Machine learning active-nematic hydrodynamics

Abstract

Significance Artificial intelligence holds considerable promise for transforming quantitative modeling in materials science. We illustrate this potential by developing machine-learning models of a paradigmatic class of biomaterials called active nematics. These hybrid materials can be viewed as artificial muscles composed of biological fibers and molecular motors. Here, the macroscopic coefficients characterizing energy injection by motors and material elasticity are not constant. They are unknown functions of space and time that we extract directly from experiments using neural networks. Our physics-inspired machine-learning algorithms can also forecast the evolution of these complex materials simply using image sequences from their past, without any knowledge of the governing dynamics. 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. Here, we 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. 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. Our study paves the way for artificial-intelligence characterization and control of coupled chaotic fields in diverse physical and biological systems, even in the absence of knowledge of the underlying dynamics.