Parts | Days | Selection | Search | Updates | Downloads | Help

SYAN: Symposium Active nematics: From 2D to 3D

SYAN 1: Active nematics: From 2D to 3D

SYAN 1.5: Invited Talk

Friday, October 1, 2021, 12:15–12:45, Audimax 1

Machine learning active nematic hydrodynamics — •Vincenzo Vitelli — James Franck Institute and Department of physics, University of Chicago

Hydrodynamic theories effectively describe many-body systems out of equilibrium in terms of a few macroscopic parameters. However, such parameters are difficult to determine from microscopic information. Seldom is this challenge more apparent than in active matter, where the hydrodynamic parameters are in fact fields that encode the distribution of energy-injecting microscopic components. In this talk, I will use active nematics to demonstrate that neural networks can map out the spatiotemporal variation of multiple hydrodynamic parameters and forecast the chaotic dynamics of these systems. We analyze biofilament/molecular-motor experiments with microtubule/kinesin and actin/myosin complexes as computer vision problems. Our algorithms can determine how activity and elastic moduli change as a function of space and time, as well as adenosine triphosphate (ATP) or motor concentration both in 2D and 3D. The only input needed is the orientation of the biofilaments and not the coupled velocity field which is harder to access in experiments. We can also forecast the evolution of these chaotic many-body systems solely from image sequences of their past using a combination of autoencoders and recurrent neural networks with residual architecture. In realistic experimental setups for which the initial conditions are not perfectly known, our physics-inspired machine-learning algorithms can surpass deterministic simulations.