Journal
CHEMICAL ENGINEERING JOURNAL
Volume 426, Issue -, Pages -Publisher
ELSEVIER SCIENCE SA
DOI: 10.1016/j.cej.2021.131304
Keywords
Enthalpy of formation; Molecular thermodynamics; Machine learning; Property estimation
Categories
Funding
- Research Foundation -Flanders (FWO)
- European Research Council under the European Union's Horizon 2020 research and innovation program (ERC) [818607]
Ask authors/readers for more resources
A methodology has been developed for predicting the standard enthalpy of formation of gas-phase molecules using a large database, 3D descriptors, neural network structure, and uncertainty estimation. The predictions have low average deviation from high-accuracy results, at a computational cost lower than low-level theory methods.
A methodology for predicting the standard enthalpy of formation of gas-phase molecules with high speed and accuracy has been developed. This includes the development of: (a) a large, diverse database of molecular structures (consisting of H, C, O, N, and S, and up to 23 heavy atoms), computed at the G3MP2B3 level of chemically accurate theory; (b) a 3D, molecule size-independent descriptor, derived from a radial distribution function containing the convolution of weighted interatomic distances up to 8 angstrom; (c) a neural network structure that is capable to decode 3D structural information and use it to correct enthalpy of formation of lower level theory to that of the high-accuracy method; and (d) a method to estimate uncertainty of predictions. The predictions have about 2.5 kJ/mol (0.6 kcal/mol) average deviation from G3MP2B3 level results, at the computational cost of the B3LYP/6-31G* method. The model is able to extrapolate to increased molecular sizes and to different type of hetero-atoms - although with reduced accuracy but still at significant improvements comparing to low-level theory results. Extrapolations with the neural-network based model does not generate spurious results, which may be attributed to the careful selection of a physically and chemically relevant set of inputs. The methodology may be useful for other computational methods, and for computation of other chemical properties in an automated fashion.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available