Decoding hexanitrobenzene (HNB) and 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) as two distinctive energetic nitrobenzene compounds by machine learning

Abstract

Energetic materials (EMs) are a group of special energy materials, and it is generally full of safety risk and generally costs much to create new EMs. Thus, the machine learning...

Recent advances in studying the nonnegligible role of noncovalent interactions in various types of energetic molecular crystals

“…Recently, Zhang's group has reported a combination study of theoretical calculations and machine learning and found that moderate energy content and extremely high safety of TATB basically stem from its face-to-face π-stacking mode that facilitates enhanced molecular stability compared to other ∼370 000 000 single ring-containing aromatic compounds. 82…”

Simple rule for linking atoms to construct high energy isomers

“…5 Nowadays, the big data-driven molecular design becomes increasingly popular with the further enhancement of efficiency, and numerous fuel molecules and energetic molecules with excellent properties have been designed and synthesized. 6–9…”

“…For example, the combination of the SMILES codes of various groups and frames enables us to produce a large number of molecules in no time for subsequent high throughput calculations. 6 In general, a larger part of the combination is ineffective, i.e. , most of these molecules cannot be potential candidates.…”

General Graph Neural Network-Based Model To Accurately Predict Cocrystal Density and Insight from Data Quality and Feature Representation

“…However, due to the high requirement of DFT to the computation resource, it is infeasible to use DFT to explore huge unknown compound space. Recently, machine learning (ML), as a key technique of artificial intelligence, has been increasingly popular in accelerating the discovery of novel functional materials and pharmaceutical materials, − including the cocrystal materials. It is noted that previous ML applications on the cocrystals mainly focused on the classification task to screen a possible pair of coformers to form cocrystals. ,− However, successful cocrystal design requires not only to quickly screen the potential coformer pair but also to know whether the cocrystal can achieve desired properties.…”