A new artificial intelligence (AI) system capable of automatically identifying contaminated construction and demolition wood waste has been developed by researchers from Monash University and Charles Darwin University (CDU), marking a breakthrough for sustainable construction and recycling efforts.
Published in the journal Resources, Conservation & Recycling, the study introduces the first real-world image dataset of contaminated wood waste — a crucial step toward smarter recycling and the circular economy.
The research team, led by Madini De Alwis with Dr Milad Bazli (CDU) and supervised by Associate Professor Mehrdad Arashpour, Head of Construction Engineering at Monash, trained and tested advanced deep learning models to detect six types of contamination in wood waste using standard RGB images.
Contaminated wood from construction and demolition sites is a significant global waste challenge. Manual sorting is difficult and costly, leading much of this material to end up in landfills.
The new AI system, which demonstrated 91 per cent accuracy, offers a scalable solution by enabling automated, high-precision sorting via camera-enabled sorting lines, drones, or handheld devices.
“We curated the first real-world image dataset of contaminated construction and demolition wood waste,” said Madini, a PhD candidate at Monash’s Department of Civil and Environmental Engineering.
“This new system could be deployed via camera-enabled sorting lines, drones or handheld tools to support on-site decision-making.”
While computer vision has been applied in general waste streams, its use for contaminated wood waste has been limited — until now.
“By fine-tuning state-of-the-art deep learning models, including CNNs and Transformers, we showed that these tools can automatically recognise contamination types in wood using everyday RGB images,” Dr Bazli said.
Wood is one of the largest components of construction waste globally, but contamination from paint, chemicals, metals, and residues makes recycling difficult.
“This opens the door to scalable, AI-driven solutions that support wood waste reuse, recycling and reclamation,” Dr Bazli added.
By integrating AI with waste management practices, the study supports Australia’s circular economy goals and the global push for greener construction.
“This is a practical, scalable solution for a global waste problem,” Madini said.
By enabling automated sorting, we’re giving recyclers and contractors a powerful tool to recover valuable resources and reduce landfill dependency.”
