A DFT/machine-learning hybrid method for the prediction of3JHCCHcouplings

A machine learning model for the prediction of vicinal proton-proton couplings has been developed based on a hybrid representation that includes geometrical and electronic parameters derived from natural bond orbital (NBO) analysis of low-level BLYP/STO-3G computations. The model can predict(3)J(HH)couplings with accuracy comparable or better than the well-known Altona equation, and it can provide sensible(3)J(HH)predictions in systems not well handled by the Altona equation such as epoxide or cyclopropane rings.

Automated summary

A machine learning model has been developed for predicting vicinal proton-proton couplings with accuracy comparable or better than the Altona equation, especially in systems like epoxide or cyclopropane rings where the Altona equation may not perform well.