Learning Hydro-Phoretic Interactions in Active Matter

TL;DR

This paper introduces a novel method combining simulations, symmetry-preserving descriptors, and neural networks to accurately predict hydro-phoretic interactions in active matter, enabling advanced particle-only modeling.

Contribution

It presents a new approach that captures full hydro-phoretic pair interactions directly from particle data, advancing the modeling of collective behavior in active matter.

Findings

First self-contained particle-only simulations with full hydro-phoretic interactions.

Demonstrates accurate prediction of complex hydrodynamic effects.

Enables scalable modeling of large active matter systems.

Abstract

In the quest to understand large-scale collective behavior in active matter, the complexity of hydrodynamic and phoretic interactions remains a fundamental challenge. To date, most works either focus on minimal models that do not (fully) account for these interactions, or explore relatively small systems. The present work develops a generic method that combines high-fidelity simulations with symmetry-preserving descriptors and neural networks to predict hydro-phoretic interactions directly from particle coordinates (effective interactions). This method enables, for the first time, self-contained particle-only simulations and theories with full hydro-phoretic pair interactions.