Identifying high energy molecules and predicting their detonation potency using chemometric modelling approaches
Shikha Gupta, Nikita Basant, Kunwar Pal Singh · Combustion Theory and Modelling · 2015
This study reports linear chemometric methods for identification of explosives and prediction of their characteristic parameters using a set of descriptors derived for 244 chemicals. Linear discriminant analysis and k-means clustering methods were developed for discriminating the ideal, non-ideal, and non-explosives, whereas logistic regression and partial least squares regression methods were developed for predicting the detonation parameters. Classification models yielded misclassification of 10.66 and 9.84% in complete data, and regression models predicted detonation velocity and pressure with correlation values of 0.876, 0.861, 0.879 and 0.836 in complete data. These models can be used for predicting the behaviour of new chemicals.