Zhixiang Zhang , Chao Chen , Yilin Cao , Linyuan Wen , Xiaokai He , Yingzhe Liu
{"title":"描述符在机器学习辅助预测高能材料热分解温度中的适用性:模型评估和离群值分析的启示","authors":"Zhixiang Zhang , Chao Chen , Yilin Cao , Linyuan Wen , Xiaokai He , Yingzhe Liu","doi":"10.1016/j.tca.2024.179717","DOIUrl":null,"url":null,"abstract":"<div><p>Machine learning is an emerging approach to predict thermal decomposition temperature in the field of energetic materials, while an assessment of the descriptor applicability is still lacking. In this work, we have systematically established 5 general descriptor sets for 1091 compounds and combined them with 9 algorithms to construct a suite of predictive models with mean absolute error ranging 41–29 K, which is comparable to the cutting-edge endeavors. Our study emphasizes the significant influence of multi-level structural interactions on the thermal stability and decomposition of energetic materials, contributing insights conducive to the development of corresponding descriptors.</p></div>","PeriodicalId":23058,"journal":{"name":"Thermochimica Acta","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Descriptors applicability in machine learning-assisted prediction of thermal decomposition temperatures for energetic materials: Insights from model evaluation and outlier analysis\",\"authors\":\"Zhixiang Zhang , Chao Chen , Yilin Cao , Linyuan Wen , Xiaokai He , Yingzhe Liu\",\"doi\":\"10.1016/j.tca.2024.179717\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Machine learning is an emerging approach to predict thermal decomposition temperature in the field of energetic materials, while an assessment of the descriptor applicability is still lacking. In this work, we have systematically established 5 general descriptor sets for 1091 compounds and combined them with 9 algorithms to construct a suite of predictive models with mean absolute error ranging 41–29 K, which is comparable to the cutting-edge endeavors. Our study emphasizes the significant influence of multi-level structural interactions on the thermal stability and decomposition of energetic materials, contributing insights conducive to the development of corresponding descriptors.</p></div>\",\"PeriodicalId\":23058,\"journal\":{\"name\":\"Thermochimica Acta\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2024-03-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Thermochimica Acta\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S004060312400056X\",\"RegionNum\":2,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, ANALYTICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thermochimica Acta","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S004060312400056X","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, ANALYTICAL","Score":null,"Total":0}
Descriptors applicability in machine learning-assisted prediction of thermal decomposition temperatures for energetic materials: Insights from model evaluation and outlier analysis
Machine learning is an emerging approach to predict thermal decomposition temperature in the field of energetic materials, while an assessment of the descriptor applicability is still lacking. In this work, we have systematically established 5 general descriptor sets for 1091 compounds and combined them with 9 algorithms to construct a suite of predictive models with mean absolute error ranging 41–29 K, which is comparable to the cutting-edge endeavors. Our study emphasizes the significant influence of multi-level structural interactions on the thermal stability and decomposition of energetic materials, contributing insights conducive to the development of corresponding descriptors.
期刊介绍:
Thermochimica Acta publishes original research contributions covering all aspects of thermoanalytical and calorimetric methods and their application to experimental chemistry, physics, biology and engineering. The journal aims to span the whole range from fundamental research to practical application.
The journal focuses on the research that advances physical and analytical science of thermal phenomena. Therefore, the manuscripts are expected to provide important insights into the thermal phenomena studied or to propose significant improvements of analytical or computational techniques employed in thermal studies. Manuscripts that report the results of routine thermal measurements are not suitable for publication in Thermochimica Acta.
The journal particularly welcomes papers from newly emerging areas as well as from the traditional strength areas:
- New and improved instrumentation and methods
- Thermal properties and behavior of materials
- Kinetics of thermally stimulated processes