A DFT/machine‐learning hybrid method for the prediction of 3JHCCH couplings

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 3JHH couplings with accuracy comparable or better than the well‐known Altona equation, and it can provide sensible 3JHH predictions in systems not well handled by the Altona equation such as epoxide or cyclopropane rings. 3JHCCH vicinal couplings are predicted through a machine–learning procedure using a combination of geometrical and DFT–obtained electronic parameters.