Skip to Content
You are currently on the new version of our website. Access the old version .
EnvironmentsEnvironments
  • Article
  • Open Access

17 February 2025

18 Pages

Advancing Waste Electrical and Electronic Equipment (WEEE) Recycling: A Random Forest Approach to Classifying WEEE Plastics for Sustainable Waste Management

,
and
1
CIRCE—Technology Centre for Energy Resources and Consumption, Parque Empresarial Dinamiza, Av. Ranillas 3D, 1st Floor, 50018 Zaragoza, Spain
2
School of Computing, Engineering & Physical Sciences, University of the West of Scotland, Paisley PA1 2BE, UK
*
Author to whom correspondence should be addressed.

Abstract

The rapid growth of waste electrical and electronic equipment (WEEE) highlights its significance as a critical waste stream, with plastics comprising 30% of its volume. These plastics often contain hazardous brominated flame retardants (BFRs), which are regulated to prevent negative environmental and public health impacts, but are predominantly managed through incineration, challenging circular economy goals. Addressing this issue requires innovation in sorting technologies and predictive methodologies to reduce reliance on incineration and enhance recycling efficiency. Despite progress, existing recycling practices are hindered by overly conservative contamination assumptions and a lack of detailed data on WEEE characteristics, leading to resource inefficiencies and missed opportunities for material recovery. This research aimed to bridge these gaps by developing a Random Forest-based predictive model to classify WEEE plastics as recyclable or non-recyclable, thereby supporting sustainable waste management. Using a dataset of over 15,000 samples analysed for polymer type, bromine concentration as an indicator of recyclability, and five additional variables, the model demonstrated 80–88% accuracy in validation tests. Polymer type appeared as the most significant predictor, followed by manufacturer and year of manufacture. Regional testing highlighted the adaptability of the model but also underscored the need for extended datasets and improved data management to simplify variable retrieval, as the model relies on hard-to-access data. The findings of this study have broad implications, including enhanced sorting efficiency, regulatory compliance, and alignment with circular economy principles. By refining classification accuracy and expanding its application, the model offers a scalable solution to advancing WEEE recycling and optimizing resource recovery, thereby promoting sustainability and reducing the environmental impact.
Keywords:
WEEE; Python; modelling

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.