Jyothirmai M V, Dantuluri Roshini, Sinha Priyanka, Abraham B Moses, Singh Jayant K
Department of Chemical Engineering, Indian Institute of Technology Kanpur, Kanpur 208016, India.
Departament de Ciència de Materials i Química Física, Institut de Química Teòrica i Computacional (IQTCUB), Universitat de Barcelona, c/Martí i Franquès 1-11, Barcelona 08028, Spain.
ACS Appl Mater Interfaces. 2024 Mar 13;16(10):12437-12445. doi: 10.1021/acsami.3c17389. Epub 2024 Mar 4.
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-CN/MX (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 (Δ) 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 (H), MX layer (H), S site (H), and intercalation of TM atoms at the N site (I). Overall, our integrated approach utilizing DFT and ML effectively identifies hydrogen adsorption on the N site (site-3) of g-CN as a pivotal active site, showcasing exceptional HER activity in heterostructures intercalated with Sc and Ti, underscoring their potential for advancing catalytic performance.
全球能源需求不断增长，加之与传统化石燃料相关的环境问题，使得向更清洁、可持续的替代能源转变成为必要。本研究聚焦于通过机器学习驱动的高通量筛选过渡金属（TM）原子插层的g-CN/MX（M = Mo、W；X = S、Se、Te）异质结构，以揭示增强析氢反应（HER）活性的丰富可能性。通过粘附能和结合能验证了异质结构的稳定性以及基底内的插层情况，展示了硫族化物选择对相互作用性质的重大影响。基于通过密度泛函理论（DFT）计算得出的氢吸附吉布斯自由能（Δ），评估了多个机器学习模型，特别是随机森林回归（RFR）成为预测HER活性的强大工具，平均绝对误差（MAE）低至0.118 eV，从而为加速催化剂筛选铺平了道路。Shapley加法解释（SHAP）分析阐明了影响HER活性的关键描述符，包括在C位点（H）、MX层（H）、S位点（H）上的氢吸附以及TM原子在N位点（I）的插层。总体而言，我们利用DFT和机器学习的综合方法有效地将g-CN在N位点（位点3）上的氢吸附确定为关键活性位点，展示了在插层有Sc和Ti的异质结构中卓越的HER活性，突出了它们在提升催化性能方面的潜力。
