Department of Civil and Environmental Engineering, Princeton University, Princeton, New Jersey 08544, United States.
Andlinger Center for Energy and the Environment, Princeton University, Princeton, New Jersey 08544, United States.
Environ Sci Technol. 2024 Jun 11;58(23):10128-10139. doi: 10.1021/acs.est.4c00060. Epub 2024 May 14.
Pervaporation (PV) is an effective membrane separation process for organic dehydration, recovery, and upgrading. However, it is crucial to improve membrane materials beyond the current permeability-selectivity trade-off. In this research, we introduce machine learning (ML) models to identify high-potential polymers, greatly improving the efficiency and reducing cost compared to conventional trial-and-error approach. We utilized the largest PV data set to date and incorporated polymer fingerprints and features, including membrane structure, operating conditions, and solute properties. Dimensionality reduction, missing data treatment, seed randomness, and data leakage management were employed to ensure model robustness. The optimized LightGBM models achieved RMSE of 0.447 and 0.360 for separation factor and total flux, respectively (logarithmic scale). Screening approximately 1 million hypothetical polymers with ML models resulted in identifying polymers with a predicted permeation separation index >30 and synthetic accessibility score <3.7 for acetic acid extraction. This study demonstrates the promise of ML to accelerate tailored membrane designs.
渗透汽化（PV）是一种有效的膜分离过程，可用于有机脱水、回收和升级。然而，突破当前渗透性-选择性权衡的限制，改进膜材料至关重要。在这项研究中，我们引入机器学习（ML）模型来识别高潜力聚合物，与传统的试错法相比，大大提高了效率并降低了成本。我们利用了迄今为止最大的 PV 数据集，并结合了聚合物指纹和特性，包括膜结构、操作条件和溶质性质。我们采用了降维、缺失数据处理、种子随机性和数据泄露管理，以确保模型的稳健性。经过优化的 LightGBM 模型在分离因子和总通量方面的 RMSE 分别达到了 0.447 和 0.360（对数尺度）。使用 ML 模型对大约 100 万种假设聚合物进行筛选，结果确定了具有预测渗透分离指数>30 和合成可及性评分<3.7 的聚合物，可用于醋酸提取。这项研究表明，机器学习有希望加速定制膜设计。
