An official website of the United States government
Abstract The electrochemical ammonia oxidation to dinitrogen as a means for energy and environmental applications is a key technology toward the realization of a sustainable nitrogen cycle. The state-of-the-art metal catalysts including Pt and its bimetallics with Ir show promising activity, albeit suffering from high overpotentials for appreciable current densities and the soaring price of precious metals. Herein, the immense design space of ternary Pt alloy nanostructures is explored by graph neural networks trained on ab initio data for concurrently predicting site reactivity, surface stability, and catalyst synthesizability descriptors. Among a few Ir-free candidates that emerge from the active learning workflow, Pt3Ru-M (M: Fe, Co, or Ni) alloys were successfully synthesized and experimentally verified to be more active toward ammonia oxidation than Pt, Pt3Ir, and Pt3Ru. More importantly, feature attribution analyses using the machine-learned representation of site motifs provide fundamental insights into chemical bonding at metal surfaces and shed light on design strategies for high-performance catalytic systems beyond thed-band center metric of binding sites.
more »
« less
Explainable AI for optimizing oxygen reduction on Pt monolayer core–shell catalysts
Abstract As a subfield of artificial intelligence (AI), machine learning (ML) has emerged as a versatile tool in accelerating catalytic materials discovery because of its ability to find complex patterns in high‐dimensional data. While the intricacy of cutting‐edge ML models, such as deep learning, makes them powerful, it also renders decision‐making processes challenging to explain. Recent advances in explainable AI technologies, which aim to make the inner workings of ML models understandable to humans, have considerably increased our capacity to gain insights from data. In this study, taking the oxygen reduction reaction (ORR) on {111}‐oriented Pt monolayer core–shell catalysts as an example, we show how the recently developed theory‐infused neural network (TinNet) algorithm enables a rapid search for optimal site motifs with the chemisorption energy of hydroxyl (OH) as a single descriptor, revealing the underlying physical factors that govern the variations in site reactivity. By exploring a broad design space of Pt monolayer core–shell alloys ( candidates) that were generated from thermodynamically stable bulk structures in existing material databases, we identified novel alloy systems along with previously known catalysts in the goldilocks zone of reactivity properties. SHAP (SHapley Additive exPlanations) analysis reveals the important role of adsorbate resonance energies that originate from ‐band interactions in chemical bonding at metal surfaces. Extracting physical insights into surface reactivity with explainable AI opens up new design pathways for optimizing catalytic performance beyond active sites.
more »
« less
- Award ID(s):
- 2245402
- PAR ID:
- 10611402
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Electrochemical Science Advances
- Volume:
- 4
- Issue:
- 6
- ISSN:
- 2698-5977
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract The hydrogen produced by Al‐doped SrTiO3/TiO2core‒shell catalysts with a range of Al‐doped SrTiO3cores and the same TiO2shell are compared. The study included SrTiO3cores doped with different amounts of Al (0, 1, 2, or 3 mol%) added at different points in the synthesis (prior to or during the molten salt treatment) and at different temperatures (900°C, 1000°C, and 1100°C). It was found that core‒shell catalysts with different cores had hydrogen generation rates that varied by a factor of more than 40 and varied with the processing parameters in the same way as the hydrogen generation rates of the cores alone. The best catalysts had 2 or 3 mol% added Al, added during treatment in a SrCl2molten salt at 1000°C or 1100°C. Because the core absorbs most of the light, its ability to separate and transport photogenerated charge carriers dominates the properties of the core‒shell catalyst. This indicates that, to optimize the properties of core‒shell catalysts, it is essential to optimize the properties of the core. While the shell can be important to protect the core from degradation, it is not as important to the overall reactivity as the core.more » « less
-
Abstract The electrocatalytic hydrogen evolution reaction (HER) is one of the most studied and promising processes for hydrogen fuel generation. Single-atom catalysts have been shown to exhibit ultra-high HER catalytic activity, but the harsh preparation conditions and the low single-atom loading hinder their practical applications. Furthermore, promoting hydrogen evolution reaction kinetics, especially in alkaline electrolytes, remains as an important challenge. Herein, Pt/C60catalysts with high-loading, high-dispersion single-atomic platinum anchored on C60are achieved through a room-temperature synthetic strategy. Pt/C60-2 exhibits high HER catalytic performance with a low overpotential (η10) of 25 mV at 10 mA cm−2. Density functional theory calculations reveal that the Pt-C60polymeric structures in Pt/C60-2 favors water adsorption, and the shell-like charge redistribution around the Pt-bonding region induced by the curved surfaces of two adjacent C60facilitates the desorption of hydrogen, thus favoring fast reaction kinetics for hydrogen evolution.more » « less
-
null (Ed.)Abstract Despite recent advances of data acquisition and algorithms development, machine learning (ML) faces tremendous challenges to being adopted in practical catalyst design, largely due to its limited generalizability and poor explainability. Herein, we develop a theory-infused neural network (TinNet) approach that integrates deep learning algorithms with the well-established d -band theory of chemisorption for reactivity prediction of transition-metal surfaces. With simple adsorbates (e.g., *OH, *O, and *N) at active site ensembles as representative descriptor species, we demonstrate that the TinNet is on par with purely data-driven ML methods in prediction performance while being inherently interpretable. Incorporation of scientific knowledge of physical interactions into learning from data sheds further light on the nature of chemical bonding and opens up new avenues for ML discovery of novel motifs with desired catalytic properties.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1002/elsa.202300028
