基于物理信息的贝叶斯机器学习：稀疏且不完美的核数据
Physics Informed Bayesian Machine Learning of Sparse and Imperfect Nuclear Data
AI总结：
本研究通过引入物理信息的贝叶斯方法，利用稀疏且不完整的核数据，提高裂变产物产量能量依赖性的预测精度。
摘要：
现有的数据驱动机器学习面临着缺乏物理知识和数据稀缺的问题。我们将在贝叶斯机器学习中引入物理模型指导的先验知识，以评估独立裂变产物产量的能量依赖性，这对于先进核能应用至关重要，但仅能获取稀疏且不完整的实验数据。信息性先验是学习生成数据后的后验分布。此外，通过转换矩阵将累积裂变产量作为物理约束纳入其中，以提供增强的能量依赖性。我们的工作展示了一种真正的贝叶斯机器学习方法，通过整合全面的物理知识，将稀疏但昂贵的核数据作为强大工具加以利用。
英文摘要：
The prevailing data-driven machine learning has been plagued by the absence of physics knowledge and the scarcity of data. We implement the physics-model informed prior into Bayesian machine learning to evaluate the energy dependence of independent fission product yields, which are crucial for advanced nuclear energy applications but only sparse and imperfect experimental data are available. The informative prior is the posterior after learning the generated data from fission models. Furthermore, cumulative fission yields are included as a physical constraint via a conversion matrix to provide augmented energy dependence. Our work demonstrated a truly Bayesian machine learning by incorporating comprehensive physics knowledges as a powerful tool to exploit the sparse but expensive nuclear data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
