Machine Learning of Energetic Material Properties

TL;DR

This paper explores machine learning methods to rapidly predict energetic material properties like detonation energy and velocity, analyzing molecular features and comparing algorithms to enable efficient material screening.

Contribution

It introduces a comprehensive evaluation of various machine learning algorithms and descriptors for predicting energetic material properties with limited training data.

Findings

Non-linear regression models achieve useful accuracy with small datasets.

Different feature descriptors impact prediction accuracy.

Kernel methods and neural networks are effective for property prediction.

Abstract

In this work, we discuss use of machine learning techniques for rapid prediction of detonation properties including explosive energy, detonation velocity, and detonation pressure. Further, analysis is applied to individual molecules in order to explore the contribution of bonding motifs to these properties. Feature descriptors evaluated include Morgan fingerprints, E-state vectors, a custom "sum over bonds" descriptor, and coulomb matrices. Algorithms discussed include kernel ridge regression, least absolute shrinkage and selection operator ("LASSO") regression, Gaussian process regression, and the multi-layer perceptron (a neural network). Effects of regularization, kernel selection, network parameters, and dimensionality reduction are discussed. We determine that even when using a small training set, non-linear regression methods may create models within a useful error tolerance for screening of materials.