Machine learning active-nematic hydrodynamics

Abstract

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.

Document Details

Document Type
Pub Defense Publication
Publication Date
Mar 02, 2021
Source ID
10.1073/pnas.2016708118

Entities

People

  • Jonathan Colen
  • Juan J. de Pablo
  • Link Morgan
  • Linnea Lemma
  • Margaret Gardel
  • Ming Han
  • Paul V. Ruijgrok
  • Raymond Adkins
  • Rui Zhang
  • Steven A. Redford
  • Vincenzo Vitelli
  • Zev Bryant
  • Zvonimir Đogić

Organizations

  • Argonne National Laboratory
  • Army Research Office
  • Brandeis University
  • Hong Kong University of Science and Technology
  • Istituto Superiore di Sanità
  • National Science Foundation
  • Stanford University
  • Stanford University Medical Center
  • University of California
  • University of Chicago

Tags

Readers

  • Neural Network Machine Learning.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space