Using Artificial Intelligence to Predict and Validate Nuclear Data

使用人工智能预测和验证核数据

• 批准号: 2462417
• 金额: --
• 依托单位: University of Cambridge
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2020
• 资助国家: 英国
• 起止时间: 2020 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2462417
• 关键词: Using; Artificial; Intelligence; Predict; Validate

Nuclear data, such as cross sections and reaction products, underpins all of nuclear science and technology. Even the most complex and concisely written nuclear data analysis tools can be unreliable and untrustworthy if they use old or un-benchmarked nuclear data. Common problems encountered in nuclear data are missing and conflicting data and large and untrustworthy uncertainties. The best way to tackle these problems is via targeted experiments. However, nuclear data experiments are complex, expensive and the lifecycle time to plan, perform and analyse the results is relatively long. Hence, the current approach involves the use of statistics and theory in conjunction with experiments. To date, the use of artificial intelligence (AI) and machine learning (ML) in the field of nuclear data evaluation has not been fully explored. Hence, this project aims to explore whether or not it would be advantageous to use AI/ML in conjunction with other nuclear data evaluation methods to assist and enhance the evaluation process

核数据，如截面和反应产物，是所有核科学和技术的基础。即使是最复杂和最简洁的核数据分析工具，如果使用旧的或未基准化的核数据，也可能不可靠和不可信。在核数据方面遇到的常见问题是数据缺失和相互矛盾，以及巨大和不可信的不确定性。解决这些问题的最好方法是通过有针对性的实验。然而，核数据实验复杂、昂贵，计划、执行和分析结果的生命周期相对较长。因此，目前的方法涉及使用统计和理论与实验相结合。迄今为止，人工智能（AI）和机器学习（ML）在核数据评估领域的应用尚未得到充分探索。因此，本项目旨在探索将AI/ML与其他核数据评估方法结合使用是否有利，以协助和加强评估过程