AI detects contaminated wood waste with 91 percent accuracy

A new artificial intelligence (AI) system that can automatically identify contaminated construction and demolition wood waste has been developed by researchers from Monash University and Charles Darwin University (CDU).

Published in Resources, Conservation & Recycling, researchers say the study presents the first real-world image dataset of contaminated wood waste—a major step toward smarter recycling and sustainable construction.

The research team, led by Madini De Alwis and Milad Bazli of CDU, under the supervision of Associate Professor Mehrdad Arashpour, head of construction engineering at Monash, trained and tested deep learning models to detect contamination in wood waste using images.

Contaminated wood from construction and demolition sites often ends up in landfill due to the difficulty of sorting it manually. But by applying AI models the team found strong precision and recall across six types of wood contamination.

“We curated the first real-world image dataset of contaminated construction and demolition wood waste,” says 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 explored in general waste streams, its application to contaminated wood waste has remained limited, until now.

“By fine-tuning state-of-the-art deep learning models, including CNNs [convolutional neural networks] and transformers, we showed that these tools can automatically recognize contamination types in wood using everyday RGB [red, green, blue] images,” Bazli says.

Wood waste is one of the largest components of construction waste globally, according to researchers. Most of it can be recycled, but contamination from paint, chemicals, metals and other construction residues makes sorting difficult and costly. 

“This opens the door to scalable, AI-driven solutions that support wood waste reuse, recycling and reclamation,” Bazli says.

Madini adds, “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.”