Cheap Turns Superior: A Linear Regression-Based Correction Method to Reaction Energy from the DFT

Workflows to predict chemical reaction networks based
on density
functional theory (DFT) are prone to systematic errors in reaction
energy due to the extensive use of cheap DFT exchange–correlation
functionals to limit computational cost. Recently, machine learning-based
models are increasingly applied to mitigate this problem. However,
machine learning models require systems similar to trained data, and
the models often perform poorly for out-of-distribution systems. Here,
we present a simple bond-based correction method that improves the
accuracy of DFT-derived reaction energies. It is based on linear regression,
and the correction terms for each bond are derived from reactions
among the QM9 data set. We demonstrate the effectiveness of this method
with three DFT functionals in three different rungs of Jacob’s
ladder. The simple correction method is effective for all rungs but
especially so for the cheapest PBE functional. Finally, we applied
the correction method to a few reactions with molecules significantly
different from those in the QM9 data set that was used to fit the
linear regression model. Once corrected by this method, we found that
the DFT reaction energies for such out-of-distribution reactions are
within 0.05 eV of the G4MP2 method.