期刊
JOURNAL OF COMPUTATIONAL PHYSICS
卷 311, 期 -, 页码 173-195出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jcp.2016.01.034
关键词
Bayesian; Density functional theory; Exchange-correlation functional; Uncertainty quantification
资金
- EPSRC [EP/L027682/1]
- Computer Science and Mathematics Division of ORNL under DARPA EQUiPS program
- Royal Society through Wolfson Research Merit Award
- Hans Fisher Senior Fellowship - German Excellence Initiative
- European Union [291763]
- EPSRC [EP/L027682/1] Funding Source: UKRI
- Engineering and Physical Sciences Research Council [EP/L027682/1] Funding Source: researchfish
This paper presents the development of a new exchange-correlation functional from the point of view of machine learning. Using atomization energies of solids and small molecules, we train a linear model for the exchange enhancement factor using a Bayesian approach which allows for the quantification of uncertainties in the predictions. A relevance vector machine is used to automatically select the most relevant terms of the model. We then test this model on atomization energies and also on bulk properties. The average model provides a mean absolute error of only 0.116 eV for the test points of the G2/97 set but a larger 0.314 eV for the test solids. In terms of bulk properties, the prediction for transition metals and monovalent semiconductors has a very low test error. However, as expected, predictions for types of materials not represented in the training set such as ionic solids show much larger errors. (C) 2016 Elsevier Inc. All rights reserved.
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