Published June 28, 2021 | Version v1
Dataset Open

Impact of quantum-chemical metrics on the machine learning prediction of electron density

  • 1. Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland

* Contact person

Description

Machine learning (ML) algorithms have undergone an explosive development impacting every aspect of computational chemistry. To obtain reliable predictions, one needs to maintain the proper balance between the black-box nature of ML frameworks and the physics of the target properties. One of the most appealing quantum-chemical properties for regression models is the electron density, and some of us recently proposed a transferable and scalable model based on the decomposition of the density onto an atom-centered basis set. The decomposition, as well as the training of the model, is at its core a minimization of some loss function, which can be arbitrarily chosen and may lead to results of different quality. Well-studied in the context of density fitting (DF), the impact of the metric on the performance of ML models has not been analyzed yet. In this work, we compare predictions obtained using the overlap and the Coulomb repulsion metrics for both the decomposition and training. As expected, the Coulomb metric used as both the DF and ML loss functions leads to the best results for the electrostatic potential and dipole moments. The origin of this difference lies in the fact that the model is not constrained to predict densities that integrate to the exact number of electrons N. Since an a posteriori correction for the number of electrons decreases the errors, we proposed a modification of the model where N is included directly into the kernel function, which allowed to lower the errors on the test and out-of-sample sets.

Files

File preview

files_description.md

All files

Files (592.2 MiB)

Name Size
md5:98e2f2d971fd7201479d9efa59cd1464
393 Bytes Preview Download
md5:3899245e78516642e4d7d42000171479
592.2 MiB Download
md5:0824eafc3c6564a9fe9c28dd97a027c7
2.6 KiB Preview Download

References

Journal reference
K. R. Briling, A. Fabrizio, C. Corminboeuf, J. Chem. Phys., 155, 024107 (2021), doi: 10.1063/5.0055393

Journal reference
K. R. Briling, A. Fabrizio, C. Corminboeuf, J. Chem. Phys., 155, 024107 (2021)

Preprint
K. R. Briling, A. Fabrizio, C. Corminboeuf, arXiv:2104.12457 (2021)