arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.09084cond-mat.mtrl-sci
收藏

无视力场的Zeolitic Imidazolate Frameworks多形相分类

Systematic Study of Machine Learning Classification Algorithms of Zeolitic Imidazolate Framework Polymorphs

Sorbonne Université(索邦大学);Chimie ParisTech, PSL University(巴黎化学学院,巴黎文理研究大学)

Emilio Méndez, Léna Triestram, Dune André, François-Xavier Coudert, Rocio Semino

AI总结:

本文通过神经网络分类器对ZIFs多形相进行实时分类,利用不同维度和力场的特征描述符提升分类准确性,并揭示ZIF-4-cp到ZIF-4-cp-II相变的机理细节。

摘要:

Zeolitic Imidazolate Frameworks (ZIFs) 是一类金属-有机框架材料,其金属中心通过咪唑类配体四面体连接,并采用类似沸石的拓扑结构。由锌离子和咪唑类连接体形成的ZIFs表现出显著的多形性,可通过改变合成参数或热力学条件(如温度和压力)来调节。计算机模拟为研究这些材料及其相变提供了独特途径,从微观角度揭示其分子机制。然而,研究这些机制需要能够自动且无偏见地对每个分子实体的相进行分类,这在两种结构非常相似的相之间尤为具有挑战性。本文系统研究了神经网络分类器,用于在分子动力学模拟过程中实时分类ZIFs的相。我们测试了多种输入特征,这些特征在维度和性质上各不相同,并且在构建训练/测试数据库时使用了不同种类的力场。我们发现即使使用低维描述符,分类也高度准确,而使用高维描述符则进一步提高了性能。通过使用不同力场的配置训练分类器,可以消除力场偏差并增强分类器的性能和通用性。最后,我们应用这些分类器揭示了ZIF-4-cp→ZIF-4-cp-II相变的机理细节。

英文摘要:

Zeolitic Imidazolate Frameworks (ZIFs) are a family of metal--organic frameworks that feature metal centers tetrahedrally linked to imidazole-based ligands and adopt zeolite-like topologies. ZIFs formed by Zinc cations and imidazolate linkers exhibit a remarkable degree of polymorphism, which can be modulated by varying synthesis parameters or thermodynamic conditions (i.e., temperature and pressure). Computer simulations provide a unique way of studying these materials and their phase transitions from the microscopic standpoint, revealing their underlying molecular mechanisms. However, studying these mechanisms requires to be able to classify the phase of each molecular entity in an agnostic and automatic fashion, which is particularly challenging when the two phases involved are structurally very similar. In this work, we systematically study neural network classifiers to classify ZIF phases on-the-fly during molecular dynamics simulations. We test a variety of input features, differing both in the dimensionality and nature of the descriptors and in the kind of force field used for building the training/testing database. We reveal that even with low-dimensional descriptors the classification is highly accurate, while the use of high-dimensional descriptors leads to an even better performance. Training the classifier with configurations coming from different force fields we can remove force field bias and enhance the classifier performance and general applicability. Finally, we apply our classifiers to reveal mechanistic details of the ZIF-4-cp $\xrightarrow{}$ ZIF-4-cp-II phase transition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑