Intelligent leaching rare earth elements from waste fluorescent lamps

Area of Science:

• Materials Science
• Environmental Science
• Chemical Engineering

Background:

• Rare earth elements (REEs) are critical strategic resources facing overexploitation and environmental concerns.
• Recycling REEs from secondary sources like waste fluorescent lamps (WFLs) offers a sustainable solution.
• Traditional pyrometallurgy and acid leaching methods require extensive optimization, increasing costs and risks.

Purpose of the Study:

• To develop machine learning (ML) models for optimizing the leaching of six REEs (Tb, Y, Eu, La, Gd) from WFLs.
• To reduce the cost and environmental impact associated with REE recovery.
• To provide a rapid method for determining optimal leaching parameters.

Main Methods:

• Application of machine learning (ML) to predict REE leaching efficiency.
• Utilizing particle size and waste feed composition as primary input features.
• Feature importance analysis to identify key factors influencing REE leaching.

Main Results:

• ML models accurately predicted REE leaching based on particle size and elemental composition (Mg, Al, Fe, Sr, Ca, Ba, Sb).
• Feature importance analysis revealed significant impacts of particle size and specific elements on REE leaching.
• Influence rules of these factors on different REEs were elucidated.

Conclusions:

• ML models enable rapid determination of optimal parameters for REE recycling from WFLs.
• This intelligent approach significantly lowers recovery costs and minimizes environmental risks.
• The study establishes a pathway for the smart recycling of strategic REEs from waste materials.