Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts
Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts
复制标题
DOI：
10.1021/acs.jpclett.9b01428
复制
发表时间：
2019-08-01
影响因子：
5.7
通讯作者：
Ulissi, Zachary W.
中科院分区：
文献类型：
--
作者：
Back, Seoin;Yoon, Junwoong;Ulissi, Zachary W.
高通量筛选催化剂可以使用密度泛函理论计算来预测催化性能，通常与吸附结合能相关联。然而，与目前的方法相比，更完整的调查需要多进行2次计算，这使得计算成本成为一个瓶颈。最近开发的机器学习方法已经被证明可以从手工制作的特征中预测这些属性，但一直难以扩展到大的合成空间或复杂的活动位置。在这里，我们提出了一个基于原子和Voronoi多面体的邻域信息的原子表面结构深度学习卷积神经网络的应用。该模型有效地学习了最重要的表面特征来预测结合能。我们的方法用12000个数据训练后预测了CO和H的结合能，对于不同的化学空间，平均绝对误差为0.15 eV。我们的方法还能够创建显著图，确定原子对结合能的贡献。
High-throughput screening of catalysts can be performed using density functional theory calculations to predict catalytic properties, often correlated with adsorbate binding energies. However, more complete investigations would require an order of 2 more calculations compared to the current approach, making the computational cost a bottleneck. Recently developed machine-learning methods have been demonstrated to predict these properties from hand-crafted features but have struggled to scale to large composition spaces or complex active sites. Here, we present an application of a deep-learning convolutional neural network of atomic surface structures using atomic and Voronoi polyhedra-based neighbor information. The model effectively learns the most important surface features to predict binding energies. Our method predicts CO and H binding energies after training with 12 000 data for each adsorbate with a mean absolute error of 0.15 eV for a diverse chemical space. Our method is also capable of creating saliency maps that determine atomic contributions to binding energies.