Machine learning high-throughput screening of rare earth SACs with different coordination environments for the HER

Area of Science:

• Materials Science
• Computational Chemistry
• Electrochemistry

Background:

• Developing efficient electrocatalysts for the hydrogen evolution reaction (HER) is crucial for clean energy technologies.
• Rare earth single-atom catalysts (SACs) offer unique electronic properties for catalytic applications.
• High-throughput screening methods are needed to accelerate the discovery of novel SACs.

Purpose of the Study:

• To perform a high-throughput screening of rare earth SACs for HER.
• To evaluate the catalytic performance using machine learning (ML) and density functional theory (DFT).
• To identify potential SACs with high HER activity.

Main Methods:

• Employed ML for high-throughput screening of rare earth SACs.
• Utilized DFT to calculate the Gibbs free energy of hydrogen adsorption (ΔG_*H) for 100 catalyst groups.
• Trained a Gradient Boosting Regressor (GBR) model to predict HER performance.

Main Results:

• The GBR model achieved high accuracy (R² = 0.970, RMSE = 0.157) in predicting ΔG_*H.
• Identified three rare earth SACs with excellent HER performance, indicated by |ΔG_*H| < 0.20 eV.
• Demonstrated the effectiveness of ML-guided screening for catalyst discovery.

Conclusions:

• ML combined with DFT is a powerful approach for accelerating the discovery of efficient HER catalysts.
• The identified rare earth SACs show significant potential for practical applications in hydrogen production.
• This study provides a pathway for designing next-generation electrocatalysts.