KIHOON BANG Hong, Doosun Park, Youngtae 김동훈 한상수 Lee, Hyuck Mo 2024-01-12T06:36:08Z 2024-01-12T06:36:08Z 2023-06-18 2023-05 2041-1723 https://pubs.kist.re.kr/handle/201004/79929 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.</jats:p> English Nature Publishing Group Machine learning-enabled exploration of the electrochemical stability of real-scale metallic nanoparticles Article 10.1038/s41467-023-38758-1 1 Nature Communications, v.14, no.1 Nature Communications 14 1 Y scie scopus 001001080600025 Multidisciplinary Sciences Science & Technology - Other Topics Article ADSORBATE-ADSORBATE INTERACTIONS OXYGEN REDUCTION REACTION FUEL-CELL ADSORPTION ENERGIES SURFACE OXIDATION CATALYSTS CO ELECTROCATALYSTS APPROXIMATION