Electron-Density-Informed Molecular Property Prediction Using Surrogate Functionals

Key points

• Machine learning methods are increasingly used to predict chemical properties directly from the molecular structure to bypass the often prohibitive cost of quantum mechanical calculations.1
• Recent work has shown that including the ground-state electron density as input to the machine learning model can improve accuracy in this setting.1
• We show that passing the ground-state density as input to the model, while simultaneously enforcing it to be the minimum of the surrogate functional, surpasses state-of-the-art performance for six out of seven extensive properties of the QM9 dataset.1
• On all extensive properties of both datasets, our approach outperforms models that are informed by the ground-state density but do not enforce the surrogate functional constraints.1

Sources (1)

• [1]Electron-Density-Informed Molecular Property Prediction Using Surrogate Functionals
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 02:27 PM

  This work employs the recent surrogate functional framework originally developed for orbital-free density functional theory and extends it to predicting molecular properties.

  Machine learning methods are increasingly used to predict chemical properties directly from the molecular structure to bypass the often prohibitive cost of quantum mechanical calculations.

Extractive summary: sentences quoted from the sources.