期刊
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
卷 16, 期 2, 页码 1105-1114出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jctc.9b00986
关键词
-
资金
- National Science Foundation [DMREF-1534260, OIA-1632824]
- U.S. Department of Energy Office of Science, Office of Basic Energy Sciences, Catalysis Science Program [DE-SC0007167]
- Texas Advanced Computing Center (TACC) [TG-CTS090100]
- U.S. Department of Energy at the National Energy Research Scientific Computing Center (NERSC) [DE-AC02-05CH11231]
- Pacific Northwest National Laboratory [130367, 49246]
Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Moreover, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predict-this is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据