EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Predicting Drop‐Weight Impact Sensitivity From Molecular Graphs Using Physics‐Informed Artificial Intelligence

Grant Hutchings, Jack V. Davis, Virginia W. Manner, Marc J. Cawkwell, Frank W. Marrs

Propellants, Explosives, Pyrotechnics · 2026-05 · 51 (5) · 705-713

DOI: 10.1002/prep.70098 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Propellants, Explosives, Pyrotechnics, online erschienen am 08.12.2025. Verfasst von Grant Hutchings und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Los Alamos National Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting the drop‐weight impact sensitivity () of energetic materials accurately and efficiently is a crucial step for the design of safe explosives. Traditional experimental determination of values is costly, time‐consuming, and inherently uncertain. This work presents an approach for predicting of pure molecular explosives directly from two‐dimensional molecular graphs, encoded as simplified molecular‐input line‐entry system (SMILES) strings, using physics‐informed artificial intelligence (AI) models. To address limited experimental drop‐weight impact sensitivity data, we augment our dataset of experimentally measured sensitivities of 625 unique high explosive molecules with physics‐informed synthetic predictions for 1 additional real molecules containing energetic functional groups. Using the existing, publicly available Chemprop software—implementing a message‐passing neural network encoder and feed‐forward neural network predictor—we trained a robust predictive model that improves upon existing models. The proposed approach shows a reduction in predictive error of about 10% over an existing physics‐informed model, which predicts from a hand‐crafted set of descriptors. Our results demonstrate the feasibility and effectiveness of leveraging publicly available chemical databases and physics‐informed models for accelerating the screening of energetic materials based solely on molecular graphs.

Förderung

  • Los Alamos National Laboratory

Zitieren

APA

Hutchings, G., Davis, J. V., Manner, V. W., Cawkwell, M. J., & Marrs, F. W. (2026). Predicting Drop‐Weight Impact Sensitivity From Molecular Graphs Using Physics‐Informed Artificial Intelligence. Propellants, Explosives, Pyrotechnics, 51(5), 705-713. https://doi.org/10.1002/prep.70098

Vancouver

Hutchings G, Davis JV, Manner VW, Cawkwell MJ, Marrs FW. Predicting Drop‐Weight Impact Sensitivity From Molecular Graphs Using Physics‐Informed Artificial Intelligence. Propellants, Explosives, Pyrotechnics. 2026;51(5):705-713. doi:10.1002/prep.70098

BibTeX
@article{Hutchings2026,
  author = {Hutchings, Grant and Davis, Jack V. and Manner, Virginia W. and Cawkwell, Marc J. and Marrs, Frank W.},
  title = {Predicting Drop‐Weight Impact Sensitivity From Molecular Graphs Using Physics‐Informed Artificial Intelligence},
  journal = {Propellants, Explosives, Pyrotechnics},
  year = {2026},
  volume = {51},
  number = {5},
  pages = {705--713},
  doi = {10.1002/prep.70098}
}
Kostenlos starten →