Topology-Based Phase Identification of Bulk, Interface, and Confined Water Using an Edge-Conditioned Convolutional Graph Neural Network

Topology-Based Phase Identification of Bulk, Interface, and Confined Water Using an Edge-Conditioned Convolutional Graph Neural Network
复制标题

DOI:
10.1021/acs.jpcc.2c07423
复制
发表时间:
2022-04
期刊:
The Journal of Physical Chemistry C
影响因子:
--
通讯作者:
A. Moradzadeh;H. Oliaei;N. Aluru
A. Moradzadeh;H. Oliaei;N. Aluru
中科院分区:
其他
文献类型:
--
作者:
A. Moradzadeh;H. Oliaei;N. Aluru

文献摘要

相似文献

水在各种物理化学和生物过程中起着重要作用。理解和识别各种系统中的水相,如体水、界面水和承压水,对于改进和设计最先进的纳米设备至关重要。为了区分水相,人们开发了各种有序参数,包括键序参数、局部结构指数和四面体有序参数。这些顺序参数通常是在同质批量系统的假设下开发的,而大多数应用涉及异构和非批量系统,因此限制了它们的泛化性。我们的研究开发了一种基于图神经网络的方法来直接从数据中区分水相,并学习特征而不是预先定义它们。我们比较了使用常规顺序参数作为特征训练的基线方法,以及使用径向距离和氢键信息训练的图神经网络模型,用于具有连续和不连续相变的散装、界面和密闭系统中的水的相分类和相变。六、七、八、九、冰和液态水。对于界面和密闭系统,我们使用与散装系统类似的输入,但输出是一个二进制值,表示水是液体还是固体。gnn被训练来预测碳纳米管内部或界面在不同温度下的特定原子构型是液态还是固态。我们研究了CNT 10x10,其连续和间断熔化温度均为275.0±2.5 K。在我们研究的温度范围内,GNN的行为是单调的,表现出越来越多的类液体分子,而RF随着温度的升高表现出非单调和不一致的行为。
Water plays a significant role in various physicochemical and biological processes. Understanding and identifying water phases in various systems such as bulk, interface, and confined water is crucial in improving and engineering state-of-the-art nano-devices. Various order parameters have been developed to distinguish water phases, including bond-order parameters, local structure index, and tetrahedral order parameters. These order parameters are often developed with the assumption of homogenous bulk systems, while most applications involve heterogeneous and non-bulk systems, thus, limiting their generalizability. Our study develops a methodology based on the graph neural network to distinguish water phases directly from data and to learn features instead of predefining them. We provide comparisons between baseline methods trained using conventional order-parameters as features, and a graph neural network model trained using radial distance and hydrogen-bonding information for phase classification and phase transition of water in bulk, interface, and confined systems with continuous and discontinuous phase transitions. VI, VII, VIII, and IX Ices as well as liquid water. For interface and confined systems, we use similar input as for a bulk system, but the output is a binary value indicating whether water is liquid or solid. GNNs are trained to predict whether a particular configuration of atoms is liquid-like or solid-like inside CNTs or at interface for various temperatures. We study CNT 10x10, inside which both continuous and discontinuous melting temperature of 275.0 ± 2.5 K. The behavior of GNN is monotonic within the temperature range of our study, showing an increasing number of liquid-like molecules, while RF shows a non-monotonic and inconsistent behavior with temperature increase.