto the next computation.

“Now we can use advanced quantum chemical simulations and AI models to predict how these panels can be disassembled at the molecular level,” said UNE computational chemist Dr Kasimir Gregory. “These technologies are giving an exponential boost to the process of scientific discovery.”

Another team member, Professor Amir Karton, said the discovery process is being driven through a pairing of an AI platform based at UNE, and a $2.7 million ARC-funded automated robotic laboratory shared by several institutions.

With this system, Karton said, “We can efficiently create an effective feedback loop between AI-driven predictions and experimental observations. This allows us to actively steer the experimental discovery of optimal recycling pathways at unprecedented speeds.”

The research aligns closely with NSW Government capability commitments to address renewable energy waste. It has attracted attention from the solar energy sector, which recognises that maximising material recovery is an important element in the long-term sustainability of solar power.

Renewables developer ACEN Australia is supporting the research by providing panels from its New England Solar project, near Uralla in the NSW Northern Tablelands. The company’s Managing Director David Pollington said the UNE research is an important step in further improving the effectiveness and efficiencies of recycling processes.

“We are also committed to supporting the regions in which we operate, so we’re extra excited that this industry-leading research is happening right here in the New England,” Pollington said.

For UNE, a key reason for getting panel recycling right is to support the local economies that host renewables infrastructure.

“UNE is in the heart of NSW’s largest renewable energy zone (REZ),” Karton said. “It is not practical to ship thousands of tonnes of solar waste across the country for processing. The university has a strategic focus on ensuring the renewables rollout here provides maximum benefit to the region while it benefits the nation.

“New technologies are making it possible for us to apply world-class methods to these challenges, not as some distant abstract issue, but in support of an energy revolution that is almost literally taking place in our backyards.”

Image caption: (L–R) Professor Amir Karton, Dr Kasimir Gregory and PHD student in Computational Chemistry Amber Hocks. Image: Supplied