Machine-Learning-Driven High-Throughput Screening of Transition-Metal Atom Intercalated g-C₃N₄/MX₂ (M = Mo, W; X = S, Se, Te) Heterostructures for the Hydrogen Evolution Reaction

Abstract

Rising global energy demand, accompanied by environmental concerns linked to conventional fossil fuels, necessitates a shift toward cleaner and sustainable alternatives. This study focuses on the machine-learning (ML)-driven high-throughput screening of transition-metal (TM) atom intercalated g-C3N4/MX2 (M = Mo, W; X = S, Se, Te) heterostructures to unravel the rich landscape of possibilities for enhancing the hydrogen evolution reaction (HER) activity. The stability of the heterostructures and the intercalation within the substrates are verified through adhesion and binding energies, showcasing the significant impact of chalcogenide selection on the interaction properties. Based on hydrogen adsorption Gibbs free energy (ΔG H) computed via density functional theory (DFT) calculations, several ML models were evaluated, particularly random forest regression (RFR) emerges as a robust tool in predicting HER activity with a low mean absolute error (MAE) of 0.118 eV, thereby paving the way for accelerated catalyst screening. The Shapley Additive exPlanation (SHAP) analysis elucidates pivotal descriptors that influence the HER activity, including hydrogen adsorption on the C site (HC), MX layer (HMX), S site (HS), and intercalation of TM atoms at the N site (IN). Overall, our integrated approach utilizing DFT and ML effectively identifies hydrogen adsorption on the N site (site-3) of g-C3N4 as a pivotal active site, showcasing exceptional HER activity in heterostructures intercalated with Sc and Ti, underscoring their potential for advancing catalytic performance.

InVO4-Decorated Ti3C2 MXene for Efficient Photocatalytic Hydrogen Evolution

“…The optimized structures of InVO 4 , Ti 3 C 2 , and IVTC are shown in Figure a–c. The catalytic activity in HERs is often assessed using the Gibbs free energy (Δ G H* ) of hydrogen adsorption, , where the Δ G H close to zero reflects excellent catalytic performance as it balances the adsorption and desorption processes necessary for effective hydrogen evolution. Figure d,e shows the relaxed configurations of hydrogen adsorption on InVO 4 , Ti 3 C 2 , and IVTC structures and the associated Gibbs free energy diagram.…”

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

“…To predict HER performance, the study utilized six different ML models with four different feature types: Physicochemical properties: This set included the Mendeleev Number, Row, Valence Electrons of d orbital, and Electronegativity. Simple one-hot encoding of atomic number: A method to encode the presence of each metal atom in the catalyst without implying any physicochemical properties, effectively turning the atomic number into a binary vector. Gibbs free energies of the TMSACs: Values that were included as part of the input features to directly relate the single-atom catalytic performance to the performance of dual-atom configurations. Further discussion of the use of these properties along with ML in the context of HER catalyzed by TMs can be found also in the work of Jyothirmai et al (2024) Combination of one-hot encoding and Gibbs free energies: This combined approach integrates the simplicity of one-hot encoding with the direct relevance of Gibbs free energy values for TMSACs. Among these, the ANN model showed the highest accuracy using simple input features, specifically one-hot encoding of atomic numbers and Gibbs free energies of the TMSACs.…”

“…Gibbs free energies of the TMSACs: Values that were included as part of the input features to directly relate the single-atom catalytic performance to the performance of dual-atom configurations. Further discussion of the use of these properties along with ML in the context of HER catalyzed by TMs can be found also in the work of Jyothirmai et al (2024) …”