Applying machine learning techniques to predict the properties of energetic materials

@article{Elton2018ApplyingML,
  title={Applying machine learning techniques to predict the properties of energetic materials},
  author={Daniel C. Elton and Zois Boukouvalas and Mark S Butrico and Mark D. Fuge and Peter W. Chung},
  journal={Scientific Reports},
  year={2018},
  volume={8}
}
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. [] Key Method 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…
Predicting Energetics Materials' Crystalline Density from Chemical Structure by Machine Learning
TLDR
It is demonstrated that machine learning methods can indeed be used to directly learn the relationship between chemical structures and bulk crystalline properties of molecules, even in the absence of any crystal structure information or quantum mechanical calculations.
Prediction of Thermal Properties of Zeolites through Machine Learning
The use of machine learning for the prediction of physical and chemical properties of crystals based on their structure alone is currently an area of intense research in computational materials
Machine learning transition temperatures from 2D structure.
TLDR
This work extends a molecular representation, or set of descriptors, first developed for quantitative structure-property relationship modeling by Yalkowsky and coworkers known as the Unified Physicochemical Property Estimation Relationships (UPPER), and uses the UPPER descriptors to construct a vector representation for use with machine learning techniques.
Density Prediction Models for Energetic Compounds Merely Using Molecular Topology
TLDR
Three machine learning (ML) models, support vector machine (SVM), random forest (RF), and Graph neural network (GNN), using molecular topology as the only known input are proposed, with high accuracy and lower computational resource cost than the widely accepted DFT-QSPR model.
Prediction of Energetic Material Properties from Electronic Structure Using 3D Convolutional Neural Networks
We develop a convolutional neural network capable of directly parsing the 3D electronic structure of a molecule described by spatial point data for charge density and electrostatic potential
Machine Learning of Energetic Material Properties
TLDR
It is determined that even when using a small training set, non-linear regression methods may create models within a useful error tolerance for screening of materials.
Machine-learning Assisted Screening of Energetic Materials.
TLDR
In this work, machine learning (ML), materials informatics (MI) and thermochemical data are combined to screen potential candidates of energetic materials and the heat of explosion ∆He is used as the target property to directly characterize energetic performance.
Independent Vector Analysis for Molecular Data Fusion: Application to Property Prediction and Knowledge Discovery of Energetic Materials
TLDR
This work proposes a data fusion framework that uses Independent Vector Analysis to uncover underlying complementary information contained in different molecular featurization methods and generates a low dimensional set of features—molecular signatures—that can be used for the prediction of molecular properties and for knowledge discovery.
...
...

References

SHOWING 1-10 OF 83 REFERENCES
Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error.
TLDR
Numerical evidence that ML model predictions deviate from DFT less than DFT (B3LYP) deviates from experiment for all properties is presented and suggests that ML models could be more accurate than hybrid DFT if explicitly electron correlated quantum (or experimental) data were available.
Predicting the Thermodynamic Stability of Solids Combining Density Functional Theory and Machine Learning
We perform a large scale benchmark of machine learning methods for the prediction of the thermodynamic stability of solids. We start by constructing a data set that comprises density functional
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
TLDR
A systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules and is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space.
Accelerating materials property predictions using machine learning
TLDR
It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions.
Machine Learning of Energetic Material Properties
TLDR
It is determined that even when using a small training set, non-linear regression methods may create models within a useful error tolerance for screening of materials.
Intrinsic Bond Energies from a Bonds-in-Molecules Neural Network.
TLDR
This work presents a neural network that predicts the energies of molecules as a sum of intrinsic bond energies, and shows that the network makes predictions of relative bond strengths in good agreement with measured trends and human predictions.
Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations
TLDR
Using DFT data from high-throughput calculations to create faster, surrogate models with machine learning (ML) that can be used to guide new searches and is proposed to accelerate the discovery of new materials by identifying the most promising materials to study with DFT at little additional computational cost.
Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity.
TLDR
This work introduces a hierarchy of representations which meet uniqueness and target similarity criteria, and relies on interatomic many body expansions, as implemented in universal force-fields, including Bonding, Angular (BA), and higher order terms to systematically control target similarity.
Materials Screening for the Discovery of New Half-Heuslers: Machine Learning versus ab Initio Methods.
TLDR
Classification via random forests is used to predict the stability of half-Heusler (HH) compounds, using only experimentally reported compounds as a training set, and an excellent agreement is found between the fraction of compounds classified as stable and the actual fraction of truly stable compounds in the ICSD.
Learning molecular energies using localized graph kernels.
TLDR
This paper uses a random walk graph kernel to measure the similarity of two adjacency matrices that represent a local atomic environment and presents a machine learning approach based on graph theory that naturally incorporates translation, rotation, and permutation symmetries.
...
...