Scientists at the University of New England’s Australian Institute for Strategic Artificial Intelligence are using artificial intelligence and powerful supercomputers to assess potential solvents to separate silicon wafers with minimal contamination.
Researchers from the University of New England and the Australian Institute for Strategic Artificial Intelligence are using artificial intelligence (AI) and supercomputers to develop methods for recycling silicon wafers with minimal pollution.
Silicon, currently the most valuable component in a solar panel, cannot be recycled to its original purity due to the substrates used to prevent degradation over the life of a panel. The researchers use AI-driven quantum chemical simulations to identify molecular solvent formulations that can cleanly separate silicon from wafers. The simulations evaluate chemical efficacy, identify new pathways and guide subsequent calculations.
UNE computational chemist Kasimir Gregory said it is now possible to predict how panels might be disassembled at the molecular level. “These technologies provide an exponential boost to the process of scientific discovery,” Gregory said.
Research colleague and ISA director Amir Carton said the team has created an efficient feedback loop between AI-driven predictions and experimental observations. “This allows us to actively drive the experimental discovery of optimal recycling pathways at unprecedented speeds,” Karton said.
The project is supported by an automated robotic laboratory worth AUD 2.7 million ($1.9 million), funded by the Australian Research Council and shared by different institutions. The laboratory can physically produce the solvents and materials identified through AI-driven simulations.
It can then test them in real-world experiments powered by agentic AI: autonomous AI agents capable of independently running experiments and managing workflows with minimal human intervention. The agents work continuously, reducing development times from years to months.
The research has received support from the Philippines-based renewable energy developer ACEN Australiathat supplies panels from its 720 MW New England Solar Project in the northern tablelands of New South Wales.
Director David Pollington said the company recently went into operation Stubbo solar project is the first large-scale project to be realized Circular PV Alliance certification, adding that the UNE study is “an important step in further improving the effectiveness and efficiency of recycling processes.”
“We are also committed to supporting the regions we serve, so we are especially excited that this leading research is taking place here in New England,” said Pollington.
The cumulative volume of waste solar panels in Australia is expected to reach one million tonnes by 2035, with the tangible value of these panels expected to exceed AUD 1 billion.
“It is not practical to transport thousands of tons of solar waste across the country for processing,” Amir Carton said. “The university has a strategic focus on ensuring that the rollout of renewable energy here delivers maximum benefit to the region while benefiting the nation.”
On May 7, 2026, UNE launched the Institute for Strategic Artificial Intelligenceworking indoors LabNext70Australia’s first purpose-built AI research and delivery center focused on education.
The institute is co-led by an associate professor Aaron driverUNE’s Chief AI Officer and Director of LabNext70. It will work in various areas including materials science, education transformation, geopolitical analysis and strategic decision-making.
This content is copyrighted and may not be reused. If you would like to collaborate with us and reuse some of our content, please contact: editors@pv-magazine.com.
