从数据中学习动力学不稳定性的切空间
Learning the Tangent Space of Dynamical Instabilities from Data
摘要:
对于一个大类的动力系统,最优时间相关(OTD)模式,一组可变形的正交切向量,跟踪方向的不稳定性沿任何轨迹,被称为“逐点”依赖于系统的状态的吸引子,而不是在历史上的轨迹。我们利用神经网络的力量,直接从数据中学习这种从相空间到OTD空间的“逐点”映射。学习过程的结果是与相空间中的最强不稳定性相关联的方向的制图。数据驱动的预测和控制动力学不稳定性的影响进行了讨论。
英文摘要:
For a large class of dynamical systems, the optimally time-dependent (OTD) modes, a set of deformable orthonormal tangent vectors that track directions of instabilities along any trajectory, are known to depend "pointwise" on the state of the system on the attractor, and not on the history of the trajectory. We leverage the power of neural networks to learn this "pointwise" mapping from phase space to OTD space directly from data. The result of the learning process is a cartography of directions associated with strongest instabilities in phase space. Implications for data-driven prediction and control of dynamical instabilities are discussed.
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。