Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis.
Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis.
复制标题
DOI：
10.1038/s41467-022-33256-2
复制
发表时间：
2022-10-02
影响因子：
16.6
通讯作者：
中科院分区：
文献类型：
--
作者：
多相催化反应受到原子尺度因素的微妙相互作用的影响，从催化剂的局部形态到高吸附物覆盖率的存在。通过计算模型描述这种现象需要生成和分析大空间的原子配置。为了解决这一挑战，我们提出了基于吸附剂化学环境的图形卷积神经网络（ACE-GCN），这是一种筛选工作流程，可以解释包括不同吸附物，结合位置，配位环境和底物形态的原子结构。使用该工作流程，我们开发了两个说明性系统的催化剂表面模型：（i）吸附在Pt 3Sn（111）合金表面上的NO，这对硝酸盐电还原过程很有意义，其中高吸附质覆盖率与合金基底的低对称性相结合产生了大的构型空间，以及（ii）吸附在台阶状Pt（221）面上的OH *，与氧还原反应相关，其中构型复杂性是由于存在不规则晶体表面、高吸附物覆盖率和方向依赖的吸附物-吸附物相互作用。在这两种情况下，ACE-GCN模型，在总DFT松弛配置的一部分（~10%）上训练，成功地描述了从大的配置空间中采样的非松弛原子配置的相对稳定性的趋势。这种方法预计将加速发展严格的描述催化剂表面在原位条件下。电子结构计算和机器学习策略的组合被开发用于预测复杂非均相催化剂在现实环境中的结构，从而为能源应用的优化提供新的机会。
Heterogeneous catalytic reactions are influenced by a subtle interplay of atomic-scale factors, ranging from the catalysts’ local morphology to the presence of high adsorbate coverages. Describing such phenomena via computational models requires generation and analysis of a large space of atomic configurations. To address this challenge, we present Adsorbate Chemical Environment-based Graph Convolution Neural Network (ACE-GCN), a screening workflow that accounts for atomistic configurations comprising diverse adsorbates, binding locations, coordination environments, and substrate morphologies. Using this workflow, we develop catalyst surface models for two illustrative systems: (i) NO adsorbed on a Pt3Sn(111) alloy surface, of interest for nitrate electroreduction processes, where high adsorbate coverages combined with low symmetry of the alloy substrate produce a large configurational space, and (ii) OH* adsorbed on a stepped Pt(221) facet, of relevance to the Oxygen Reduction Reaction, where configurational complexity results from the presence of irregular crystal surfaces, high adsorbate coverages, and directionally-dependent adsorbate-adsorbate interactions. In both cases, the ACE-GCN model, trained on a fraction (~10%) of the total DFT-relaxed configurations, successfully describes trends in the relative stabilities of unrelaxed atomic configurations sampled from a large configurational space. This approach is expected to accelerate development of rigorous descriptions of catalyst surfaces under in-situ conditions. A combination of electronic structure calculations and machine learning strategies is developed to predict structures of complex heterogeneous catalysts in realistic environments, yielding new opportunities for optimization for energy applications.
登录
查看更多内容
影响因子：
12.9
作者：
Cybulskis, Viktor J.;Bukowski, Brandon C.;Miller, Jeffrey T.
通讯作者：
Miller, Jeffrey T.
影响因子：
41.2
作者：
Greeley, J;Mavrikakis, M
通讯作者：
Mavrikakis, M
影响因子：
9.7
作者：
Deshpande, Siddharth;Maxson, Tristan;Greeley, Jeffrey
通讯作者：
Greeley, Jeffrey
影响因子：
21.8
作者：
Greeley, J.;Stephens, I. E. L.;Norskov, J. K.
通讯作者：
Norskov, J. K.
影响因子：
3.6
作者：
Ghanekar, Pushkar;Kubal, Joseph;Greeley, Jeffrey
通讯作者：
Greeley, Jeffrey