气候变化领域集成服务门户(CCPortal): Machine learning active-nematic hydrodynamics

CCPortal

DOI	10.1073/pnas.2016708118
	Machine learning active-nematic hydrodynamics
	Colen J.; Han M.; Zhang R.; Redford S.A.; Lemma L.M.; Morgan L.; Ruijgrok P.V.; Adkins R.; Bryant Z.; Dogic Z.; Gardel M.L.; de Pablo J.J.; Vitelli V.
发表日期	2021
ISSN	00278424
卷号	118 期号:10
英文摘要	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. © 2021 National Academy of Sciences. All rights reserved.
英文关键词	Active turbulence; Biomaterials; Deep learning; Liquid crystals; Topological defects
语种	英语
来源期刊	Proceedings of the National Academy of Sciences of the United States of America
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/180398
作者单位	Department of Physics, University of Chicago, Chicago, IL 60637, United States; James Franck Institute, University of Chicago, Chicago, IL 60637, United States; Pritzer School of Molecular Engineering, University of Chicago, Chicago, IL 60637, United States; Department of Physics, Hong Kong University of Science and Technology, Kowloon, Hong Kong; Graduate Program in Biophysical Sciences, University of Chicago, Chicago, IL 60637, United States; Department of Physics, Brandeis University, Waltham, MA 02454, United States; Department of Physics, University of California, Santa Barbara, CA 92111, United States; Department of Bioengineering, Stanford University, Stanford, CA 94305, United States; Department of Structural Biology, Stanford University Medical Center, Stanford, CA 94305, United States; Center for Molecular Engineering, Argonne National Laboratory, Lemont, IL 60439, United States
推荐引用方式 GB/T 7714	Colen J.,Han M.,Zhang R.,et al. Machine learning active-nematic hydrodynamics[J],2021,118(10).
APA	Colen J..,Han M..,Zhang R..,Redford S.A..,Lemma L.M..,...&Vitelli V..(2021).Machine learning active-nematic hydrodynamics.Proceedings of the National Academy of Sciences of the United States of America,118(10).
MLA	Colen J.,et al."Machine learning active-nematic hydrodynamics".Proceedings of the National Academy of Sciences of the United States of America 118.10(2021).