Search

We introduce a computational method to optimize target physical properties in the full configuration space regarding atomic composition, chemical stoichiometry, and crystal structure. The approach combines the universal potential of the crystal graph neural network and Bayesian optimization. The proposed approach effectively obtains the crystal structure with the strongest atomic cohesion from all possible crystals. Several new crystals with high atomic cohesion are identified and confirmed by density functional theory for thermodynamic and dynamic stability. Our method introduces a novel approach to inverse materials design with additional functional properties for practical applications.

We developed a density functional theory-free approach for crystal structure prediction via combing graph network (GN) and Bayesian optimization (BO). GN is adopted to establish the correlation model between crystal structure and formation enthalpies. BO is to accelerate searching crystal structure with optimal formation enthalpy. The approach of combining GN and BO for crystal Structure Searching (GN-BOSS), in principle, can predict crystal structure at given chemical compositions without additional constraints on cell shapes and lattice symmetries. The applicability and efficiency of GN-BOSS approach is then verified via solving the classical Ph-vV challenge. It can correctly predict the crystal structures of 24 binary compounds from scratch with averaged computational cost ~ 30 minutes each by only one CPU core. GN-BOSS approach may open a new avenue to data-driven crystal structural prediction without using the expensive DFT calculations.

Symbolic regression (SR) is an emerging method for building analytical formulas to find models that best fit data sets. Here, SR was used to guide the design of new oxide perovskite catalysts with improved oxygen evolution reaction (OER) activities. An unprecedentedly simple descriptor, {\mu}/t, where {\mu} and t are the octahedral and tolerance factors, respectively, was identified, which accelerated the discovery of a series of new oxide perovskite catalysts with improved OER activity. We successfully synthesized five new oxide perovskites and characterized their OER activities. Remarkably, four of them, Cs0.4La0.6Mn0.25Co0.75O3, Cs0.3La0.7NiO3, SrNi0.75Co0.25O3, and Sr0.25Ba0.75NiO3, outperform the current state-of-the-art oxide perovskite catalyst, Ba0.5Sr0.5Co0.8Fe0.2O3 (BSCF). Our results demonstrate the potential of SR for accelerating data-driven design and discovery of new materials with improved properties.

Halide perovskites, with prototype cubic phase ABX3, undergo various phase transitions accompanied by rigid rotations of corner-sharing BX6 octahedra. Using first-principles density functional theory calculations, we have performed a comprehensive investigation of all the possible octahedral tilting in eighteen halide perovskites ABX3 (A = Cs, Rb, K; B= Pb, Sn; X= I, Br, Cl) and found that the stabilization energies i.e. energy differences between cubic and the most stable tilted phases, are linearly correlated with tolerance factor t. Moreover, the tilt energies i.e. energy differences between cubic and various tilted phases, are linearly correlated with the change of atomic packing fractions ({\Delta}{\eta}), confirming the importance of atomic packing fraction as part of stability descriptor (t+{\mu}){\eta}, proposed in our previous work [JACS 139, 14905 (2017)]. We further demonstrate that (t+{\mu}){\eta}remains the best stability descriptor for tilted perovskites among descriptor candidates of {\eta}, {\mu}, t, and t+{\mu},extending previously proposed stability trend from cubic phases to tilted phases in general perovskites., Comment: 15 pages; 6 figures

Perovskite stability is of the core importance and difficulty in current research and application of perovskite solar cells. Nevertheless, over the past century, the formability and stability of perovskite still relied on simplified factor based on human knowledge, such as the commonly used tolerance factor t. Combining machine learning (ML) with first-principles density functional calculations, we proposed a strategy to firstly calculate the decomposition energies, considered to be closely related to thermodynamic stability, of 354 kinds halide perovskites, establish the machine learning relationship between decomposition energy and compositional ionic radius and investigate the stabilities of 14,190 halide double perovskites. The ML-predicted results enable us to rediscover a series of stable rare earth metal halide perovskites (up to ~1000 kinds), indicating the generalization of this model and further provide elemental and concentration suggestion for improving the stability of mixed perovskite., Comment: 11 pages, 5 figures, 12 pages for supporting information