Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis
In this study, machine learning (ML)-assisted regression modeling was conducted to predict the thermal decomposition temperatures and explore the factors that correlate with the thermal stability of energetic materials (EMs). The modeling was performed based on a dataset consisting of 885 various co...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2024-12-01
|
| Series: | Energetic Materials Frontiers |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266664722300043X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592772836622336 |
|---|---|
| author | Zhi-xiang Zhang Yi-lin Cao Chao Chen Lin-yuan Wen Yi-ding Ma Bo-zhou Wang Ying-zhe Liu |
| author_facet | Zhi-xiang Zhang Yi-lin Cao Chao Chen Lin-yuan Wen Yi-ding Ma Bo-zhou Wang Ying-zhe Liu |
| author_sort | Zhi-xiang Zhang |
| collection | DOAJ |
| description | In this study, machine learning (ML)-assisted regression modeling was conducted to predict the thermal decomposition temperatures and explore the factors that correlate with the thermal stability of energetic materials (EMs). The modeling was performed based on a dataset consisting of 885 various compounds using linear and nonlinear algorithms. The tree-based models established demonstrated acceptable predictive abilities, yielding a low mean absolute error (MAE) of 31°C. By analyzing the dataset through hierarchical classification, this study insightfully identified the factors affecting EMs’ thermal decomposition temperatures, with the overall accuracy improved through targeted modeling. The SHapley Additive exPlanations (SHAP) analysis indicated that descriptors such as BCUT2D, PEOE_VSA, MolLog_P, and TPSA played a significant role, demonstrating that the thermal decomposition process is influenced by multiple factors relating to the composition, electron distribution, chemical bond properties, and substituent type of molecules. Additionally, descriptors such as Carbon_contents and Oxygen_Balance proposed for characterizing EMs showed strong linear correlations with thermal decomposition temperatures. The trends of their SHAP values indicated that the most suitable ranges of Carbon_contents and Oxygen_Balance were 0.2∼0.35 and −65∼−55, respectively. Overall, the study shows the potential of ML models for decomposition temperature prediction of EMs and provides insights into the characteristics of molecular descriptors. |
| format | Article |
| id | doaj-art-1defe2a222ae489986342f64d282249c |
| institution | Kabale University |
| issn | 2666-6472 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Energetic Materials Frontiers |
| spelling | doaj-art-1defe2a222ae489986342f64d282249c2025-01-21T04:13:20ZengKeAi Communications Co. Ltd.Energetic Materials Frontiers2666-64722024-12-0154274282Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysisZhi-xiang Zhang0Yi-lin Cao1Chao Chen2Lin-yuan Wen3Yi-ding Ma4Bo-zhou Wang5Ying-zhe Liu6Xi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; State Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, ChinaXi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; State Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, ChinaXi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; State Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, ChinaXi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; State Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, ChinaXi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; State Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, ChinaState Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; Corresponding author.Xi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; State Key Laboratory of Fluorine & Nitrogen Chemicals, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China; Corresponding author. Xi'an Key Laboratory of Liquid Crystal and Organic Photovoltaic Materials, Xi'an Modern Chemistry Research Institute, Xi'an, 710065, China.In this study, machine learning (ML)-assisted regression modeling was conducted to predict the thermal decomposition temperatures and explore the factors that correlate with the thermal stability of energetic materials (EMs). The modeling was performed based on a dataset consisting of 885 various compounds using linear and nonlinear algorithms. The tree-based models established demonstrated acceptable predictive abilities, yielding a low mean absolute error (MAE) of 31°C. By analyzing the dataset through hierarchical classification, this study insightfully identified the factors affecting EMs’ thermal decomposition temperatures, with the overall accuracy improved through targeted modeling. The SHapley Additive exPlanations (SHAP) analysis indicated that descriptors such as BCUT2D, PEOE_VSA, MolLog_P, and TPSA played a significant role, demonstrating that the thermal decomposition process is influenced by multiple factors relating to the composition, electron distribution, chemical bond properties, and substituent type of molecules. Additionally, descriptors such as Carbon_contents and Oxygen_Balance proposed for characterizing EMs showed strong linear correlations with thermal decomposition temperatures. The trends of their SHAP values indicated that the most suitable ranges of Carbon_contents and Oxygen_Balance were 0.2∼0.35 and −65∼−55, respectively. Overall, the study shows the potential of ML models for decomposition temperature prediction of EMs and provides insights into the characteristics of molecular descriptors.http://www.sciencedirect.com/science/article/pii/S266664722300043XEnergetic compoundMolecular descriptorThermal decomposition temperatureMachine learningFeature analysis |
| spellingShingle | Zhi-xiang Zhang Yi-lin Cao Chao Chen Lin-yuan Wen Yi-ding Ma Bo-zhou Wang Ying-zhe Liu Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis Energetic Materials Frontiers Energetic compound Molecular descriptor Thermal decomposition temperature Machine learning Feature analysis |
| title | Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis |
| title_full | Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis |
| title_fullStr | Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis |
| title_full_unstemmed | Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis |
| title_short | Machine learning-assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis |
| title_sort | machine learning assisted quantitative prediction of thermal decomposition temperatures of energetic materials and their thermal stability analysis |
| topic | Energetic compound Molecular descriptor Thermal decomposition temperature Machine learning Feature analysis |
| url | http://www.sciencedirect.com/science/article/pii/S266664722300043X |
| work_keys_str_mv | AT zhixiangzhang machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis AT yilincao machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis AT chaochen machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis AT linyuanwen machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis AT yidingma machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis AT bozhouwang machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis AT yingzheliu machinelearningassistedquantitativepredictionofthermaldecompositiontemperaturesofenergeticmaterialsandtheirthermalstabilityanalysis |