Which molecular properties determine the impact sensitivity of an explosive? A machine learning quantitative investigation of nitroaromatic explosives.

We decomposed density functional theory charge densities of 53 nitroaromatic molecules into atom-centered electric multipoles using the distributed multipole analysis that provides a detailed picture of the molecular electronic structure. Three electric multipoles, (the charge of the nitro groups), (the total dipole, , polarization, of the nitro groups), (the total electron delocalization of the ring atoms), and the number of explosophore groups (#NO) were selected as features for a comprehensive machine learning (ML) investigation. The target property was the impact sensitivity (cm) values quantified by drop-weight measurements, with a large (, 150 cm) indicating that an explosive is insensitive and . After a preliminary screening of 42 ML algorithms, four were selected based on the lowest root mean square errors: Extra Trees, Random Forests, Gradient Boosting, and AdaBoost. Compared to experimental data, the predicted values of molecules having very different sensitivities for the four algorithms have differences in the range 19-28%. The most important properties for predicting are the electron delocalization in the ring atoms and the polarization of the nitro groups with averaged weights of 39% and 35%, followed by the charge (16%) and number (10%) of nitro groups. A significant result is how the contribution of these properties to depends on their actual sensitivities: for the most sensitive explosives ( up to ∼50 cm), the four properties contribute to reducing , and for intermediate ones (∼50 cm ≲ ≲ 100 cm) #NO and contribute to increasing it and the other two properties to reducing it. For highly insensitive explosives ( ≳ 200 cm), all four properties essentially contribute to increasing it. These results furnish a consistent molecular basis of the sensitivities of known explosives that also can be used for developing safer new ones.