Gou Qiaolin, Liu Jing, Su Haoming, Guo Yanzhi, Chen Jiayi, Zhao Xueyan, Pu Xuemei
College of Chemistry, Sichuan University, Chengdu 610064, China.
Institute of Chemical Materials, China Academy of Engineering Physics, Mianyang 621900, China.
iScience. 2024 Mar 8;27(4):109452. doi: 10.1016/j.isci.2024.109452. eCollection 2024 Apr 19.
High energy and low sensitivity have been the focus of developing new energetic materials (EMs). However, there has been a lack of a quick and accurate method for evaluating the stability of diverse EMs. Here, we develop a machine learning prediction model with high accuracy for bond dissociation energy (BDE) of EMs. A reliable and representative BDE dataset of EMs is constructed by collecting 778 experimental energetic compounds and quantum mechanics calculation. To sufficiently characterize the BDE of EMs, a hybrid feature representation is proposed by coupling the local target bond into the global structure characteristics. To alleviate the limitation of the low dataset, pairwise difference regression is utilized as a data augmentation with the advantage of reducing systematic errors and improving diversity. Benefiting from these improvements, the XGBoost model achieves the best prediction accuracy with R of 0.98 and MAE of 8.8 kJ mol, significantly outperforming competitive models.
高能量和低感度一直是新型含能材料（EMs）研发的重点。然而，目前缺乏一种快速准确的方法来评估多种含能材料的稳定性。在此，我们开发了一种对含能材料的键解离能（BDE）具有高精度的机器学习预测模型。通过收集778种实验含能化合物并进行量子力学计算，构建了一个可靠且具有代表性的含能材料BDE数据集。为了充分表征含能材料的BDE，通过将局部目标键与全局结构特征相结合，提出了一种混合特征表示方法。为了缓解数据集较少的局限性，采用成对差异回归作为数据增强方法，其优点是减少系统误差并提高多样性。受益于这些改进，XGBoost模型实现了最佳预测精度，相关系数R为0.98，平均绝对误差MAE为8.8 kJ/mol，显著优于竞争模型。
