Stability and Equilibrium Structures of Unknown Ternary Metal Oxides Explored by Machine-Learned Potentials

Abstract

Ternary metal oxides are crucial components in a wide range of applications and have been extensively cataloged in experimental materials databases. However, there still exist cation combinations with unknown stability and structures of their compounds in oxide forms. In this study, we employ extensive crystal structure prediction methods, accelerated by machinelearned potentials, to investigate these untapped chemical spaces. We examine 181 ternary metal oxide systems, encompassing most cations except for partially filled 3d or f shells, and determine their lowest-energy crystal structures with representative stoichiometry derived from prevalent oxidation states or recommender systems. Consequently, we discover 45 ternary oxide systems containing stable compounds against decomposition into binary or elemental phases, the majority of which incorporate noble metals. Comparisons with other theoretical databases highlight the strengths and limitations of informatics-based material searches. With a relatively modest computational resource requirement, we contend that heuristic-based structure searches, as demonstrated in this study, offer a promising approach for future materials discovery endeavors.

Intelligent Structure Searching and Designs for Nanoclusters: Effective Units in Atomic Manufacturing

“…[ 252,253 ] Besides the prediction of cluster structures, the MLPs also play an important role in crystal structure prediction. [ 254–259 ] These studies indicate the feasibility of predicting cluster structures through MLPs. The development of efficient machine learning methods can take into account both accuracy and large‐scale simulation, and is expected to solve practical problems in cluster applications.…”

Machine Learning-Assisted Exploration and Identification of Aqueous Dispersants in the Vast Diversity of Organic Chemicals

“…From deciphering intricate biological processes to optimizing industrial operations, ML offers a transformative approach to uncovering insights and solving challenges that were once considered insurmountable. The application of ML in materials exploration was pioneered in chemoinformatics for drug discovery , and in materials informatics for inorganic material development. − However, these efforts were primarily geared toward the prediction of intrinsic material properties, such as melting point, hardness, etc. There have only been a few reports addressing complex systems, such as the fabrication of dispersions and interaction with other materials, where the dispersion outcome is inseparably governed by the fabrication factors.…”

Band Alignment of Oxides by Learnable Structural-Descriptor-Aided Neural Network and Transfer Learning

“…Virtual screening based on machine learning is an efficient way to explore new materials with desired functions, where a surrogate model enables us to virtually predict material properties. − In particular, theoretical calculations can generate comparatively large data sets that are prerequisites for constructing accurate surrogate models. Previous studies have reported successful materials screening for various properties by machine learning in combination with theoretical calculations. − ,− …”