We describe a first open-access database of experimentally investigated hybrid organic-inorganic materials with two-dimensional (2D) perovskite-like crystal structure. The database includes 515 compounds, containing 180 different organic cations, 10 metals (Pb, Sn, Bi, Cd, Cu, Fe, Ge, Mn, Pd, Sb) and 3 halogens (I, Br, Cl) known so far and will be regularly updated. The database contains a geometrical and crystal chemical analysis of the structures, which are useful to reveal quantitative structure-property relationships for this class of compounds. We show that the penetration depth of spacer organic cation into the inorganic layer and M-X-M bond angles increase in the number of inorganic layers (n). The machine learning model is developed and trained on the database, for the prediction of a band gap with accuracy within 0.1 eV. Another machine learning model is trained for the prediction of atomic partial charges with accuracy within 0.01 e. We show that the predicted values of band gaps decrease with an increase of the n and with an increase of M-X-M angles for single-layered perovskites. In general, the proposed database and machine learning models are shown to be useful tools for the rational design of new 2D hybrid perovskite materials.
Nowadays the development of new functional materials/chemical compounds using machine learning (ML) techniques is a hot topic and includes several crucial steps, one of which is the choice of chemical structure representation. The classical approach of rigorous feature engineering in ML typically improves the performance of the predictive model, but at the same time, it narrows down the scope of applicability and decreases the physical interpretability of predicted results. In this study, we present graph convolutional neural networks (GCNNs) as an architecture that allows for successfully predicting the properties of compounds from diverse domains of chemical space, using a minimal set of meaningful descriptors. The applicability of GCNN models has been demonstrated by a wide range of chemical domain-specific properties. Their performance is comparable to state-of-the-art techniques; however, this architecture exempts from the need to carry out precise feature engineering.
Nanoporous materials have attracted significant interest as an emerging platform for adsorption-related applications. The high-throughput computational screening became a standard technique to access the performance of thousands of candidates, but its accuracy is highly dependent on a partial charge assignment method. In this study, we propose a machine learning model that can reconcile the benefits of two main approaches: the high accuracy of density-derived electrostatic and chemical charge (DDEC) method and the scalability of charge equilibration (Qeq) method. The mean absolute deviation of predicted partial charges from the original DDEC counterparts achieves an excellent level of 0.01 e. The model, initially designed for metal−organic frameworks (MOFs), is also capable of assigning charges to another class of nanoporous materials, covalent organic frameworks, with acceptable accuracy. Adsorption properties of carbon dioxide, calculated by means of machine learning-derived charges, are consistent with the reference data obtained with DDEC charges. We also provide the first virtually complete set of partial charges for the publicly available subset of the Computation-Ready, Experimental (CoRE) MOF 2019 database.
The unprecedented structural flexibility and diversity of inorganic frameworks of layered hybrid halide perovskites (LHHPs) rise up a wide range of useful optoelectronic properties thus predetermining the extraordinary high interest to this family of materials. Nevertheless, the influence of different types of distortions of their inorganic framework on key physical properties such as band gap has not yet been quantitatively identified. We provided a systematic study of the relationships between LHHPs' band gaps and six main structural descriptors of inorganic framework, including interlayer distances (d int ), in-plane and out-of-plane distortion angles in layers of octahedra (θ in , θ out ), layer shift factor (LSF), axial and equatorial Pb-I bond distances (d ax , d eq ). Using the set on the selected structural distortions we realized the inverse materials design based on multi-step DFT and machine learning approach to search LHHPs with target values of the band gap. The analysis of calculated descriptors -band gap dependences for the wide range of generated model structures of (100) single-layered LHHPs results in the following descending order of their importance: d int > θ in > d ax > LSF min > θ out > d eq > LSF max , and also implies a strong interaction value for some pairs of structural descriptors. Moreover, we found that the structures with completely different distortions of inorganic framework can have similar band gap, as illustrated by a number of both experimental and model structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.