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:
- 10560449
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- 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 Fabrication of 3dmetal‐based core@shell nanocatalysts with engineered Pt‐surfaces provides an effective approach for improving the catalytic performance. The challenges in such preparation include shape control of the 3dmetallic cores and thickness control of the Pt‐based shells. Herein, we report a colloidal seed‐mediated method to prepare octahedral CuNi@Pt‐Cu core@shell nanocrystals using CuNi octahedral cores as the template. By precisely controlling the synthesis conditions including the deposition rate and diffusion rate of the shell‐formation through tuning the capping ligand, reaction temperature, and heating rate, uniform Pt‐based shells can be achieved with a thickness of <1 nm. The resultant carbon‐supported CuNi@Pt‐Cu core@shell nano‐octahedra showed superior activity in electrochemical methanol oxidation reaction (MOR) compared with the commercial Pt/C catalysts and carbon‐supported CuNi@Pt‐Cu nano‐polyhedron counterparts.more » « less
-
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-establishedd-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
-
Machine learning (ML) algorithms have advanced significantly in recent years, progressively evolving into artificial intelligence (AI) agents capable of solving complex, human-like intellectual challenges. Despite the advancements, the interpretability of these sophisticated models lags behind, with many ML architectures remaining black boxes that are too intricate and expansive for human interpretation. Recognizing this issue, there has been a revived interest in the field of explainable AI (XAI) aimed at explaining these opaque ML models. However, XAI tools often suffer from being tightly coupled with the underlying ML models and are inefficient due to redundant computations. We introduce provenance-enabled explainable AI (PXAI). PXAI decouples XAI computation from ML models through a provenance graph that tracks the creation and transformation of all data within the model. PXAI improves XAI computational efficiency by excluding irrelevant and insignificant variables and computation in the provenance graph. Through various case studies, we demonstrate how PXAI enhances computational efficiency when interpreting complex ML models, confirming its potential as a valuable tool in the field of XAI.more » « less
-
The extensive research on ultrathin ferrous oxide (FeO) islands and films over the last few decades has significantly contributed to the understanding of their structural and catalytic properties. In this regard, the local chemical properties of FeO edges, such as their metal affinity, play a critical role in determining and tuning the catalytic reactivity of FeO, which however remains largely unexplored. In this work, we use scanning tunneling microscopy (STM) to study the interaction of Pd and Pt with FeO grown on Au(111). Different Fe affinities for Pd and Pt are demonstrated by the preferential growth of Pd on the Fe-terminated edge and Pt on the O-terminated edge of FeO nanoislands, resulting in selectively blocked FeO edges. In addition to revealing the different metal affinities of FeO edges, our results provide new insights into the edge reactivity of FeO/Au(111) and suggest an approach for controlling the selectivity of FeO catalysts.more » « less
