RESUMEN
Optical properties in solids, such as refractive index and absorption, hold vast applications ranging from solar panels to sensors, photodetectors, and transparent displays. However, first-principles computation of optical properties from crystal structures is a complex task due to the high convergence criteria and computational cost. Recent progress in machine learning shows promise in predicting material properties, yet predicting optical properties from crystal structures remains challenging due to the lack of efficient atomic embeddings. Here, Graph Neural Network for Optical spectra prediction (GNNOpt) is introduced, an equivariant graph-neural-network architecture featuring universal embedding with automatic optimization. This enables high-quality optical predictions with a dataset of only 944 materials. GNNOpt predicts all optical properties based on the Kramers-Krönig relations, including absorption coefficient, complex dielectric function, complex refractive index, and reflectance. The trained model is applied to screen photovoltaic materials based on spectroscopic limited maximum efficiency and search for quantum materials based on quantum weight. First-principles calculations validate the efficacy of the GNNOpt model, demonstrating excellent agreement in predicting the optical spectra of unseen materials. The discovery of new quantum materials with high predicted quantum weight, such as SiOs, which host exotic quasiparticles with multifold nontrivial topology, demonstrates the potential of GNNOpt in predicting optical properties across a broad range of materials and applications.
RESUMEN
Understanding the structure-property relationship is crucial for designing materials with desired properties. The past few years have witnessed remarkable progress in machine-learning methods for this connection. However, substantial challenges remain, including the generalizability of models and prediction of properties with materials-dependent output dimensions. Here we present the virtual node graph neural network to address the challenges. By developing three virtual node approaches, we achieve Γ-phonon spectra and full phonon dispersion prediction from atomic coordinates. We show that, compared with the machine-learning interatomic potentials, our approach achieves orders-of-magnitude-higher efficiency with comparable to better accuracy. This allows us to generate databases for Γ-phonon containing over 146,000 materials and phonon band structures of zeolites. Our work provides an avenue for rapid and high-quality prediction of phonon band structures enabling materials design with desired phonon properties. The virtual node method also provides a generic method for machine-learning design with a high level of flexibility.
RESUMEN
Topological superconductors (TSCs) have garnered significant research and industry attention in the past two decades. By hosting Majorana bound states which can be used as qubits that are robust against local perturbations, TSCs offer a promising platform toward (nonuniversal) topological quantum computation. However, there has been a scarcity of TSC candidates, and the experimental signatures that identify a TSC are often elusive. In this Perspective, after a short review of the TSC basics and theories, we provide an overview of the TSC materials candidates, including natural compounds and synthetic material systems. We further introduce various experimental techniques to probe TSCs, focusing on how a system is identified as a TSC candidate and why a conclusive answer is often challenging to draw. We conclude by calling for new experimental signatures and stronger computational support to accelerate the search for new TSC candidates.