Self-Evolving Machine: A Continuously Improving Model for Molecular Thermochemistry
Author(s)
Li, Yi-Pei; Han, Kehang; Grambow, Colin A.; Green Jr, William H![Thumbnail](/bitstream/handle/1721.1/123874/Li_Han_2019_self-evolving_machine.pdf.jpg?sequence=4&isAllowed=y)
DownloadAccepted version (1.411Mb)
Publisher Policy
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
Because collecting precise and accurate chemistry data is often challenging, chemistry data sets usually only span a small region of chemical space, which limits the performance and the scope of applicability of data-driven models. To address this issue, we integrated an active learning machine with automatic ab initio calculations to form a self-evolving model that can continuously adapt to new species appointed by the users. In the present work, we demonstrate the self-evolving concept by modeling the formation enthalpies of stable closed-shell polycyclic species calculated at the B3LYP/6-31G(2df,p) level of theory. By combining a molecular graph convolutional neural network with a dropout training strategy, the model we developed can predict density functional theory (DFT) enthalpies for a broad range of polycyclic species and assess the quality of each predicted value. For the species which the current model is uncertain about, the automatic ab initio calculations provide additional training data to improve the performance of the model. For a test set composed of 2858 cyclic and polycyclic hydrocarbons and oxygenates, the enthalpies predicted by the model agree with the reference DFT values with a root-mean-square error of 2.62 kcal/mol. We found that a model originally trained on hydrocarbons and oxygenates can broaden its prediction coverage to nitrogen-containing species via an active learning process, suggesting that the continuous learning strategy is not only able to improve the model accuracy but is also capable of expanding the predictive capacity of a model to unseen species domains. Keyword: Physical and theoretical chemistry; Thermodynamic modeling; Molecular modeling; Molecules; Thermochemistry enthalpy
Date issued
2019-02Department
Massachusetts Institute of Technology. Department of Chemical EngineeringJournal
Journal of Physical Chemistry A
Publisher
American Chemical Society (ACS)
Citation
Li, Yi-Pei et al. "Self-Evolving Machine: A Continuously Improving Model for Molecular Thermochemistry." Journal of Physical Chemistry, 123, 10 (March 2019) 2142-2152 © 2019 American Chemical Society
Version: Author's final manuscript
ISSN
1089-5639
1520-5215