arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.02430cs.LGphysics.comp-ph
收藏

天体物理模拟中基于熵的异常检测的发展

Towards the Development of Entropy-Based Anomaly Detection in an Astrophysics Simulation

Oak Ridge National Laboratory(橡树岭国家实验室)

Drew Schmidt, Bronson Messer, M. Todd Young, Michael Matheson

摘要:

将AI和ML用于科学应用目前是一个非常令人兴奋和充满活力的领域。HPC的大部分兴奋点都集中在ML应用程序上,这些应用程序的分析和分类会产生大量的失败。其他人则试图用数据驱动的代理模型取代科学模拟。但另一个重要的用例是ML的组合应用,以提高模拟精度。为此,我们提出了一个异常的问题,这是从核心坍缩超新星模拟。我们讨论了将机器学习中的异常检测技术应用于科学模拟的策略和早期成功,以及当前的挑战和未来的可能性。

英文摘要:

The use of AI and ML for scientific applications is currently a very exciting and dynamic field. Much of this excitement for HPC has focused on ML applications whose analysis and classification generate very large numbers of flops. Others seek to replace scientific simulations with data-driven surrogate models. But another important use case lies in the combination application of ML to improve simulation accuracy. To that end, we present an anomaly problem which arises from a core-collapse supernovae simulation. We discuss strategies and early successes in applying anomaly detection techniques from machine learning to this scientific simulation, as well as current challenges and future possibilities.

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。

↑