Automatized discovery of polymer membranes with AI generative design and molecular dynamics simulations

Data sets and scripts for computational discovery of polymer membranes for carbon dioxide separation. The training data set with 1,169 homo-polymers provides carbon dioxide permeability, glass transition temperature and half decomposition temperature for each listed material. The output data set contains 784 optimized homo-polymer candidates generated by Inverse Design and Machine Learning techniques. The Jupyter notebook enables the use of the Polymer Property Prediction Engine as a service for generating the properties provided in the training data set.

面向二氧化碳分离用聚合物膜计算发现的数据集与配套脚本。
本次训练数据集涵盖1169种均聚物（homo-polymer），可为每一种收录材料提供二氧化碳渗透系数、玻璃化转变温度与半分解温度三项性能参数。
输出数据集包含通过逆向设计与机器学习技术生成的784种优化均聚物候选材料。
配套的Jupyter笔记本支持调用聚合物性能预测引擎服务，用于生成训练数据集中收录的各项性能指标。