Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis

Energetic Materials Frontiers, Journal Year: 2023, Volume and Issue: unknown

Published: Sept. 1, 2023

In this study, machine learning (ML)-assisted regression modeling was conducted to predict the thermal decomposition temperatures and explore factors that correlate with stability of energetic materials (EMs). The performed based on a dataset consisting 885 various compounds using linear nonlinear algorithms. tree-based models established demonstrated acceptable predictive abilities, yielding low mean absolute error (MAE) 31°C. By analyzing through hierarchical classification, study insightfully identified affecting EMs' temperatures, overall accuracy improved targeted modeling. SHapley Additive exPlanations (SHAP) analysis indicated descriptors such as BCUT2D, PEOE_VSA, MolLog_P, TPSA played significant role, demonstrating process is influenced by multiple relating composition, electron distribution, chemical bond properties, substituent type molecules. Additionally, Carbon_contents Oxygen_Balance proposed for characterizing EMs showed strong correlations temperatures. trends their SHAP values most suitable ranges were 0.2–0.35 −65 −55, respectively. Overall, shows potential ML temperature prediction provides insights into characteristics molecular descriptors.

Language: Английский

---

Towards the prediction of drug solubility in binary solvent mixtures at various temperatures using machine learning

Journal of Cheminformatics, Journal Year: 2024, Volume and Issue: 16(1)

Published: Oct. 28, 2024

Abstract Drug solubility is an important parameter in the drug development process, yet it often tedious and challenging to measure, especially for expensive drugs or those available small quantities. To alleviate these challenges, machine learning (ML) has been applied predict as alternative approach. However, majority of existing ML research focused on predictions aqueous and/or at specific temperatures, which restricts model applicability pharmaceutical development. bridge this gap, we compiled a dataset 27,000 datapoints, including molecules measured range binary solvent mixtures under various temperatures. Next, panel models were trained with their hyperparameters tuned using Bayesian optimization. The resulting top-performing models, both gradient boosted decision trees (light boosting extreme boosting), achieved mean absolute errors (MAE) 0.33 LogS (S g/100 g) holdout set. These further validated through prospective study, wherein four predicted by then in-house experiments. This study demonstrated that accurately solutes different whose features closely align within (MAE < 0.5 LogS). support future facilitate advancements field, have made code openly available. Scientific contribution Our advances state-of-the-art predicting leveraging uniquely comprehensive dataset. Unlike studies predominantly focus solvents fixed our work enables prediction variety over broad temperature range, providing practical insights modeling realistic applications. along open access significant steps process new molecule discovery, analysis formulation. Graphical

Language: Английский

---

Prediction and Construction of Energetic Materials Based on Machine Learning Methods

Molecules, Journal Year: 2022, Volume and Issue: 28(1), P. 322 - 322

Published: Dec. 31, 2022

Energetic materials (EMs) are the core of weapons and equipment. Achieving precise molecular design efficient green synthesis EMs has long been one primary concerns researchers around world. Traditionally, advanced were discovered through a trial-and-error processes, which required research development (R&D) cycles high costs. In recent years, machine learning (ML) method matured into tool that compliments aids experimental studies for predicting designing EMs. This paper reviews critical process ML methods to discover predict EMs, including data preparation, feature extraction, model construction, performance evaluation. The main ideas basic steps applying analyzed outlined. state-of-the-art about applications in property prediction inverse material is further summarized. Finally, existing challenges strategies coping with proposed.

Language: Английский

---

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

Physical Chemistry Chemical Physics, Journal Year: 2022, Volume and Issue: 24(17), P. 9875 - 9884

Published: Jan. 1, 2022

Energetic materials (EMs) are a group of special energy materials, and it is generally full safety risks costs much to create new EMs. Thus, machine learning (ML)-aided discovery becomes highly desired for EMs, as ML good at risk cost reduction. This work decodes hexanitrobenzene (HNB) 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) two distinctive energetic nitrobenzene compounds by ML, in combination with theoretical calculations. Based on series accurate models density, heat formation, bond dissociation molecular flatness, the predictions show that HNB most among ∼370 000 single benzene ring-containing compounds, while TATB possesses moderate content very high safety, determined experimentally. exhibits significant power presents an instructive procedure using field The ML-aided design efficient synthesis fabrication combined strategy expected accelerate

Language: Английский

---

Force field-inspired transformer network assisted crystal density prediction for energetic materials

Journal of Cheminformatics, Journal Year: 2023, Volume and Issue: 15(1)

Published: July 19, 2023

Abstract Machine learning has great potential in predicting chemical information with greater precision than traditional methods. Graph neural networks (GNNs) have become increasingly popular recent years, as they can automatically learn the features of molecule from graph, significantly reducing time needed to find and build molecular descriptors. However, application machine energetic materials property prediction is still initial stage due insufficient data. In this work, we first curated a dataset 12,072 compounds containing CHON elements, which are traditionally regarded main composition elements materials, Cambridge Structural Database, then implemented refinement our force field-inspired network (FFiNet), through adoption Transformer encoder, resulting (FFiTrNet). After improvement, model outperforms other learning-based GNNs-based models shows its powerful predictive capabilities especially for high-density materials. Our also capability crystal density (i.e. Huang & Massa dataset), will be helpful practical high-throughput screening

Language: Английский

---

Transfer learning for a foundational chemistry model

Chemical Science, Journal Year: 2023, Volume and Issue: 15(14), P. 5143 - 5151

Published: Nov. 24, 2023

Harnessing knowledge from crystal structures yields a model that can predict variety of chemistry-relevant outcomes.

Language: Английский

---

Screening heat-resistant energetic molecules via deep learning and high-throughput computation

Chemical Engineering Journal, Journal Year: 2025, Volume and Issue: unknown, P. 160218 - 160218

Published: Feb. 1, 2025

Language: Английский

---

Applications of Predictive Modeling for Energetic Materials

Challenges and advances in computational chemistry and physics, Journal Year: 2025, Volume and Issue: unknown, P. 339 - 364

Published: Jan. 1, 2025

Language: Английский

---

Predictive Modeling for Energetic Materials

Challenges and advances in computational chemistry and physics, Journal Year: 2025, Volume and Issue: unknown, P. 265 - 310

Published: Jan. 1, 2025

Language: Английский

---

Harnessing machine learning enabled quickly predicting density of CHON molecules for discovering new energetic materials

AIP Advances, Journal Year: 2025, Volume and Issue: 15(4)

Published: April 1, 2025

The application of machine learning in the research and development energetic materials is becoming increasingly widespread for performance prediction inverse design. Many advances have been achieved, especially discovery various new materials. However, main properties such as data acquisition, molecular characterization, limitations objects insufficient. Density, a critical factor influencing detonation materials, difficult to predict with high precision speed at large scale. In this study, techniques are employed density CHNO result explore simultaneously possessing stability. By screening dataset 16 548 candidate molecules, 175 potential high-performance molecules were identified. Among candidates, it noted that molecule velocity 7.328 Km/s pressure 24.48 GPa was which comparable TNT. study shows transformative accelerating novel vital diverse applications optimized expected accelerate next-generation

Language: Английский

---