Hostname: page-component-cb9f654ff-kl2l2 Total loading time: 0 Render date: 2025-08-29T09:15:35.783Z Has data issue: false hasContentIssue false
  • English
  • Français

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

Published online by Cambridge University Press:  27 August 2025

Aditya Mohapatra ,
Aditya Kumar ,
Mayurakshi Deb ,
Siddharth Dhomkar Open the ORCID record for Siddharth Dhomkar [Opens in a new window]  and
Rajesh Singh Open the ORCID record for Rajesh Singh [Opens in a new window]
Aditya Mohapatra
Affiliation:
Department of Physics, IIT Madras, Chennai 600036, India
Aditya Kumar*
Affiliation:
Department of Physics, IIT Madras, Chennai 600036, India
Mayurakshi Deb
Affiliation:
Department of Physics, IIT Madras, Chennai 600036, India
Siddharth Dhomkar
Affiliation:
Department of Physics, IIT Madras, Chennai 600036, India
Rajesh Singh*
Affiliation:
Department of Physics, IIT Madras, Chennai 600036, India
*
Corresponding authors: Rajesh Singh, rsingh@physics.iitm.ac.in; Aditya Mohapatra, adityamohapatra217@gmail.com
Corresponding authors: Rajesh Singh, rsingh@physics.iitm.ac.in; Aditya Mohapatra, adityamohapatra217@gmail.com
Get access Rights & Permissions [Opens in a new window]

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.

JFM classification

Complex Fluids: Active matter Low-Reynolds-number flows: Boundary integral methods Mathematical Foundations: Machine learning

Information

Type
JFM Rapids
Information
Journal of Fluid Mechanics , Volume 1018 , 10 September 2025 , R1
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Adrian, R.J. 1991 Particle-imaging techniques for experimental fluid mechanics. Annu. Rev. Fluid Mech. 23 (1), 261–304.10.1146/annurev.fl.23.010191.001401CrossRefGoogle Scholar
Baruah, P.V., Padhan, N.B., Maji, B., Pandit, R. & Sharma, P., 2025 Emergent active turbulence and intermittency in dense algal suspensions of Chlamydomonas reinhardtii . arXiv:2503.03834.Google Scholar
Blake, J.R. 1971 A spherical envelope approach to ciliary propulsion. J. Fluid Mech. 46 (1), 199–208.10.1017/S002211207100048XCrossRefGoogle Scholar
Boffi, N.M. & Vanden-Eijnden, E. 2024 Deep learning probability flows and entropy production rates in active matter. Proc. Natl Acad. Sci. 121 (25), e2318106121.10.1073/pnas.2318106121CrossRefGoogle ScholarPubMed
Brennen, C. & Winet, H. 1977 Fluid mechanics of propulsion by cilia and flagella. Annu. Rev. Fluid Mech. 9 (1), 339–398.10.1146/annurev.fl.09.010177.002011CrossRefGoogle Scholar
Cichos, F., Gustavsson, K., Mehlig, B. & Volpe, G. 2020 Machine learning for active matter. Nat. Machine Intell. 2 (2), 94–103.10.1038/s42256-020-0146-9CrossRefGoogle Scholar
Deb, M. & Singh, R. 2025 Ewald summing irreducible components of flow around active particles. J. Chem. Phys. 163 (2), 024901.10.1063/5.0270763CrossRefGoogle ScholarPubMed
Delmotte, B., Keaveny, E.E., Plouraboué, F. & Climent, E. 2015 Large-scale simulation of steady and time-dependent active suspensions with the force-coupling method. J. Comput. Phys. 302, 524–547.10.1016/j.jcp.2015.09.020CrossRefGoogle Scholar
Drescher, K., Dunkel, J., Cisneros, L.H., Ganguly, S. & Goldstein, R.E. 2011 Fluid dynamics and noise in bacterial cell–cell and cell–surface scattering. Proc. Natl Acad. Sci. 108 (27), 10940–10945.10.1073/pnas.1019079108CrossRefGoogle ScholarPubMed
Drescher, K., Goldstein, R.E., Michel, N., Polin, M. & Tuval, I. 2010 Direct measurement of the flow field around swimming microorganisms. Phys. Rev. Lett. 105 (16), 168101.10.1103/PhysRevLett.105.168101CrossRefGoogle ScholarPubMed
Ebbens, S.J. & Howse, J.R. 2010 In pursuit of propulsion at the nanoscale. Soft Matt. 6 (4), 726–738.10.1039/b918598dCrossRefGoogle Scholar
Ghose, S. & Adhikari, R. 2014 Irreducible representations of oscillatory and swirling flows in active soft matter. Phys. Rev. Lett. 112 (11), 118102.10.1103/PhysRevLett.112.118102CrossRefGoogle ScholarPubMed
Glorot, X., Bordes, A. & Bengio, Y. 2011 Deep sparse rectifier neural networks. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, vol. 15 (ed. G. Gordon, D. Dunson & M. Dudík), Proc. Mach. Learn. Res.), pp. 315–323. PMLR.Google Scholar
Goldstein, R.E. 2015 Green algae as model organisms for biological fluid dynamics. Ann. Rev. Fluid Mech. 47, 343–375.10.1146/annurev-fluid-010313-141426CrossRefGoogle ScholarPubMed
Goodfellow, I., Bengio, Y., Courville, A. & Bengio, Y. 2016 Deep Learning. vol. 1. MIT press Cambridge.Google Scholar
Guasto, J.S., Johnson, K.A. & Gollub, J.P. 2010 Oscillatory flows induced by microorganisms swimming in two dimensions. Phys. Rev. Lett. 105 (16), 168102.10.1103/PhysRevLett.105.168102CrossRefGoogle ScholarPubMed
Hannel, M.D., Abdulali, A., O’Brien, M. & Grier, D.G. 2018 Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles. Opt. Express 26 (12), 15221–15231.10.1364/OE.26.015221CrossRefGoogle ScholarPubMed
Hess, S. 2015 Tensors for Physics. Springer.10.1007/978-3-319-12787-3CrossRefGoogle Scholar
Hornik, K., Stinchcombe, M. & White, H. 1989 Multilayer feedforward networks are universal approximators. Neural Networks 2 (5), 359–366.10.1016/0893-6080(89)90020-8CrossRefGoogle Scholar
Kingma, D.P. & Ba, J. 2014 Adam: a method for stochastic optimization. arXiv:1412.6980.Google Scholar
Krishnamurthy, D. & Prakash, M. 2023 Emergent programmable behavior and chaos in dynamically driven active filaments. Proc. Natl Acad. Sci. 120 (28), e2304981120.10.1073/pnas.2304981120CrossRefGoogle ScholarPubMed
Lauga, E. 2020 The Fluid Dynamics of Cell Motility, vol. 62. Cambridge University Press.10.1017/9781316796047CrossRefGoogle Scholar
Lighthill, M.J. 1952 On the squirming motion of nearly spherical deformable bodies through liquids at very small Reynolds numbers. Commun. Pure Appl. Maths 5 (2), 109–118.10.1002/cpa.3160050201CrossRefGoogle Scholar
Marmol, M., Gachon, E. & Faivre, D. 2024 Colloquium: magnetotactic bacteria: from flagellar motor to collective effects. Rev. Mod. Phys. 96 (2), 021001.10.1103/RevModPhys.96.021001CrossRefGoogle Scholar
Maxey, M.R. & Patel, B.K. 2001 Localized force representations for particles sedimenting in Stokes flow. Intl J Multiphase Flow 27 (9), 1603–1626.10.1016/S0301-9322(01)00014-3CrossRefGoogle Scholar
Newby, J.M., Schaefer, A.M., Lee, P.T., Forest, M.G. & Lai, S.K. 2018 Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D. Proc. Natl Acad. Sci. 115 (36), 9026–9031.10.1073/pnas.1804420115CrossRefGoogle ScholarPubMed
Pedley, T.J. 2016 Spherical squirmers: models for swimming micro-organisms. IMA J. Appl. Maths 81 (3), 488–521.10.1093/imamat/hxw030CrossRefGoogle Scholar
Pozrikidis, C. 1992 Boundary Integral and Singularity Methods for Linearized Viscous Flow. Cambridge University Press.10.1017/CBO9780511624124CrossRefGoogle Scholar
Rabault, J., Kolaas, J. & Jensen, A. 2017 Performing particle image velocimetry using artificial neural networks: a proof-of-concept. Meas. Sci. Technol. 28 (12), 125301.10.1088/1361-6501/aa8b87CrossRefGoogle Scholar
Singh, R. 2018 Microhydrodynamics of active colloids [HBNI Th131]. PhD thesis, HBNI.Google Scholar
Singh, R., Ghose, S. & Adhikari, R. 2015 Many-body microhydrodynamics of colloidal particles with active boundary layers. J. Stat. Mech. 2015 (6), P06017.10.1088/1742-5468/2015/06/P06017CrossRefGoogle Scholar
Supekar, R., Song, B., Hastewell, A., Choi, G.P.T., Mietke, A. & Dunkel, J. 2023 Learning hydrodynamic equations for active matter from particle simulations and experiments. Proc. Natl Acad. Sci. 120 (7), e2206994120.10.1073/pnas.2206994120CrossRefGoogle ScholarPubMed
Thutupalli, S., Geyer, D., Singh, R., Adhikari, R. & Stone, H.A. 2018 Flow-induced phase separation of active particles is controlled by boundary conditions. Proc. Natl Acad. Sci. 115 (21), 5403–5408.10.1073/pnas.1718807115CrossRefGoogle ScholarPubMed
Tsang, A.C.H., Tong, P.W., Nallan, S. & Pak, O.S. 2020 Self-learning how to swim at low Reynolds number. Phys. Rev. Fluids 5, 074101.10.1103/PhysRevFluids.5.074101CrossRefGoogle Scholar
van der Walt, S., Schönberger, J.L., Nunez-Iglesias, J., Boulogne, F., Warner, J.D., Yager, N., Gouillart, E. & Yu, T. 2014 scikit-image: image processing in Python. PeerJ 2, e453.10.7717/peerj.453CrossRefGoogle ScholarPubMed
Wang, H., Liu, Y. & Wang, S. 2022 Dense velocity reconstruction from particle image velocimetry/particle tracking velocimetry using a physics-informed neural network. Phys. Fluids 34 (1), 017116.10.1063/5.0078143CrossRefGoogle Scholar
Weng, W.G., Fan, W.C., Liao, G.X. & Qin, J. 2001 Wavelet-based image denoising in (digital) particle image velocimetry. Signal Process. 81 (7), 1503–1512.10.1016/S0165-1684(01)00047-0CrossRefGoogle Scholar
Willert, C.E. & Gharib, M. 1991 Digital particle image velocimetry. Exp. Fluids 10 (4), 181–193.10.1007/BF00190388CrossRefGoogle Scholar