Machine Learning-Enabled Development of Lithium Adsorbents for Salt Lakes: Practice and Innovation in Digital-Intelligence Chemistry Instruction
LIU Si-Ying1, TAO Hao-Lan2, SU Hai-Ping1, LIN Yi-Ting2, LIN Sen3, LIAN Cheng1**, ZHANG Wen-Qing1, LIU Hong-Lai1
1. School of Chemistry and Molecular Engineering,East China University of Science and Technology,Shanghai 200237,China; 2. School of Chemical Engineering,East China University of Science and Technology,Shanghai 200237,China; 3. School of Resources and Environmental Engineering,East China University of Science and Technology,Shanghai 200237,China
Abstract This study deeply integrates machine learning algorithms with SHAP analysis.Using the screening of doping elements for aluminum-based lithium adsorbents as an example,it guides students through the complete machine learning workflow,fostering their ability to apply data science knowledge to solve materials design problems.A total of 59 students from East China University of Science and Technology(19 from the advanced class and 40 from the regular class) participated in the study.The advanced class demonstrated superior overall academic performance,while there was no significant difference in their mastery of foundational concepts.This simplified framework has been successfully implemented in a high school summer camp.This course design not only enhances students’ comprehension of the interdisciplinary field of chemistry and machine learning but also sparks their interests in chemical research and fosters innovative thinking,laying a solid foundation for their future development.
LIU Si-Ying, TAO Hao-Lan, SU Hai-Ping, LIN Yi-Ting, LIN Sen, LIAN Cheng, ZHANG Wen-Qing, LIU Hong-Lai. Machine Learning-Enabled Development of Lithium Adsorbents for Salt Lakes: Practice and Innovation in Digital-Intelligence Chemistry Instruction[J]. Chinese Journal of Chemical Education, 2026, 47(18): 113-120.
