Advanced Approach towards Zero Waste: Modeling of Copper Recovery from e-Waste by Using Machine Learning Technique

Abstract

Abstract E-waste contains significant proportions of hazardous materials, metals, and polymers, including toxic chemicals, which pose an enormous threat to contaminating the environment. This study promotes the concept of zero waste by recycling valuable metals from a scrap of e-waste. The recovery of precious metals like copper from e-waste is a challenging task, considering the selection of a suitable methodology and further optimizing the adopted methods. The recovery of precious metals and waste management through recycling hazardous waste can reduce the harmful impact of these chemicals on the environment. This study reveals an efficient methodology for the recovery of copper and further developed a model using the popular Machine Learning Technique. A model was developed using Machine Learning Techniques, Artificial Neural Networks (ANN), and Boosting Algorithm (BA). Boosting Algorithm preferred over ANN due to better results and high accuracy for predictability. Four variables (H2SO4, H2O2, Solid/Liquid ratio, and Reaction Time) were utilized in developing this model. The developed model results and findings will be valuable to copper recovery, e-waste management, and hazardous waste management. In addition, the proposed model can facilitate efficient automation of the copper recovery process at the industrial level.