In traditional machine learning (ML)-based material design, the defects of low prediction accuracy, overfitting and low generalization ability are mainly caused by the training of a single ML model. Here, a Soft Voting Ensemble Learning (SVEL) approach is proposed to solve the above issues by integrating multiple ML models in the same scene, thus pursuing more stable and reliable prediction. As a case study, SVEL is applied to develop the broad chemical space of novel pyrochlore electrocatalysts with the molecular formula of A2B2O7, to explore promising pyrochlore oxides and accelerate predictions of unknown pyrochlore in the periodic table. The model successfully established the structure-property relationship of pyrochlore, and selected six cost-effective pyrochlore from the periodic table with a high prediction accuracy of 91.7%, all of which showed good electrocatalytic performance. SVEL not only effectively avoids the high costs of experimentation and lengthy computations, but also addresses biases arising from data scarcity in single models. Furthermore, it has significantly reduced the research cycle of pyrochlore by ≈ 22 years, offering broad prospects for accelerating the development of materials genomics. SVEL method is intended to integrate multiple AI models to provide broader model training clues for the AI material design community.

The green and sustainable electrocatalytic conversion of nitrogen-containing compounds to ammonia is currently in high demand in order to replace the eco-unfriendly Haber-Bosch process. Model catalysts for the nitrate reduction reaction were obtained by electrodeposition of metal Co, Fe, and bimetallic Fe/Co nanoparticles from aqueous solutions onto a graphite substrate. The samples were characterized by the following methods: SEM, XRD, XPS, UV-vis spectroscopy, cyclic (and linear) voltammetry, chronoamperometry, and electrochemical impedance spectroscopy. In addition, the determination of the electrochemically active surface was also performed for all electrocatalysts. The best electrocatalyst was a sample containing Fe-nanoparticles on the layer of Co-nanoparticles, which showed a Faradaic efficiency of 58.2% (E = -0.785 V vs. RHE) at an ammonia yield rate of 14.6 μmol h-1 cm-2 (at ambient condition). An opinion was expressed to elucidate the mechanism of coordinated electrocatalytic action of a bimetallic electrocatalyst. This work can serve primarily as a starting point for future investigations on electrocatalytic conversion reactions to ammonia using model catalysts of the proposed type.

暂无摘要。

暂无摘要。