新 AI 模型可助联合国核监督机构近乎完美评估铀浓缩

由 Lisa Lock 编辑,Andrew Zinin 审阅
本文已按照 Science X 的编辑流程与政策进行审阅。编辑在确保内容可信度的同时,重点标注了以下属性:
添加到首选来源
科学家表示,他们开发出一种新的人工智能系统,能够以极高精度预测铀浓缩水平,同时利用伽马能谱数据识别不同类型的核材料。据沙迦大学的研究人员称,这项基于对三种机器学习模型——XGBoost、CatBoost 和 LightGBM——测试得出的发现,可能为联合国核监督机构提供有价值的新工具,以加强其在《不扩散核武器条约》(NPT)框架下的保障监督。
该研究发表于《核能年鉴》(Annals of Nuclear Energy),发现三种模型在识别铀类别时均表现完美,准确率、精确率、召回率和 F1 分数均达到 100%。
该研究提出了一种双任务机器学习框架,可同时预测铀-235(235U)的浓缩水平,并利用伽马能谱数据对核材料类型进行分类。
这三种梯度提升模型在结构化数据集上进行训练,这些数据集源自 IAEA 对高纯锗(HPGe)探测器输出的基准模拟。
作者写道:“回归部分达到了当前最优性能,其中 XGBoost 的均方误差(MSE)为 0.0019,平均绝对误差(MAE)为 0.0281,决定系数(R²)为 1.0000。LightGBM 和 CatBoost 紧随其后,R² 分别为 0.99999 和 0.9971。”
在三个模型中,XGBoost 在预测富集水平方面表现最强,预测误差几乎可以忽略不计,R² 得分达到完美的 1.0000。
作者报告称,即便是 LightGBM 也达到了几乎相同的准确率,同时计算速度更快。至于 CatBoost,他们指出其表现出色,在较小的数据集上尤为稳健,结果稳定且一致。
事实上,研究人员坚持认为,三个分类模型都取得了满分,在高浓缩铀(HEU)、低浓缩铀(LEU)和天然铀(NU)三个类别上均录得 100% 的准确率、精确率、召回率和 F1 分数。
他们指出,其系统对改进核保障监督至关重要,因为它能对核材料进行更快、更准确的分析,有可能增强联合国核核查人员与监管机构监测国际防扩散协议遵守情况的能力。
“这些结果证实了梯度提升决策树算法在核保障监督这一高度敏感领域中的稳健性与泛化能力,”作者解释道。“所提出的框架展示了机器学习作为决策支持工具,在涉及伽马能谱的特定保障监督活动中的潜力。”
推进联合国核监督机构的保障监督工作
作者的方法论针对两项关键分析任务:(1) 回归,用于预测铀-235(235U)富集度的百分比;(2) 分类,用于将核材料识别为天然铀(NU)、低浓缩铀(LEU)或高浓缩铀(HEU)。
作者指出:“这些目标与涉及无损分析(NDA)的 IAEA 核查活动尤为相关,在这些活动中,核查人员可能需要同时确定定量的浓缩水平和定性的材料分类,以支持保障监督核查与异常检测。”
为模拟现实中的保障监督条件,该研究采用了结构化伽马能谱数据集,这些数据代表使用高纯锗(HPGe)探测器获得的测量结果——HPGe 探测器是同位素分析的行业标准。
所提出的框架采用了三种最先进的梯度提升算法:XGBoost、CatBoost 和 LightGBM,每种算法都因其在结构化数据上的稳健性以及适用于小规模、高维核数据集而被选中。
作者解释说:“这些模型使用工程特征和同位素衍生特征,分别针对回归和分类任务进行独立训练,并依据均方误差(MSE)、平均绝对误差(MAE)、决定系数(R²)、准确率、精确率、召回率和 F1-score 等指标进行评估。”
尽管在 IAEA 保障监督框架内部署之前,还需要在运行条件下进行额外验证,但作者的分析表明,这些模型在基准数据集上展现出极佳的预测性能。
结果显示,XGBoost 是准确度和泛化能力最强的模型。其细粒度的树构建方式,结合稳健的正则化和精心优化的超参数,似乎使其能够捕捉能谱与同位素特征空间中复杂的非线性关系。
在涉及伽马能谱的保障监督应用中,这样的预测精度可为富集度估算提供有价值的决策支持,但前提是需在真实检查条件下进一步验证。
CatBoost 同样表现强劲,不过其残差方差略大。该模型的 MSE 为 2.7757,MAE 为 0.7580,决定系数(R²)为 0.9971。误差较高——尤其是在较低富集度水平上——可能反映出该模型对数据稀疏性的敏感,以及在较小数据集上训练时其 ordered boosting 方法的特性。
尽管如此,CatBoost 仍达到了完美的分类准确率(100%),在所有材料类别上的精确率、召回率和 F1 分数均为 1.00。其对称树架构和稳定的梯度估计使模型即便在类别分布不均衡的情况下,也能有效区分各富集度类别。
LightGBM 兼具出色的计算效率与高预测精度。在回归任务中,其 MSE 为 0.0119,MAE 为 0.0389,R² 为 0.99999,性能已十分接近 XGBoost。
在所需训练时间和内存大幅减少的情况下仍能取得这样的性能,凸显了 LightGBM 在低延迟保障监督应用中的潜力。其分类模型同样达到 100% 的准确率,在 HEU、LEU 和 NU 类别上的精确率、召回率和 F1 分数均保持均衡。
从前景到实践
虽然仍需要在真实核检查条件下进一步验证,但本研究范围仅限于使用具有代表性的铀伽马能谱测量基准数据集,对机器学习算法进行评估。
因此,这些研究结果尚未在 IAEA 保障监督的实际运行条件下接受评估——在那种情形下,核查活动受保障监督协定、针对具体设施的安排、检查目标、测量不确定度要求以及一系列法律和操作考量的约束。
因此,这些结果应被理解为 AI 辅助光谱分析在技术潜力方面的证据,而非保障监督有效性得到提升的证明。
作者强调,未来研究应在具有代表性的实际运行数据集上检验这些方法,并与保障监督领域的相关方合作,以更好地评估其在现有核查框架内的适用性。
Muhammad Zubair 等,《用于核不扩散的 AI 驱动光谱分析以提升保障监督技术的运行就绪度》,Annals of Nuclear Energy(2027)。DOI: 10.1016/j.anucene.2026.112793
这篇报道的作者是谁?
艺术史学士,物质文化硕士。曾任博物馆编辑、急救员和器官移植协调员。自 2021 年起为 Science X 担任编辑。完整简介 →
物理学硕士,有科研经历。长期热衷科学新闻。在 Science X 的编辑工作中发挥关键作用。完整简介 →
引用:新 AI 模型可帮助联合国核监督机构实现近乎完美的铀浓缩评估(2026 年 11 月 9 日),2026 年 11 月 9 日检索自 https://techxplore.com/news/2026-11-ai-nuclear-watchdog-uranium-enrichment.html
本文件受版权保护。除为私人学习或研究目的的合理使用外,未经书面许可,不得复制本文件的任何部分。内容仅供参考。
获取即时摘要文本(要点)
三个梯度提升模型在模拟伽马能谱基准测试中以 100% 准确率对铀类别进行了分类。XGBoost 对铀-235 富集度的预测最准确(MSE 0.0019),其次是 LightGBM。在部署到核保障领域之前,需要在真实检查条件下进行验证。
本摘要由 LLM 自动生成。完整免责声明
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(New AI model could help UN nuclear watchdog achieve near-perfect uranium enrichment assessment)
edited by Lisa Lock, reviewed by Andrew Zinin
This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
Add to Preferred Sources
Credit: Unsplash/CC0 Public Domain
Scientists say they have developed a new artificial intelligence system capable of predicting uranium enrichment levels with extraordinary precision while identifying different types of nuclear material using gamma spectroscopy data. The findings, based on tests of three machine-learning models—XGBoost, CatBoost and LightGBM—could offer the U.N. nuclear watchdog valuable new tools to strengthen its safeguards under the Nuclear Non-Proliferation Treaty (NPT), according to researchers at the University of Sharjah.
The study, published in the Annals of Nuclear Energy, found that all three models performed perfectly in identifying uranium categories, recording 100% accuracy, precision, recall and F1-score.
The research introduces a dual-task machine learning framework that simultaneously predicts uranium-235 (235U) enrichment levels and classifies nuclear material types using gamma spectroscopy data.
The three gradient boosting models were trained on structured datasets derived from IAEA benchmark simulations of high-purity germanium (HPGe) detector outputs.
"The regression component achieved state-of-the-art performance, with XGBoost yielding a mean squared error (MSE) of 0.0019, a mean absolute error (MAE) of 0.0281 and a coefficient of determination (R²) of 1.0000," the authors write. "LightGBM and CatBoost followed with R² values of 0.99999 and 0.9971, respectively."
Among the three models, XGBoost delivered the strongest performance in predicting enrichment levels, achieving an almost negligible prediction error and a perfect R² score of 1.0000.
The authors report that even LightGBM attained nearly identical accuracy while offering faster computation times. As for CatBoost, they note that it demonstrated excellent performance and proved particularly robust with smaller datasets, maintaining stable and consistent results.
In fact, the researchers maintain that all three classification models achieved perfect scores, recording 100% accuracy, precision, recall and F1-score across the highly enriched uranium (HEU), low-enriched uranium (LEU) and natural uranium (NU) categories.
They point out that their system would prove critical to improving nuclear safeguards by providing faster and more accurate analysis of nuclear materials, potentially enhancing the ability of U.N. nuclear inspectors and regulators to monitor compliance with international nonproliferation agreements.
"These results confirm the robustness and generalizability of gradient-boosted decision tree algorithms in the highly sensitive domain of nuclear safeguards," the authors explain. "The proposed framework demonstrates the potential of machine learning as a decision-support tool for selected safeguards activities involving gamma spectroscopy."
Advancing U.N. nuclear watchdog's safeguards
The authors' methodology addresses two critical analytical tasks: (1) regression to predict the percentage of uranium-235 (235U) enrichment, and (2) classification to identify nuclear material as natural uranium (NU), low-enriched uranium (LEU) or highly enriched uranium (HEU).
"These objectives are particularly relevant to those IAEA verification activities that involve nondestructive assay (NDA), where inspectors may need to simultaneously determine quantitative enrichment levels and qualitative material classifications to support safeguards verification and anomaly detection," the authors note.
To simulate real-world safeguards conditions, the study draws on structured gamma spectroscopy datasets representing measurements obtained using high-purity germanium (HPGe) detectors, the industry standard for isotopic assay.
The proposed framework employs three state-of-the-art gradient boosting algorithms, XGBoost, CatBoost and LightGBM, each selected for its robustness on structured data and suitability for small, high-dimensional nuclear datasets.
"These models were trained independently for regression and classification tasks using engineered and isotope-derived features and evaluated across metrics including mean squared error (MSE), mean absolute error (MAE), coefficient of determination (R²), accuracy, precision, recall and F1-score," the authors explain.
Although additional validation under operational conditions would be required before deployment within IAEA safeguards, the authors' analysis demonstrates excellent predictive performance on benchmark datasets.
The results identify XGBoost as the most accurate and generalizable model. Its fine-grained tree construction, combined with robust regularization and carefully optimized hyperparameters, appears to have enabled it to capture complex nonlinear relationships within the spectral and isotopic feature space.
In safeguards applications involving gamma spectroscopy, such predictive accuracy could provide valuable decision support for enrichment estimation, subject to further validation under real-world inspection conditions.
CatBoost also delivered strong performance, although it exhibited slightly greater residual variance. The model achieved an MSE of 2.7757, MAE of 0.7580 and a coefficient of determination (R²) of 0.9971. The higher error, particularly at lower enrichment levels, may reflect the model's sensitivity to data sparsity and the characteristics of its ordered boosting approach when trained on smaller datasets.
Nevertheless, CatBoost attained perfect classification accuracy (100%), achieving precision, recall and F1-scores of 1.00 across all material categories. Its symmetric tree architecture and stable gradient estimation enabled the model to distinguish effectively between enrichment classes despite imbalances in class distribution.
LightGBM combined exceptional computational efficiency with high predictive accuracy. In the regression task, it achieved an MSE of 0.0119, MAE of 0.0389 and an R² score of 0.99999, closely approaching the performance of XGBoost.
Achieving such performance while requiring substantially less training time and memory underscores LightGBM's potential for use in low-latency safeguards applications. The classification model likewise achieved 100% accuracy, with balanced precision, recall and F1-score across HEU, LEU and NU categories.
From promise to practice
While further validation under real-world nuclear inspection conditions remains necessary, the scope of the study is limited to the evaluation of machine-learning algorithms using benchmark gamma spectroscopy datasets representative of uranium gamma spectroscopy measurements.
As a result, the findings have yet to be assessed under the operational realities of IAEA safeguards, where verification activities are governed by safeguards agreements, facility-specific arrangements, inspection objectives, measurement uncertainty requirements and a range of legal and operational considerations.
Consequently, the results should be interpreted as evidence of the technical potential of AI-assisted spectral analysis rather than as proof of enhanced safeguards effectiveness.
The authors emphasize that future research should test these methods on representative operational datasets and in collaboration with safeguards stakeholders to better evaluate their suitability within existing verification frameworks.
Muhammad Zubair et al., AI-powered spectral analysis for nuclear non-proliferation to enhance operational readiness of safeguards technologies, Annals of Nuclear Energy (2027). DOI: 10.1016/j.anucene.2026.112793
Who's behind this story?
BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →
Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →
Citation: New AI model could help UN nuclear watchdog achieve near-perfect uranium enrichment assessment (2026, November 9) retrieved 9 November 2026 from https://techxplore.com/news/2026-11-ai-nuclear-watchdog-uranium-enrichment.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
Get Instant Summarized Text (Gist)
Three gradient-boosting models classified uranium categories with 100% accuracy on simulated gamma spectroscopy benchmarks. XGBoost predicted uranium-235 enrichment most accurately (MSE 0.0019), followed by LightGBM. Validation under real-world inspection conditions is required before deployment in nuclear safeguards.
This summary was automatically generated using LLM. Full disclaimer
This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.
原文为英文,正文由自动抓取并保留原文。
原文发布于 TechXplore(New AI model could help UN nuclear watchdog achieve near-perfect uranium enrichment assessment),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。
