Back to Search
Start Over
Improving Density Functional Prediction of Molecular Thermochemical Properties with a Machine-Learning-Corrected Generalized Gradient Approximation
- Source :
- The Journal of Physical Chemistry A. 126:970-978
- Publication Year :
- 2022
- Publisher :
- American Chemical Society (ACS), 2022.
-
Abstract
- The past decade has seen an increasing interest in designing sophisticated density functional approximations (DFAs) by integrating the power of machine learning (ML) techniques. However, application of the ML-based DFAs is often confined to simple model systems. In this work, we construct an ML correction to the widely used Perdew-Burke-Ernzerhof (PBE) functional by establishing a semilocal mapping from the electron density and reduced gradient to the exchange-correlation energy density. The resulting ML-corrected PBE is immediately applicable to any real molecule, and yields significantly improved heats of formation while preserving the accuracy for other thermochemical and kinetic properties. This work highlights the prospect of combining the power of data-driven ML methods with physics-inspired derivations for reaching the heaven of chemical accuracy.
- Subjects :
- Work (thermodynamics)
Electron density
business.industry
Functional prediction
Kinetic energy
Machine learning
computer.software_genre
Power (physics)
Generalized gradient
Simple (abstract algebra)
Density functional theory
Artificial intelligence
Physical and Theoretical Chemistry
business
computer
Mathematics
Subjects
Details
- ISSN :
- 15205215 and 10895639
- Volume :
- 126
- Database :
- OpenAIRE
- Journal :
- The Journal of Physical Chemistry A
- Accession number :
- edsair.doi.dedup.....21d77c27230a19f0232f49e7f39e1329