Neural Structure Fields with Application to Crystal Structure Autoencoders
This enables more accurate inverse design of materials with desired properties, addressing a domain-specific bottleneck in materials science.
The authors tackled the problem of representing crystal structures for machine learning applications by proposing neural structure fields (NeSF), which treat crystal structures as continuous fields rather than discrete sets of atoms, and demonstrated superior performance over existing grid-based approaches with extensive quantitative results.
Representing crystal structures of materials to facilitate determining them via neural networks is crucial for enabling machine-learning applications involving crystal structure estimation. Among these applications, the inverse design of materials can contribute to explore materials with desired properties without relying on luck or serendipity. 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. We propose an autoencoder of crystal structures that can recover various crystal structures, such as those of perovskite structure materials and cuprate superconductors. Extensive quantitative results demonstrate the superior performance of the NeSF compared with the existing grid-based approach.