Compared with the traditional electrocatalyst screening of the nitrogen reduction reaction (NRR), machine learning (ML) has achieved high-throughput screening with less computational cost. In this paper, 140 TM@g-C_xN_y single-atom catalysts (SACs) are constructed for the NRR. The deep neural network (DNN) classification model and the extreme gradient boosting (XGBoost) model are selected from different models. A total of 10 features are proposed based on anchoring TM atom, coordination environment and adsorption intermediates. The former model distinguishes qualified and non-qualified catalysts with an accuracy rate of 87.5%, while the latter model predicts the free energy of NRR with a fitting coefficient of 0.82 on the test set. The NN bond length and the number of outermost d electrons of TM (N_d) are found to be the most important features for both models. Moreover, the NN bond length, N_d, and adsorption energy of *N₂H (ΔE_ad[N₂H]) are proved to reflect the degree of nitrogen (N₂) activation and serve as NRR descriptors. The moderate activation and half-filled or nearly half-filled d-orbitals of the TM atom (N_d ≈ 4) favor the NRR process. Among the 20 screened catalysts, Re@g-C₄N₃ shows the best catalytic activity, with a limiting potential (U_L) of only −0.13 V under implicit solvation. The activity origin is illustrated by the electronic properties and bond changes of NRR intermediates. This research provides a new approach for the high-throughput design and screening of SACs by ML based on DFT.

中文翻译：

---

基于机器学习的氮化碳单原子固氮催化剂高通量筛选


与传统的氮还原反应（NRR）电催化剂筛选相比，机器学习（ML）以更少的计算成本实现了高通量筛选。在本文中，为 NRR 构建了 140 个 TM@gC _x N _y单原子催化剂（SAC）。深度神经网络（DNN）分类模型和极限梯度提升（XGBoost）模型是从不同的模型中选取的。基于锚定TM原子、配位环境和吸附中间体，总共提出了10个特征。前一个模型区分合格和不合格催化剂的准确率为87.5%，而后一个模型预测NRR的自由能，在测试集上的拟合系数为0.82。然后 N 键长和 TM 最外层 d 电子数 ( N _d ) 被发现是两个模型最重要的特征。此外，N N键长、 N _d和*N ₂ H的吸附能( ΔE _ad [N ₂ H])被证明反映了氮(N ₂ )的活化程度并可作为NRR描述符。 TM原子的适度活化和半填充或接近半填充的d轨道（ N _d ≈ 4）有利于NRR过程。 在20种筛选的催化剂中，Re@gC ₄ N ₃显示出最好的催化活性，隐式溶剂化下的极限电势（ UL ）仅为_-0.13 V。 NRR 中间体的电子特性和键的变化说明了活性起源。该研究为基于DFT的机器学习高通量设计和筛选SAC提供了一种新方法。