Decentralized digital twins of complex dynamical systems

TL;DR

This paper proposes a decentralized digital twin framework for complex dynamical systems using federated learning, enabling collaborative modeling without data sharing, and demonstrating its feasibility for nonlinear spatiotemporal systems.

Contribution

It introduces a novel decentralized digital twin approach based on federated learning for complex dynamical systems, enhancing data privacy and model accuracy.

Findings

Feasibility demonstrated on various dynamical systems.

Federated learning improves model accuracy in decentralized settings.

Potential for application in complex transport phenomena.

Abstract

In this paper, we introduce a decentralized digital twin (DDT) framework for dynamical systems and discuss the prospects of the DDT modeling paradigm in computational science and engineering applications. The DDT approach is built on a federated learning concept, a branch of machine learning that encourages knowledge sharing without sharing the actual data. This approach enables clients to collaboratively learn an aggregated model while keeping all the training data on each client. We demonstrate the feasibility of the DDT framework with various dynamical systems, which are often considered prototypes for modeling complex transport phenomena in spatiotemporally extended systems. Our results indicate that federated machine learning might be a key enabler for designing highly accurate decentralized digital twins in complex nonlinear spatiotemporal systems.