We propose a novel representation of materials named an ‘orbital-field matrix (OFM)’, which is based on the distribution of valence shell electrons. We demonstrate that this new representation can be highly useful in mining material data. Experimental investigation shows that the formation energies of crystalline materials, atomization energies of molecular materials, and local magnetic moments of the constituent atoms in bimetal alloys of lanthanide metal and transition-metal can be predicted with high accuracy using the OFM. Knowledge regarding the role of the coordination numbers of the transition-metal and lanthanide elements in determining the local magnetic moments of the transition-metal sites can be acquired directly from decision tree regression analyses using the OFM. Graphical Abstract

Deep learning (DL) models currently employed in materials research exhibit certain limitations in delivering meaningful information for interpreting predictions and comprehending the relationships between structure and material properties. To address these limitations, we propose an interpretable DL architecture that incorporates the attention mechanism to predict material properties and gain insights into their structure–property relationships. The proposed architecture is evaluated using two well-known datasets (the QM9 and the Materials Project datasets), and three in-house-developed computational materials datasets. Train–test–split validations confirm that the models derived using the proposed DL architecture exhibit strong predictive capabilities, which are comparable to those of current state-of-the-art models. Furthermore, comparative validations, based on first-principles calculations, indicate that the degree of attention of the atoms’ local structures to the representation of the material structure is critical when interpreting structure–property relationships with respect to physical properties. These properties encompass molecular orbital energies and the formation energies of crystals. The proposed architecture shows great potential in accelerating material design by predicting material properties and explicitly identifying crucial features within the corresponding structures.

Existing data-driven approaches for exploring high-entropy alloys (HEAs) face three challenges: numerous element-combination candidates, designing appropriate descriptors, and limited and biased existing data. To overcome these issues, here we show the development of an evidence-based material recommender system (ERS) that adopts Dempster–Shafer theory, a general framework for reasoning with uncertainty. Herein, without using material descriptors, we model, collect and combine pieces of evidence from data about the HEA phase existence of alloys. To evaluate the ERS, we compared its HEA-recommendation capability with those of matrix-factorization- and supervised-learning-based recommender systems on four widely known datasets of up-to-five-component alloys. Thek-fold cross-validation on the datasets suggests that the ERS outperforms all competitors. Furthermore, the ERS shows good extrapolation capabilities in recommending quaternary and quinary HEAs. We experimentally validated the most strongly recommended Fe–Co-based magnetic HEA (namely, FeCoMnNi) and confirmed that its thin film shows a body-centered cubic structure.

Sputtering of a single-element material surface by monatomic ion impact is one of the simplest and most fundamental phenomena of plasma–surface interaction. Despite its seemingly simple and well-defined nature, its collision cascade dynamics is so complex that no widely applicable formula of the sputtering yield has ever been derived analytically from the first principles. When the first-principles approach to a complex problem fails to unveil its nature, a data-driven approach, or machine learning, may be used to transform the problem into a tractable model. In this study, regression models of sputtering yields of such systems were constructed based on publicly available data derived from a large number of past experiments. The analysis has also identified the descriptors (i.e., physical variables characterizing the surface and incident ion species) on which the sputtering phenomena depend most strongly and presented quantitative evaluation on how sensitively the regression models depend on each descriptor or group of descriptors. Information obtained in this study can facilitate an understanding of the fundamental workings of the sputtering phenomena in the absence of rigorous analytical theory.