Australian researchers develop system to detect contaminated construction wood with 91 pct accuracy

SYDNEY -- Australian researchers have unveiled an artificial intelligence (AI) system capable of automatically detecting contaminated construction and demolition wood waste with 91 percent accuracy.

The research introduces the first real-world image dataset dedicated to contaminated construction wood, marking a significant advance in sustainable building practices and smarter recycling, said Melbourne-based Monash University in a news release published by Medianet on Tuesday.

The new technology, jointly developed by teams at Monash University and Charles Darwin University in Australia's Northern Territory, leverages state-of-the-art deep learning models to identify six types of contamination in wood waste using standard color images, the release said.

Contaminated wood waste, often tainted by paint, chemicals, metals, and other residues, typically ends up in landfills due to the challenges of manual sorting, it said.

The AI system promises to transform this process by enabling automated, high-precision sorting via camera-equipped sorting lines, drones, or handheld devices, significantly reducing costs and landfill dependency, according to the study published in Resources, Conservation & Recycling.

"This is a practical, scalable solution for a global waste problem. By enabling automated sorting, we're giving recyclers and contractors a powerful tool to recover valuable resources and reduce landfill dependency," said Madini De Alwis, lead researcher at Monash.

The innovation advances Australia's circular economy goals and sets a global example for using AI in sustainable construction and waste management, the study said.