Abstract We demonstrate how machine learning (ML) techniques can be used as an auxiliary tool for nuclear data validation analysis. The output of the ML analysis can inform evaluators and validators on the quality, or lack thereof, of specific nuclear data and benchmark experiments with respect to simulating these experimental benchmark values. To this end, measured and simulated effective neutron multiplication factors, keff, of 875 selected ICSBEP critical assemblies and the latter's sensitivities with respect to nuclear data as well as benchmarks' features (e.g., material nuclide, core geometry) are used as input for a random forest (RF) regression model. The RF is used to encode the complex inter-dependencies between thousands of nuclear data features (i.e., sensitivity profiles and aspects describing the measurements) and 875 simulated and experimental keff values in order to understand what nuclear data features are most informative for predicting bias. The complexity of relationships and high-dimensional space is difficult-to-impossible to search fully using simply expert judgment. As a first proof-of-concept—step, it is demonstrated that this technique is able to correctly trace large discrepancies between simulated and experimental keff back to fabricated shortcomings in nuclear data that were perturbed to simulated keff values. In a second, real-case scenario, step, the RF algorithm is used to validate the ENDF/B-VIII.0 library in comparison to ENDF/B-VII.1 nuclear data. One case is showcased where the chosen ML algorithms highlighted nuclear data (the 19F(n,inl) cross section from 0.4–0.9 MeV) that are shown to be problematic by comparing them to associated differential experimental data and nuclear data from other libraries. In addition to that, it is shown that the RF results point towards poor benchmark experiments and associated underestimated uncertainties (e.g., the PU-SOL-THERM-028 series). However, using the RF algorithm for validating nuclear data with respect to keff is currently limited to pinpointing groups of questionable nuclear data due to the inherent correlations between features introduced by the nuclear data themselves and how keff is simulated. Due to this, we recommend that the ML methods presented be used to augment—rather than replace—the expert knowledge of evaluators and validators.

中文翻译：

---

使用机器学习加强核数据验证分析

摘要 我们展示了机器学习 (ML) 技术如何用作核数据验证分析的辅助工具。ML 分析的输出可以告知评估者和验证者关于模拟这些实验基准值的特定核数据和基准实验的质量或缺乏质量。为此，875 个选定的 ICSBEP 关键组件的测量和模拟有效中子倍增因子 keff 以及后者对核数据和基准特征（例如，材料核素、堆芯几何形状）的敏感性被用作随机森林 (RF) 回归模型。RF 用于编码数千个核数据特征之间复杂的相互依赖关系（即，灵敏度分布和描述测量的方面）和 875 个模拟和实验 keff 值，以了解哪些核数据特征对预测偏差最有用。关系和高维空间的复杂性很难使用简单的专家判断来完全搜索。作为概念验证的第一步，证明该技术能够正确地将模拟和实验 keff 之间的巨大差异追溯到核数据中被模拟 keff 值扰动的捏造缺陷。在第二个真实案例场景中，RF 算法用于验证 ENDF/B-VIII.0 库与 ENDF/B-VII.1 核数据相比。展示了一个案例，其中所选的 ML 算法突出显示了核数据（0.4-0 的 19F(n,inl) 横截面）。9 MeV）通过将它们与来自其他库的相关差异实验数据和核数据进行比较而被证明存在问题。除此之外，RF 结果表明基准实验很差，相关的不确定性被低估（例如，PU-SOL-THERM-028 系列）。然而，由于核数据本身引入的特征与 keff 模拟方式之间的内在相关性，使用 RF 算法验证关于 keff 的核数据目前仅限于查明可疑核数据组。因此，我们建议使用所提供的 ML 方法来增强（而不是替代）评估者和验证者的专业知识。