Controlling nonlinear dynamics is a long-standing problem in engineering. Harnessing known physical information to accelerate or constrain stochastic learning pursues new paradigm of scientific machine learning. By linearizing systems, traditional control methods cannot learn features from chaotic data for use control. Here, we introduce Physics-Informed Deep Operator Control (PIDOC), and by en...

The main contribution of this work is the development of a high-dimensional chaos control method that is effective, robust against noise, and easy to implement in experiment. Assuming no knowledge of the model equations, the method achieves control by stabilizing a desired unstable periodic orbit with any number of unstable directions, using small time-dependent perturbations of a single system...

We propose two methods to control spatial chaos in an ecological metapopulation model with long-range dispersal. The metapopulation model consists of local populations living in a patchily distributed habitat. The habitat patches are arranged in a one-dimensional array. In each generation, density-dependent reproduction occurs first in each patch. Then individuals disperse according to a Gaussi...

This paper proposes a TD (temporal difference) and GA (genetic algorithm) based reinforcement (TDGAR) neural learning scheme for controlling chaotic dynamical systems based on the technique of small perturbations. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to fulfill the reinforcement learning task. Structurely, the TDGAR learning system i...