Inferring activity from the flow field around active colloidal particles using deep learning

Abstract Active colloidal particles create flow around them due to non-equilibrium processes on their surfaces. In this paper, we infer the activity of such colloidal particles from the flow field created by them via deep learning. We first explain our method for one active particle, inferring the $2s$ mode (or the stresslet) and the $3t$ mode (or the source dipole) from the flow field data, along with the position and orientation of the particle. We then apply the method to a system of many active particles. We find excellent agreements between the predictions and the true values of activity. Our method presents a principled way to predict arbitrary activity from the flow field created by active particles.

• Publication year

  2025

• Venue

  Journal of Fluid Mechanics

• Publication date

  2025-05-15

• Fields of study

  Materials Science, Physics

• Identifiers
  DOI 10.1017/jfm.2025.10502arXiv 2505.10270
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• First observation of turbulence in dense algal suspensions

  2025cited by this paper
• Ewald summing irreducible components of flow around active particles.

  2025cited by this paper
• Fluctuating hydrodynamics of an autophoretic particle near a permeable interface

  2023cited by this paper
• Deep learning probability flows and entropy production rates in active matter

  2023cited by this paper
• Dense velocity reconstruction from particle image velocimetry/particle tracking velocimetry using a physics-informed neural network

  2022cited by this paper
• Emergent programmable behavior and chaos in dynamically driven active filaments

  2022cited by this paper
• Learning hydrodynamic equations for active matter from particle simulations and experiments

  2021cited by this paper
• Machine learning for active matter

  2020cited by this paper
• The Fluid Dynamics of Cell Motility

  2020cited by this paper
• Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles.

  2018cited by this paper
• Self-learning how to swim at low Reynolds number

  2018cited by this paper
• Flow-induced phase separation of active particles is controlled by boundary conditions

  2017cited by this paper
• Performing particle image velocimetry using artificial neural networks: a proof-of-concept

  2017cited by this paper
• Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D

  2017cited by this paper
• Deep Learning

  2016cited by this paper
• Spherical squirmers: models for swimming micro-organisms

  2016cited by this paper
• Tensors for Physics

  2015cited by this paper
• Large-scale simulation of steady and time-dependent active suspensions with the force-coupling method

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Green Algae as Model Organisms for Biological Fluid Dynamics.

  2014cited by this paper
• Many-body microhydrodynamics of colloidal particles with active boundary layers

  2014cited by this paper
• Irreducible representations of oscillatory and swirling flows in active soft matter.

  2013cited by this paper
• Deep Sparse Rectifier Neural Networks

  2011cited by this paper
• Fluid dynamics and noise in bacterial cell–cell and cell–surface scattering

  2011cited by this paper
• Oscillatory flows induced by microorganisms swimming in two dimensions.

  2010cited by this paper
• Direct measurement of the flow field around swimming microorganisms.

  2010cited by this paper
• In pursuit of propulsion at the nanoscale

  2010cited by this paper
• Digital Particle Image Velocimetry

  2003cited by this paper
• Localized force representations for particles sedimenting in Stokes flow

  2001cited by this paper
• Wavelet-based image denoising in (digital) particle image velocimetry

  2001cited by this paper
• Boundary Integral and Singularity Methods for Linearized Viscous Flow: Green's functions

  1992cited by this paper
• Particle-Imaging Techniques for Experimental Fluid Mechanics

  1991cited by this paper
• Multilayer feedforward networks are universal approximators

  1989cited by this paper
• Fluid Mechanics of Propulsion by Cilia and Flagella

  1977cited by this paper
• A spherical envelope approach to ciliary propulsion

  1971cited by this paper
• On the squirming motion of nearly spherical deformable bodies through liquids at very small reynolds numbers

  1952cited by this paper
• Distributed under Creative Commons Cc-by 4.0 Scikit-image: Image Processing in Python

  year unknowncited by this paper

• No citing papers are available for this paper.