Abstract
AbstractMaterials databases generated by high-throughput computational screening, typically using density functional theory (DFT), have become valuable resources for discovering new heterogeneous catalysts, though the computational cost associated with generating them presents a crucial roadblock. Hence there is a significant demand for developing descriptors or features, in lieu of DFT, to accurately predict catalytic properties, such as adsorption energies. Here, we demonstrate an approach to predict energies using a convolutional neural network-based machine learning model to automatically obtain key features from the electronic density of states (DOS). The model, DOSnet, is evaluated for a diverse set of adsorbates and surfaces, yielding a mean absolute error on the order of 0.1 eV. In addition, DOSnet can provide physically meaningful predictions and insights by predicting responses to external perturbations to the electronic structure without additional DFT calculations, paving the way for the accelerated discovery of materials and catalysts by exploration of the electronic space.
Publisher
Springer Science and Business Media LLC
Subject
General Physics and Astronomy,General Biochemistry, Genetics and Molecular Biology,General Chemistry
Reference68 articles.
1. Zhang, X., Chen, A. & Zhou, Z. High-throughput computational screening of layered and two-dimensional materials. WIREs Comput. Mol. Sci. 9, e1385 (2019).
2. Vergniory, M. G. et al. A complete catalogue of high-quality topological materials. Nature 566, 480–485 (2019).
3. Yan, Q. et al. Solar fuels photoanode materials discovery by integrating high-throughput theory and experiment. Proc. Natl Acad. Sci. USA 114, 3040–3043 (2017).
4. Zhang, Y., Wang, H., Wang, Y., Zhang, L. & Ma, Y. Computer-assisted inverse design of inorganic electrides. Phys. Rev. X 7, 011017 (2017).
5. Jain, A. et al. A high-throughput infrastructure for density functional theory calculations. Comput. Mater. Sci. 50, 2295–2310 (2011).
Cited by
100 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献