Applying machine learning techniques to predict the properties of energetic materials

TL;DR

This paper demonstrates that machine learning models, especially kernel ridge regression with sum over bonds features, can effectively predict properties of energetic molecules from their structures, even with limited data, offering a faster alternative to quantum simulations.

Contribution

It introduces a machine learning approach for predicting energetic material properties from molecular structures, comparing various featurizations and models, and shows promising results with small datasets.

Findings

Kernel ridge regression with sum over bonds features performs best.

Acceptable prediction errors achieved with small datasets.

Adding more data reduces errors but convergence is slow.

Abstract

We present a proof of concept that machine learning techniques can be used to predict the properties of CNOHF energetic molecules from their molecular structures. We focus on a small but diverse dataset consisting of 109 molecular structures spread across ten compound classes. Up until now, candidate molecules for energetic materials have been screened using predictions from expensive quantum simulations and thermochemical codes. We present a comprehensive comparison of machine learning models and several molecular featurization methods - sum over bonds, custom descriptors, Coulomb matrices, bag of bonds, and fingerprints. The best featurization was sum over bonds (bond counting), and the best model was kernel ridge regression. Despite having a small data set, we obtain acceptable errors and Pearson correlations for the prediction of detonation pressure, detonation velocity, explosive energy, heat of formation, density, and other properties out of sample. By including another dataset with 309 additional molecules in our training we show how the error can be pushed lower, although the convergence with number of molecules is slow. Our work paves the way for future applications of machine learning in this domain, including automated lead generation and interpreting machine learning models to obtain novel chemical insights.