# Machine learning acceleration of simulations of Stokesian suspensions

## TL;DR

This paper introduces a machine learning-augmented reduced model that significantly accelerates simulations of Stokesian suspensions, maintaining accuracy across various geometries and boundary conditions.

## Contribution

It presents a novel ML-based reduced model that replaces computationally expensive parts of fluid simulations, enabling faster and more flexible analysis of particulate Stokesian flows.

## Key findings

- Model is 10 times faster than traditional schemes.
- Accurately reproduces key flow features.
- Generalizes to arbitrary geometries without retraining.

## Abstract

Particulate Stokesian flows describe the hydrodynamics of rigid or deformable particles in Stokes flows. Due to highly nonlinear fluid-structure interaction dynamics, moving interfaces, and multiple scales, numerical simulations of such flows are challenging and expensive. In this Letter, we propose a generic machine-learning-augmented reduced model for these flows. Our model replaces expensive parts of a numerical scheme with multilayer perceptrons. Given the physical parameters of the particle, our model generalizes to arbitrary geometries and boundary conditions without the need to retrain the regression function. It is 10 times faster than a state-of-the-art numerical scheme having the same number of degrees of freedom and can reproduce several features of the flow quite accurately. We illustrate the performance of our model on integral equation formulation of vesicle suspensions in two dimensions.