用于稳健预测热稳定性的差分学习方法及其在含能材料中的应用
Differential Learning for Robust Prediction of Thermal Stability with Application to Energetic Materials
- Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
- Texas Tech University（德克萨斯理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对含能材料热稳定性预测受实验误差干扰的问题，提出差分学习方法训练消息传递神经网络预测分子间热稳定性相对差值，准确率超85%且泛化性好，为含噪声实验数据建模提供实用方案。
AI中文摘要：
在含能材料的设计中，预测其处理和储存过程中的热稳定性对于构建安全可靠的材料至关重要。然而，由于不同实验室的实验方案和分析方法存在差异，实验测量结果差异显著，这使得训练可靠的预测模型变得十分困难。我们通过差分学习方法解决这一挑战：不直接预测绝对分解温度，而是训练消息传递神经网络（Message Passing Neural Networks）来预测成对分子间的相对差值。该方法降低了对系统性实验误差的敏感性，在对化合物按热稳定性排序时准确率超过85%，在同一异质数据集上的表现优于传统回归方法。为了理解这些预测的驱动因素，我们将神经网络模型与从头算（ab initio）计算及化学信息学软件衍生描述符构建的可解释替代模型进行对比，分析发现键解离焓是热稳定性排序的关键决定因素，为热分解的复杂化学过程提供了进一步见解。差分学习框架可在不同模型架构间泛化，从图神经网络到经典的基于描述符的方法均适用。我们的结果表明，学习相对属性而非绝对值为含噪声实验数据建模提供了实用解决方案，可直接应用于热稳定性预测为安全方案提供依据的材料设计领域。
英文摘要：
Predicting thermal stability during handling and storage is essential for the design of safe and reliable energetic materials. However, experimental measurements vary significantly across laboratories due to differences in protocols and analysis methods, making it difficult to train reliable predictive models. We address this challenge through differential learning. Rather than predicting absolute decomposition temperatures, we instead train message passing neural networks to predict relative differences between pairs of molecules. This approach reduces sensitivity to systematic experimental errors and achieves >85% accuracy in ranking compounds by thermal stability, outperforming conventional regression methods on the same heterogeneous dataset. To understand what drives these predictions, we compare neural network models with interpretable alternatives built from descriptors derived from ab initio calculations and cheminformatics software. This analysis identifies bond dissociation enthalpy as a key determinant of thermal stability rankings, providing further insight into the complex chemistry of thermal decomposition. The differential learning framework generalizes across model architectures, from graph neural networks to classical descriptor-based approaches. Our results demonstrate that learning relative properties rather than absolute values offers a practical solution for modeling noisy experimental data, with direct applications in materials design where thermal stability predictions inform safety protocols.
