Neural Structure Fields with Application to Crystal Structure Autoencoders

Abstract

Representing crystal structures of materials to facilitate determining them via neural networks is crucial for enabling machine-learning applications involving crystal structure estimation. Here we propose neural structure fields (NeSF) as an accurate and practical approach for representing crystal structures using neural networks. Inspired by the concepts of vector fields in physics and implicit neural representations in computer vision, the proposed NeSF considers a crystal structure as a continuous field rather than as a discrete set of atoms. Unlike existing grid-based discretized spatial representations, the NeSF overcomes the tradeoff between spatial resolution and computational complexity and can represent any crystal structure. To evaluate the NeSF, we propose an autoencoder of crystal structures. Quantitative results demonstrate the superior performance of the NeSF compared with the existing grid-based approach.