Pathak Jaideep, Hunt Brian, Girvan Michelle, Lu Zhixin, Ott Edward
Institute for Research in Electronics and Applied Physics, University of Maryland, College Park, Maryland 20742, USA.
Department of Physics, University of Maryland, College Park, Maryland 20742, USA.
Phys Rev Lett. 2018 Jan 12;120(2):024102. doi: 10.1103/PhysRevLett.120.024102.
We demonstrate the effectiveness of using machine learning for model-free prediction of spatiotemporally chaotic systems of arbitrarily large spatial extent and attractor dimension purely from observations of the system's past evolution. We present a parallel scheme with an example implementation based on the reservoir computing paradigm and demonstrate the scalability of our scheme using the Kuramoto-Sivashinsky equation as an example of a spatiotemporally chaotic system.
我们展示了使用机器学习从系统过去演化的观测数据中，对任意大空间范围和吸引子维度的时空混沌系统进行无模型预测的有效性。我们提出了一种基于储层计算范式的并行方案及示例实现，并以Kuramoto-Sivashinsky方程作为时空混沌系统的示例，展示了我们方案的可扩展性。
