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.
Entropy Causal Graphs for Multivariate Time Series Anomaly Detection
Institute of Innovation, Science and Sustainability(创新、科学与可持续性研究所);Federation University Australia, Australia and CSIRO's Data61(联邦大学澳大利亚分校和CSIRO的数据61);Federation University Australia(联邦大学澳大利亚分校);RMIT University(皇家墨尔本理工学院)
Weakly-Supervised Anomaly Detection in the Milky Way
Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);University of California, Berkeley(加州大学伯克利分校);Rutgers University(罗格斯大学);SLAC National Accelerator Laboratory(SLAC国家加速器实验室);Bosch Research North America(博世北美研究院)
Singapore University of Technology & Design(新加坡科技设计大学);Bonn-Aachen International Center for Information Technology(波恩-亚琛信息技术国际中心);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);Technical University of Kaiserslautern(凯泽斯劳滕工业大学);Technical University of Berlin(柏林工业大学);Korea University(高丽大学)
Federal University of Rio Grande do Sul - UFRGS(鲁西南联邦大学);Federal University of Santa Maria - UFSM(圣玛丽亚联邦大学);Federal University of Rio Grande - FURG(里奥格兰德联邦大学)