Machine learning predicts electron energies

Abstract

When chemists want to model the structural and electronic properties of atoms or molecules, they often turn to a computational technique called density functional theory (DFT). When DFT fails, chemists use approaches like coupled cluster (CC) or Moller–Plesset perturbation (MP2) theories. These generate more reliable values than DFT does, but they require thousands of times as much computational power as DFT, even for small molecules. Thomas F. Miller and colleagues at California Institute of Technology now demonstrate that machine learning might be the best of both worlds—as accurate as CC or MP2 and no more costly than DFT (J. Chem. Theory Comput. 2018, DOI: 10.1021/acs.jctc.8b00636). The researchers wanted to predict electronic structure correlation energies—a measure of interactions between electrons that helps chemists model how a molecule behaves. Their machine-learning approach predicts these values based on a set of known data. Miller’s group trained its algorithm on localized molecular orbitals of