Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical cal
- PDF / 567,652 Bytes
- 9 Pages / 612 x 792 pts (letter) Page_size
- 16 Downloads / 184 Views
Artificial Intelligence Research Letter
Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations Logan Ward , Data Science and Learning Division, Argonne National Laboratory, Lemont, IL, USA; Department of Computer Science, University of Chicago, Chicago, IL, USA Ben Blaiszik , Data Science and Learning Division, Argonne National Laboratory, Lemont, IL, USA; Globus, University of Chicago, Chicago, IL, USA Ian Foster , Data Science and Learning Division, Argonne National Laboratory, Lemont, IL, USA; Department of Computer Science, University of Chicago, Chicago, IL, USA; Globus, University of Chicago, Chicago, IL, USA Rajeev S. Assary, Joint Center for Energy Storage Research (JCESR), Argonne National Laboratory, Lemont, IL, USA; Materials Science Division, Argonne National Laboratory, Lemont, IL, USA Badri Narayanan, Materials Science Division, Argonne National Laboratory, Lemont, IL, USA; Department of Mechanical Engineering, University of Louisville, Louisville, KY, USA Larry Curtiss, Joint Center for Energy Storage Research (JCESR), Argonne National Laboratory, Lemont, IL, USA; Materials Science Division, Argonne National Laboratory, Lemont, IL, USA Address all correspondence to Logan Ward at [email protected] (Received 1 April 2019; accepted 13 August 2019)
Abstract Recent studies illustrate how machine learning (ML) can be used to bypass a core challenge of molecular modeling: the trade-off between accuracy and computational cost. Here, we assess multiple ML approaches for predicting the atomization energy of organic molecules. Our resulting models learn the difference between low-fidelity, B3LYP, and high-accuracy, G4MP2, atomization energies and predict the G4MP2 atomization energy to 0.005 eV (mean absolute error) for molecules with less than nine heavy atoms (training set of 117,232 entries, test set 13,026) and 0.012 eV for a small set of 66 molecules with between 10 and 14 heavy atoms. Our two best models, which have different accuracy/speed trade-offs, enable the efficient prediction of G4MP2-level energies for large molecules and are available through a simple web interface.
Introduction There are a large range of quantum chemical methods for the calculation of molecular energies, with trade-offs between accuracy and computational cost governed by the approximations used to make the predictions computationally tractable.[1] One type of quantum chemical approach for accurate energy calculations is based on a composite technique in which a sequence of well-defined ab initio molecular orbital calculations is performed to determine the total energy of a given molecular species. Composite methods, such as G4MP2,[2] typically have a mean absolute error (MAE) accuracy of better than 1 kcal/mol (0.04 eV) for test sets of molecules with accurate data. However, at the current time, the size of molecules to which these methods can be applied is limited by the availability of sufficient computational power. Density functional methods are much faster
Data Loading...
