Machine Learning Prediction of Accurate Atomization Energies of Organic Molecules from Low-Fidelity Quantum Chemical Calculations
This enables efficient, accurate energy predictions for organic molecules, benefiting computational chemistry, though it is incremental as it builds on existing ML approaches.
The paper tackles the accuracy-cost tradeoff in molecular modeling by using machine learning to predict high-fidelity atomization energies from low-fidelity calculations, achieving mean absolute errors of 0.005 eV for small molecules and 0.012 eV for larger ones.
Recent studies illustrate how machine learning (ML) can be used to bypass a core challenge of molecular modeling: the tradeoff between accuracy and computational cost. Here, we assess multiple ML approaches for predicting the atomization energy of organic molecules. Our resulting models learn the difference between low-fidelity, B3LYP, and high-accuracy, G4MP2, atomization energies, and predict the G4MP2 atomization energy to 0.005 eV (mean absolute error) for molecules with less than 9 heavy atoms and 0.012 eV for a small set of molecules with between 10 and 14 heavy atoms. Our two best models, which have different accuracy/speed tradeoffs, enable the efficient prediction of G4MP2-level energies for large molecules and are available through a simple web interface.