Machine Learning Forecasting of Active Nematics

TL;DR

This paper introduces a deep learning method using ConvLSTM to predict the complex dynamics of active nematics, surpassing traditional hydrodynamic models by capturing detailed experimental and simulated behaviors.

Contribution

We developed a data-driven deep learning approach with ConvLSTM to forecast active nematic dynamics, improving prediction accuracy over traditional models.

Findings

Successfully predicted experimental active nematic behaviors

Achieved accurate forecasts on simulation data

Demonstrated effectiveness of deep learning in complex fluid dynamics

Abstract

Active nematics are a class of far-from-equilibrium materials characterized by local orientational order of force-generating, anisotropic constitutes. Traditional methods for predicting the dynamics of active nematics rely on hydrodynamic models, which accurately describe idealized flows and many of the steady-state properties, but do not capture certain detailed dynamics of experimental active nematics. We have developed a deep learning approach that uses a Convolutional Long-Short-Term-Memory (ConvLSTM) algorithm to automatically learn and forecast the dynamics of active nematics. We demonstrate our purely data-driven approach on experiments of 2D unconfined active nematics of extensile microtubule bundles, as well as on data from numerical simulations of active nematics.