Niu Bo, E Shanshan, Wang Xiaomin, Xu Zhenming, Qin Yufei
Key Laboratory of Farmland Ecological Environment of Hebei Province, College of Resources and Environmental Science, Hebei Agricultural University, Hebei, Baoding 071000, People's Republic of China.
College of Mechanical and Electrical Engineering, Hebei Agricultural University, Hebei, Baoding 07100, People's Republic of China.
Proc Natl Acad Sci U S A. 2024 Jan 2;121(1):e2308502120. doi: 10.1073/pnas.2308502120. Epub 2023 Dec 26.
Rare earth elements (REEs), one of the global key strategic resources, are widely applied in electronic information and national defense, etc. The sharply increasing demand for REEs leads to their overexploitation and environmental pollution. Recycling REEs from their second resources such as waste fluorescent lamps (WFLs) is a win-win strategy for REEs resource utilization and environmental production. Pyrometallurgy pretreatment combined with acid leaching is proven as an efficient approach to recycling REEs from WFLs. Unfortunately, due to the uncontrollable components of wastes, many trials were required to obtain the optimal parameters, leading to a high cost of recovery and new environmental risks. This study applied machine learning (ML) to build models for assisting the leaching of six REEs (Tb, Y, Eu, La, and Gd) from WFLs, only needing the measurement of particle size and composition of the waste feed. The feature importance analysis of 40 input features demonstrated that the particle size, Mg, Al, Fe, Sr, Ca, Ba, and Sb content in the waste feed, the pyrometallurgical and leaching parameters have important effects on REEs leaching. Furthermore, their influence rules on different REEs leaching were revealed. Finally, some verification experiments were also conducted to demonstrate the reliability and practicality of the model. This study can quickly get the optimal parameters and leaching efficiency for REEs without extensive optimization experiments, which significantly reduces the recovery cost and environmental risks. Our work carves a path for the intelligent recycling of strategic REEs from waste.
稀土元素（REEs）是全球关键战略资源之一，广泛应用于电子信息、国防等领域。对稀土元素需求的急剧增长导致了其过度开采和环境污染。从废荧光灯（WFLs）等二次资源中回收稀土元素是实现稀土资源利用和环境保护双赢的策略。火法冶金预处理结合酸浸被证明是从废荧光灯中回收稀土元素的有效方法。不幸的是，由于废物成分难以控制，需要进行大量试验才能获得最佳参数，导致回收成本高昂且产生新的环境风险。本研究应用机器学习（ML）建立模型，以辅助从废荧光灯中浸出六种稀土元素（Tb、Y、Eu、La和Gd），仅需测量废进料的粒度和成分。对40个输入特征的特征重要性分析表明，废进料中的粒度、Mg、Al、Fe、Sr、Ca、Ba和Sb含量、火法冶金和浸出参数对稀土元素浸出有重要影响。此外，还揭示了它们对不同稀土元素浸出的影响规律。最后，还进行了一些验证实验，以证明模型的可靠性和实用性。本研究无需进行大量优化实验就能快速获得稀土元素的最佳参数和浸出效率，显著降低了回收成本和环境风险。我们的工作为从废物中智能回收战略性稀土元素开辟了一条道路。
