Abstract:Mapping out reaction pathways and their corresponding activation barriers is a significant aspect of molecular simulation. Given their inherent complexity and nonlinearity, even generating a initial guess of these paths remains a challenging problem. Presented in this paper is an innovative approach that utilizes neural networks to generate initial guess for these reaction pathways. The proposed method is initiated by inputting the coordinates of the initial state, followed by progressive alterations to its structure. This iterative process culminates in the generation of the approximate representation of the reaction path and the coordinates of the final state. The application of this method extends to complex reaction pathways illustrated by organic reactions. Training was executed on the Transition1x dataset, an organic reaction pathway dataset. The results revealed generation of reactions that bore substantial similarities with the corresponding test data. The method's flexibility allows for reactions to be generated either to conform to predetermined conditions or in a randomized manner.
Abstract:A universal interatomic potential applicable to arbitrary elements and structures is urgently needed in computational materials science. Graph convolution-based neural network is a promising approach by virtue of its ability to express complex relations. Thus far, it has been thought to represent a completely different approach from physics-based interatomic potentials. In this paper, we show that these two methods can be regarded as different representations of the same tight-binding electronic relaxation framework, where atom-based and overlap integral or "bond"-based Hamiltonian information are propagated in a directional fashion. Based on this unified view, we propose a new model, named the tensor embedded atom network (TeaNet), where the stacked network model is associated with the electronic total energy relaxation calculation. Furthermore, Tersoff-style angular interaction is translated into graph convolution architecture through the incorporation of Euclidean tensor values. Our model can represent and transfer spatial information. TeaNet shows great performance in both the robustness of interatomic potentials and the expressive power of neural networks. We demonstrate that arbitrary chemistry involving the first 18 elements on the periodic table (H to Ar) can be realized by our model, including C-H molecular structures, metals, amorphous SiO${}_2$, and water.