Atomic packing controls exciton lifetime: Like semiconductors, small metallic clusters can absorb light and create excitons (electron-hole pairs). In ligand-capped gold clusters of 30 to 40 atoms (Au 30 to Au 40 ) that adopt the usual face-centered cubic packing, the lifetime of these excitons is ∼100 nanoseconds. Zhou et al. found that atomic packing and molecular orbital overlap can greatly affect carrier lifetimes. Despite having similar bandgaps to those of face-centered cubic clusters, a hexagonal close-packed Au 30 cluster had a much shorter lifetime (∼1 nanosecond), and a body-centered cubic Au 38 cluster had a lifetime of ∼5 microseconds, which is comparable to bulk silicon. Science , this issue p. 279
Materials databases generated by high-throughput computational screening, typically using density functional theory (DFT), have become valuable resources for discovering new heterogeneous catalysts, though the computational cost associated with generating them presents a crucial roadblock. Hence there is a significant demand for developing descriptors or features, in lieu of DFT, to accurately predict catalytic properties, such as adsorption energies. Here, we demonstrate an approach to predict energies using a convolutional neural network-based machine learning model to automatically obtain key features from the electronic density of states (DOS). The model, DOSnet, is evaluated for a diverse set of adsorbates and surfaces, yielding a mean absolute error on the order of 0.1 eV. In addition, DOSnet can provide physically meaningful predictions and insights by predicting responses to external perturbations to the electronic structure without additional DFT calculations, paving the way for the accelerated discovery of materials and catalysts by exploration of the electronic space.