Prospects of federated machine learning in fluid dynamics

TL;DR

This paper explores federated machine learning as a decentralized approach for fluid dynamics, enabling local data processing and collaborative model building without data centralization, promising advancements in digital twin technology.

Contribution

It introduces a federated learning framework for fluid dynamics, demonstrating its feasibility for creating accurate, decentralized predictive models and digital twins.

Findings

Federated learning can effectively reconstruct spatiotemporal fluid fields.

Decentralized models achieve comparable accuracy to centralized ones.

Potential for scalable, privacy-preserving fluid dynamics simulations.

Abstract

Physics-based models have been mainstream in fluid dynamics for developing predictive models. In recent years, machine learning has offered a renaissance to the fluid community due to the rapid developments in data science, processing units, neural network based technologies, and sensor adaptations. So far in many applications in fluid dynamics, machine learning approaches have been mostly focused on a standard process that requires centralizing the training data on a designated machine or in a data center. In this letter, we present a federated machine learning approach that enables localized clients to collaboratively learn an aggregated and shared predictive model while keeping all the training data on each edge device. We demonstrate the feasibility and prospects of such decentralized learning approach with an effort to forge a deep learning surrogate model for reconstructing spatiotemporal fields. Our results indicate that federated machine learning might be a viable tool for designing highly accurate predictive decentralized digital twins relevant to fluid dynamics.