One of the most exciting tools that have entered the material science toolbox in recent years is machine learning. This collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied research. At present, we are witnessing an explosion of works that develop and apply machine learning to solid-state systems. We provide a comprehensive overview and analysis of the most recent research in this topic. As a starting point, we introduce machine learning principles, algorithms, descriptors, and databases in materials science. We continue with the description of different machine learning approaches for the discovery of stable materials and the prediction of their crystal structure. Then we discuss research in numerous quantitative structure-property relationships and various approaches for the replacement of first-principle methods by machine learning. We review how active learning and surrogate-based optimization can be applied to improve the rational design process and related examples of applications. Two major questions are always the interpretability of and the physical understanding gained from machine learning models. We consider therefore the different facets of interpretability and their importance in materials science. Finally, we propose solutions and future research paths for various challenges in computational materials science.

We perform an exhaustive theoretical study of the phase diagram of Cu-I binaries, focusing on Cupoor compositions, relevant for p-type transparent conduction. We find that the interaction between neighboring Cu vacancies is the determining factor that stabilizes non-stoichiometric zincblende phases. This interaction leads to defect complexes where Cu vacancies align preferentially along the [100] crystallographic direction. It turns out that these defect complexes have an important influence on hole conductivity, as they lead to dispersive conducting p-states that extend up to around 0.8 eV above the Fermi level. We furthermore observe a characteristic peak in the density of electronic states, which could provide an experimental signature for this type of defect complexes.

We present a practical procedure to obtain reliable and unbiased neural network based force fields for solids.

No abstract