0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Sign in to save

Integrated Blockchain and Machine Learning Framework for Polystyrene Waste Traceability

2026
Hamza Ibrahim, Prosper Uzoma Ahakonye, Precious Nwadiuto Ahakonye, Won Jae Ryu, Love Allen Chijioke Ahakonye, Jae Min Lee, D. Kim

Summary

A blockchain-IoT-ML framework for polystyrene waste management achieved 94.8% predictive accuracy for waste forecasting and 2,847 transactions per second on a custom permissioned blockchain, enabling traceable, data-driven EPS/XPS waste energy recovery. Since expanded polystyrene is a major source of microplastic pollution, transparent digital traceability systems like this could substantially improve accountability and reduce environmental plastic leakage.

Polymers

The management of expanded and extruded polystyrene (EPS/XPS) waste presents a significant environmental challenge due to limited recyclability and the generation of microplastics. Conventional waste management systems often lack transparency, data interoperability, and operational efficiency. This study introduces a smart waste management framework that integrates Internet of Things (IoT) sensing, Machine Learning (ML), and blockchain technologies to enable traceable, data-driven energy recovery. The proposed system employs PureChain, a custom permissioned blockchain designed for the immutable recording of data from IoT-enabled smart bins equipped with fill-level, temperature, and waste-type sensors. Performance evaluation demonstrated that PureChain achieved a throughput of 2,847 transactions per second, a latency of 0.3 s, and an energy consumption of 0.02 kWh per transaction. For predictive analytics, the Long Short-Term Memory (LSTM) model achieved the highest forecasting accuracy of 94.8% with a coefficient of determination R2 = 0.947. In contrast, the XGBoost model maintained balanced accuracy of 92.8% and superior computational efficiency. The integration of PureChain and ML creates a closed-loop, intelligent system that enhances data traceability, optimizes waste-collection logistics, and enables a verifiable circular economy for EPS/XPS waste management.

Share this paper