Machine Learning-Assisted Design of Dual-Atom Catalysts for Urea Electrosynthesis

Yun Han's dataset presents a closed-loop data-driven strategy for designing carbon-based dual-atom catalysts for direct urea electrosynthesis. The data includes results from high-throughput density functional theory calculations on 90 heteroatomic metal pairs and machine learning screening of 1458 candidates. The dataset was last updated on 2026-04-21.

Use Cases

• Training machine learning models for catalyst property prediction based on intrinsic atomic features.
• Analyzing the relationship between coadsorption energy and catalytic selectivity for C-N coupling.
• Screening candidate dual-atom catalysts based on thermodynamic pathway data.
• Studying electronic structure properties, such as d-electron density near the Fermi level, for catalyst activation.

Strengths

• Dataset is based on high-throughput density functional theory calculations for 90 heteroatomic metal pairs.
• Includes machine learning screening results for a chemical space of 1458 candidate catalysts.
• Identifies a specific thermodynamic window (-3.57 to -3.08 eV) favoring the C-N coupling pathway.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data may reflect methodological bias inherent to the computational and machine learning approach described.

Provenance

Source

figshare, author Yun Han

Collection Method

Generated via high-throughput density functional theory calculations and machine learning (XGBoost) modeling.

Freshness

Last updated 2026-04-21 10:17:47; freshness should be verified.