Inorganic Crystal Structure Prototype Database Based on Unsupervised Learning of Local Atomic Environments

Abstract

Recognition of structure prototypes from tremendous known inorganic crystal structures has been an important subject beneficial for material science research and new materials design. The existing databases of inorganic crystal structure prototypes were mostly constructed by classifying materials in terms of the crystallographic space group information. Herein, we employed a distinct strategy to construct the inorganic crystal structure prototype database, relying on the classification of materials in terms of local atomic environments (LAE) accompanied by unsupervised machine learning method. Specifically, we adopted a hierarchical clustering approach onto all experimentally known inorganic crystal structures data to identify structure prototypes. The criterion for hierarchical clustering is the LAE represented by the state-of-the-art structure fingerprints of the improved bond-orientational order parameters and the smooth overlap of atomic positions. This allows us to build up a LAE-based Inorganic Crystal Structure Prototype Database (LAE-ICSPD) containing 15,613 structure prototypes with defined stoichiometries. In addition, we have developed a Structure Prototype Generator Infrastructure (SPGI) package, which is a useful toolkit for structure prototype generation. Our developed SPGI toolkit and LAE-ICSPD are beneficial for investigating inorganic materials in a global way as well as accelerating materials discovery process in the datadriven mode.

Design of Organic–Inorganic Hybrid Heterostructured Semiconductors via High-Throughput Materials Screening for Optoelectronic Applications

“…High-throughput firstprinciples calculations and ML-based data mining were performed via the Jilin Artificial Intelligence-aided Material-design Integrated Package (JAMIP), which is an open-source artificial intelligence-aided datadriven infrastructure specially designed for computational material informatics. 54,55 Data mining of the high-throughput calculated results was performed using the gradient boosting regression tree (GBRT) ML model, 56 with the aim of building a relationship between physical/chemical descriptors and target properties. We chose formation energy and band gap variation from bulk semiconductors to formed HHSs as the target properties.…”

“…The optical properties were calculated using the PBE functional with the scissor operator to fix the band gap at the HSE level. High-throughput first-principles calculations and ML-based data mining were performed via the Jilin Artificial Intelligence-aided Material-design Integrated Package (JAMIP), which is an open-source artificial intelligence-aided data-driven infrastructure specially designed for computational material informatics. , …”