首页|University of Science and Technology of China Reports Findings in Machine Learni ng (Predicting the performance of lithium adsorption and recovery from unconvent ional water sources with machine learning)
University of Science and Technology of China Reports Findings in Machine Learni ng (Predicting the performance of lithium adsorption and recovery from unconvent ional water sources with machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news originating from Hefei, People’s Republ ic of China, by NewsRx correspondents, research stated, “Selective lithium (Li) recovery from unconventional water sources (UWS) (e.g., shale gas waters, geothe rmal brines, and rejected seawater desalination brines) using inorganic lithium- ion sieve (LIS) materials can address Li supply shortages and distribution issue s. However, the development of high-performance LIS materials and the optimizati on of recovery-related operating parameters are hampered by the variety of produ ction methods, intricate procedures, and experimental expenses.” Our news journalists obtained a quote from the research from the University of S cience and Technology of China, “Machine learning (ML) techniques offer potentia l solutions for enhancing LIS material development. We collected literature data on Li adsorption, categorizing 16 parameters into adsorbent parameters, operati ng parameters, and solution components. Three tree-based algorithms-Random Fores t (RF), Gradient Boosting Decision Trees (GBDT), and Extreme Gradient Boosting ( XGBoost)-were used to evaluate the impact of these parameters on lithium adsorpt ion. The grouped random splitting method limited data leakage and mitigated over fitting. XGBoost demonstrated the best performance, with an R² of 0.98 and a roo t-mean-squared error (RMSE) of 1.72. The SHAP values highlighted that operating parameters were the most influential, followed by adsorbent parameters and coexi sting ion concentrations. Therefore, focusing on optimizing operating parameters or making targeted improvements on LIS based on operating conditions will enhan ce LIS performances in UWS.”
HefeiPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
