Data-driven learning of non-autonomous systems

TL;DR

This paper introduces a numerical framework that transforms non-autonomous dynamical systems into piecewise time-invariant systems using neural networks and local parameterizations, enabling effective system recovery and prediction.

Contribution

The paper proposes a novel deep learning-based approach for modeling non-autonomous systems by converting them into piecewise parametric systems with theoretical guarantees.

Findings

Effective recovery of non-autonomous systems demonstrated

Neural network models enable accurate local system predictions

The method outperforms traditional approaches in numerical examples

Abstract

We present a numerical framework for recovering unknown non-autonomous dynamical systems with time-dependent inputs. To circumvent the difficulty presented by the non-autonomous nature of the system, our method transforms the solution state into piecewise integration of the system over a discrete set of time instances. The time-dependent inputs are then locally parameterized by using a proper model, for example, polynomial regression, in the pieces determined by the time instances. This transforms the original system into a piecewise parametric system that is locally time invariant. We then design a deep neural network structure to learn the local models. Once the network model is constructed, it can be iteratively used over time to conduct global system prediction. We provide theoretical analysis of our algorithm and present a number of numerical examples to demonstrate the effectiveness of the method.