School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
Shandong Provincial Key Laboratory of Water Pollution Control and Resource Reuse, School of Environmental Science and Engineering, Shandong University, Qingdao, Shandong 266237, China.
Environ Sci Technol. 2023 Nov 21;57(46):17831-17840. doi: 10.1021/acs.est.2c05404. Epub 2023 Feb 15.
Ultrafiltration (UF) as one of the mainstream membrane-based technologies has been widely used in water and wastewater treatment. Increasing demand for clean and safe water requires the rational design of UF membranes with antifouling potential, while maintaining high water permeability and removal efficiency. This work employed a machine learning (ML) method to establish and understand the correlation of five membrane performance indices as well as three major performance-determining membrane properties with membrane fabrication conditions. The loading of additives, specifically nanomaterials (_wt %), at loading amounts of >1.0 wt % was found to be the most significant feature affecting all of the membrane performance indices. The polymer content (_wt %), molecular weight of the pore maker (_Da), and pore maker content (_wt %) also made considerable contributions to predicting membrane performance. Notably, _Da was more important than _wt % for predicting membrane performance. The feature analysis of ML models in terms of membrane properties (i.e., mean pore size, overall porosity, and contact angle) provided an unequivocal explanation of the effects of fabrication conditions on membrane performance. Our approach can provide practical aid in guiding the design of fit-for-purpose separation membranes through data-driven virtual experiments.
超滤（UF）作为主流的膜基技术之一，已广泛应用于水和废水处理。对清洁安全水的需求不断增加，要求合理设计具有抗污染潜力的 UF 膜，同时保持高水渗透性和去除效率。本工作采用机器学习（ML）方法，建立并理解了 5 个膜性能指标以及 3 个主要的决定膜性能的膜特性与膜制备条件之间的相关性。发现添加剂（特别是纳米材料）的负载量（_wt %）在负载量大于 1.0wt%时是影响所有膜性能指标的最显著特征。聚合物含量（_wt %）、成孔剂分子量（_Da）和成孔剂含量（_wt %）对预测膜性能也有相当大的贡献。值得注意的是，对于预测膜性能而言，_Da 比 _wt %更为重要。从膜性能（即平均孔径、总孔隙率和接触角）方面对 ML 模型的特征分析，明确解释了制备条件对膜性能的影响。我们的方法可以通过数据驱动的虚拟实验为有针对性的分离膜设计提供实际帮助。
