Deep Learning-Based Increment Theory for Formation Enthalpy Predictions
Authors:
- 11 October 2022
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 126 (41) , 7548-7556
Abstract
Machine learning predictions of molecular thermochemistry, such as formation enthalpy, have been limited for large and complicated species because of the lack of available training data. Such predictions would be important in the prediction of reaction thermodynamics and the construction of kinetic models. Herein, we introduce a graph-based deep learning approach that can separately learn the enthalpy contribution of each atom in its local environment with the effect of the overall molecular structure taken into account. Because this approach follows the additivity scheme of increment theory, it can be generalized to larger and more complicated species not present in the training data. By training the model on molecules with up to 11 heavy atoms, it can predict the formation enthalpy of testing molecules with up to 42 heavy atoms with a mean absolute error of 2 kcal/mol, which is less than half of the error of the conventional increment theory. We expect that this approach will also enable rapid prediction of other extensive properties of large molecules that are difficult to derive from experiments or ab initio calculation.Keywords
All Related Versions
Funding Information
- Ministry of Science and Technology, Taiwan (111-2636-E-002-025)
This publication has 50 references indexed in Scilit:
- ωB97X-V: A 10-parameter, range-separated hybrid, generalized gradient approximation density functional with nonlocal correlation, designed by a survival-of-the-fittest strategyPhysical Chemistry Chemical Physics, 2013
- An expanded calibration study of the explicitly correlated CCSD(T)-F12b method using large basis set standard CCSD(T) atomization energiesThe Journal of Chemical Physics, 2013
- Further benchmarks of a composite, convergent, statistically calibrated coupled-cluster-based approach for thermochemical and spectroscopic studiesMolecular Physics, 2012
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine LearningPhysical Review Letters, 2012
- Chemical accuracy in ab initio thermochemistry and spectroscopy: current strategies and future challengesTheoretical Chemistry Accounts, 2012
- Challenges for Density Functional TheoryChemical Reviews, 2011
- Atom-centered symmetry functions for constructing high-dimensional neural network potentialsThe Journal of Chemical Physics, 2011
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- ESTIMATION OF PURE-COMPONENT PROPERTIES FROM GROUP-CONTRIBUTIONSChemical Engineering Communications, 1987
- Adamantane: Consequences of the Diamondoid StructureChemical Reviews, 1964