Machine learning-enabled exploration of the electrochemical stability of real-scale metallic nanoparticles.

Surface Pourbaix diagrams are critical to understanding the stability of nanomaterials in electrochemical environments. Their construction based on density functional theory is, however, prohibitively expensive for real-scale systems, such as several nanometer-size nanoparticles (NPs). Herein, with the aim of accelerating the accurate prediction of adsorption energies, we developed a bond-type embedded crystal graph convolutional neural network (BE-CGCNN) model in which four bonding types were treated differently. Owing to the enhanced accuracy of the bond-type embedding approach, we demonstrate the construction of reliable Pourbaix diagrams for very large-size NPs involving up to 6525 atoms (approximately 4.8 nm in diameter), which enables the exploration of electrochemical stability over various NP sizes and shapes. BE-CGCNN-based Pourbaix diagrams well reproduce the experimental observations with increasing NP size. This work suggests a method for accelerated Pourbaix diagram construction for real-scale and arbitrarily shaped NPs, which would significantly open up an avenue for electrochemical stability studies.

Interpretable Deep Learning Model for Analyzing the Relationship between the Electronic Structure and Chemisorption Property.

The use of machine learning (ML) is exploding in materials science as a result of its high predictive performance of material properties. Tremendous trainable parameters are required to build an outperforming predictive model, which makes it impossible to retrace how the model predicts well. However, it is necessary to develop a ML model that can extract human-understandable knowledge while maintaining performance for a universal application to materials science. In this study, we developed a deep learning model that can interpret the correlation between surface electronic density of states (DOSs) of materials and their chemisorption property using the attention mechanism that provides which part of DOS is important to predict adsorption energies. The developed model constructs the well-known d-band center theory without any prior knowledge. This work shows that human-interpretable knowledge can be extracted from complex ML models.

Accelerated mapping of electronic density of states patterns of metallic nanoparticles via machine-learning.

Within first-principles density functional theory (DFT) frameworks, it is challenging to predict the electronic structures of nanoparticles (NPs) accurately but fast. Herein, a machine-learning architecture is proposed to rapidly but reasonably predict electronic density of states (DOS) patterns of metallic NPs via a combination of principal component analysis (PCA) and the crystal graph convolutional neural network (CGCNN). With the PCA, a mathematically high-dimensional DOS image can be converted to a low-dimensional vector. The CGCNN plays a key role in reflecting the effects of local atomic structures on the DOS patterns of NPs with only a few of material features that are easily extracted from a periodic table. The PCA-CGCNN model is applicable for all pure and bimetallic NPs, in which a handful DOS training sets that are easily obtained with the typical DFT method are considered. The PCA-CGCNN model predicts the R2 value to be 0.85 or higher for Au pure NPs and 0.77 or higher for Au@Pt core@shell bimetallic NPs, respectively, in which the values are for the test sets. Although the PCA-CGCNN method showed a small loss of accuracy when compared with DFT calculations, the prediction time takes just ~ 160 s irrespective of the NP size in contrast to DFT method, for example, 13,000 times faster than the DFT method for Pt147. Our approach not only can be immediately applied to predict electronic structures of actual nanometer scaled NPs to be experimentally synthesized, but also be used to explore correlations between atomic structures and other spectrum image data of the materials (e.g., X-ray diffraction, X-ray photoelectron spectroscopy, and Raman spectroscopy).

Reducing Time to Discovery: Materials and Molecular Modeling, Imaging, Informatics, and Integration.

Multiscale and multimodal imaging of material structures and properties provides solid ground on which materials theory and design can flourish. Recently, KAIST announced 10 flagship research fields, which include KAIST Materials Revolution: Materials and Molecular Modeling, Imaging, Informatics and Integration (M3I3). The M3I3 initiative aims to reduce the time for the discovery, design and development of materials based on elucidating multiscale processing-structure-property relationship and materials hierarchy, which are to be quantified and understood through a combination of machine learning and scientific insights. In this review, we begin by introducing recent progress on related initiatives around the globe, such as the Materials Genome Initiative (U.S.), Materials Informatics (U.S.), the Materials Project (U.S.), the Open Quantum Materials Database (U.S.), Materials Research by Information Integration Initiative (Japan), Novel Materials Discovery (E.U.), the NOMAD repository (E.U.), Materials Scientific Data Sharing Network (China), Vom Materials Zur Innovation (Germany), and Creative Materials Discovery (Korea), and discuss the role of multiscale materials and molecular imaging combined with machine learning in realizing the vision of M3I3. Specifically, microscopies using photons, electrons, and physical probes will be revisited with a focus on the multiscale structural hierarchy, as well as structure-property relationships. Additionally, data mining from the literature combined with machine learning will be shown to be more efficient in finding the future direction of materials structures with improved properties than the classical approach. Examples of materials for applications in energy and information will be reviewed and discussed. A case study on the development of a Ni-Co-Mn cathode materials illustrates M3I3's approach to creating libraries of multiscale structure-property-processing relationships. We end with a future outlook toward recent developments in the field of M3I3.

Synthesis of Chemically Ordered Pt3Fe/C Intermetallic Electrocatalysts for Oxygen Reduction Reaction with Enhanced Activity and Durability via a Removable Carbon Coating.

Recently, Pt3M (M = Fe, Ni, Co, Cu, etc.) intermetallic compounds have been highlighted as promising candidates for oxygen reduction reaction (ORR) catalysts. In general, to form those intermetallic compounds, alloy phase nanoparticles are synthesized and then heat-treated at a high temperature. However, nanoparticles easily agglomerate during the heat treatment, resulting in a decrease in electrochemical surface area (ECSA). In this study, we synthesized Pt-Fe alloy nanoparticles and employed carbon coating to protect the nanoparticles from agglomeration during heat treatment. As a result, Pt3Fe L12 structure was obtained without agglomeration of the nanoparticles; the ECSA of Pt-Fe alloy and intermetallic Pt3Fe/C was 37.6 and 33.3 m2 gPt-1, respectively. Pt3Fe/C exhibited excellent mass activity (0.454 A mgPt-1) and stability with superior resistances to nanoparticle agglomeration and iron leaching. Density functional theory (DFT) calculation revealed that, owing to the higher dissolution potential of Fe atoms on the Pt3Fe surface than those on the Pt-Fe alloy, Pt3Fe/C had better stability than Pt-Fe/C. A single cell fabricated with Pt3Fe/C showed higher initial performance and superior durability, compared to that with commercial Pt/C. We suggest that Pt3M chemically ordered electrocatalysts are excellent candidates that may become the most active and durable ORR catalysts available.

CO oxidation by MoS2-supported Au19 nanoparticles: effects of vacancy formation and tensile strain.

The mechanism of the catalytic oxidation of CO activated by MoS2-supported Au19 nanoparticles (NPs) was studied using density functional theory calculations. Of particular interest were the effects of the physical/chemical modification of a MoS2 support on the CO oxidation pathway and the activation of specific reactive centers, i.e., the Au atoms of Au19 or the Au-MoS2 perimeter sites. We systematically modified MoS2 by introducing an S vacancy or 5% tensile strain and studied the shift of each reaction step and the overall change in the reaction pathway and activity. Despite the lack of direct involvement of the Au-MoS2 perimeter in the reaction, the combination of an S vacancy and the tensile strain in the MoS2 support was found to improve the stability and catalytic activity of Au NPs for CO oxidation. The results show that support modification can provide information for new pathways for the rational design of Au-based catalysts.