Less is more: a new machine-learning methodology for spatiotemporal systems  

作　　者：Sihan Feng Kang Wang Fuming Wang Yong Zhang Hong Zhao 

机构地区：[1]Department of Physics,Xiamen University,Xiamen 361005 China [2]Lanzhou Center for Theoretical Physics,Key Laboratory of Theoretical Physics of Gansu Province,Lanzhou University,Lanzhou 730000,China

出　　处：《Communications in Theoretical Physics》2022年第5期114-120,共7页理论物理通讯（英文版）

基　　金：support from the NSFC(Grants No.11975189,No.11975190).

摘　　要：Machine learning provides a way to use only portions of the variables of a spatiotemporal system to predict its subsequent evolution and consequently avoids the curse of dimensionality.The learning machines employed for this purpose,in essence,are time-delayed recurrent neural networks with multiple input neurons and multiple output neurons.We show in this paper that such kinds of learning machines have a poor generalization ability to variables that have not been trained with.We then present a one-dimensional time-delayed recurrent neural network for the same aim of model-free prediction.It can be trained on different spatial variables in the training stage but initiated by the time series of only one spatial variable,and consequently possess an excellent generalization ability to new variables that have not been trained on.This network presents a new methodology to achieve finegrained predictions from a learning machine trained on coarse-grained data,and thus provides a new strategy for certain applications such as weather forecasting.Numerical verifications are performed on the Kuramoto coupled oscillators and the Barrio-Varea-Aragon-Maini model.

关 键 词：machine learning spatiotemporal systems prediction dynamical systems time series time-delayed recurrent neural network 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]