{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T21:53:52Z","timestamp":1768773232843,"version":"3.49.0"},"reference-count":58,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T00:00:00Z","timestamp":1697760000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T00:00:00Z","timestamp":1697760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100005683","name":"Kyoto University","doi-asserted-by":"crossref","award":["SPIRITS 2020"],"award-info":[{"award-number":["SPIRITS 2020"]}],"id":[{"id":"10.13039\/501100005683","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"crossref","award":["Kakenhi 20K03786"],"award-info":[{"award-number":["Kakenhi 20K03786"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We develop a probabilistic Stokes flow framework, using physics informed Gaussian processes, which can be used to solve both forward\/inverse flow problems with missing and\/or noisy data. The physics of the problem, specified by the Stokes and continuity equations, is exactly encoded into the inference framework. Crucially, this means that we do not need to explicitly solve the Poisson equation for the pressure field, as a physically meaningful (divergence-free) velocity field will automatically be selected. We test our method on a simple pressure driven flow problem, i.e. flow through a sinusoidal channel, and compare against standard numerical methods (Finite Element and Direct Numerical Simulations). We obtain excellent agreement, even when solving inverse problems given only sub-sampled velocity data on low dimensional sub-spaces (i.e. 1 component of the velocity on 1<jats:italic>D<\/jats:italic> domains to reconstruct 2<jats:italic>D<\/jats:italic> flows). The proposed method will be a valuable tool for analyzing experimental data, where noisy\/missing data is the norm.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad0286","type":"journal-article","created":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T22:39:30Z","timestamp":1697063970000},"page":"045013","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Stokesian processes : inferring Stokes flows using physics-informed Gaussian processes"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6132-6862","authenticated-orcid":true,"given":"John J","family":"Molina","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenta","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0017-7669","authenticated-orcid":false,"given":"Takashi","family":"Taniguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2023,10,20]]},"reference":[{"key":"mlstad0286bib1","author":"Pozrikidis","year":"1992"},{"key":"mlstad0286bib2","author":"Pozrikidis","year":"2002"},{"key":"mlstad0286bib3","author":"Logg","year":"2012"},{"key":"mlstad0286bib4","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1146\/annurev.fl.20.010188.000551","article-title":"Stokesian dynamics","volume":"20","author":"Brady","year":"1988","journal-title":"Annu. Rev. Fluid Mech."},{"key":"mlstad0286bib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109951","article-title":"NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations","volume":"426","author":"Jin","year":"2021","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib6","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1007\/s10409-021-01148-1","article-title":"Physics-informed neural networks (PINNs) for fluid mechanics: a review","volume":"37","author":"Cai","year":"2021","journal-title":"Acta Mech. Sin."},{"key":"mlstad0286bib7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MCSE.2023.3264340","article-title":"Emerging trends in machine learning for computational fluid dynamics","volume":"24","author":"Vinuesa","year":"2022","journal-title":"Comput. Sci. Eng."},{"key":"mlstad0286bib8","article-title":"Machine learning for partial differential equations","author":"Brunton","year":"2023"},{"key":"mlstad0286bib9","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1016\/j.jcp.2018.08.029","article-title":"DGM: A deep learning algorithm for solving partial differential equations","volume":"375","author":"Sirignano","year":"2018","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib10","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1126\/science.aaw4741","article-title":"Hidden fluid mechanics: learning velocity and pressure fields from flow visualizations","volume":"367","author":"Raissi","year":"2020","journal-title":"Science"},{"key":"mlstad0286bib11","article-title":"Reconstructing velocity and pressure from sparse noisy particle tracks using physics-informed neural networks","author":"Di Leoni","year":"2022"},{"key":"mlstad0286bib12","doi-asserted-by":"publisher","first-page":"7760","DOI":"10.3390\/en14227760","article-title":"Physics-based deep learning for flow problems","volume":"14","author":"Sun","year":"2021","journal-title":"Energies"},{"key":"mlstad0286bib13","doi-asserted-by":"publisher","first-page":"eabi8605","DOI":"10.1126\/sciadv.abi8605","article-title":"Learning the solution operator of parametric partial differential equations with physics-informed DeepONets","volume":"7","author":"Wang","year":"2021","journal-title":"Sci. Adv."},{"key":"mlstad0286bib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110296","article-title":"DeepM and Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks","volume":"436","author":"Cai","year":"2021","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib15","article-title":"Neural operator: learning maps between function spaces","author":"Kovachki","year":"2021"},{"key":"mlstad0286bib16","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","article-title":"Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators","volume":"3","author":"Lu","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstad0286bib17","article-title":"Stacked generative machine learning models for fast approximations of steady-state Navier-Stokes equations","author":"Wang","year":"2021"},{"key":"mlstad0286bib18","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acd168","article-title":"Applications of physics informed neural operators","volume":"4","author":"Rosofsky","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad0286bib19","author":"Neal","year":"1996","edition":"ed"},{"key":"mlstad0286bib20","article-title":"A survey of uncertainty in deep neural networks","author":"Gawlikowski","year":"2022"},{"key":"mlstad0286bib21","author":"Rasmussen","year":"2005"},{"key":"mlstad0286bib22","author":"Murphy","year":"2012"},{"key":"mlstad0286bib23","first-page":"pp 323","article-title":"Physics-informed learning machines for partial differential equations: Gaussian processes versus neural networks","author":"Pang","year":"2020","edition":"ed"},{"key":"mlstad0286bib24","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.jcp.2018.02.039","article-title":"Active learning of constitutive relation from mesoscopic dynamics for macroscopic modeling of non-Newtonian flows","volume":"363","author":"Zhao","year":"2018","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033107","article-title":"Learning the constitutive relation of polymeric flows with memory","volume":"2","author":"Seryo","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstad0286bib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.110069","article-title":"Active- and transfer-learning applied to microscale-macroscale coupling to simulate viscoelastic flows","volume":"427","author":"Zhao","year":"2020","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib27","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1678\/rheology.49.97","article-title":"Select applications of bayesian data analysis and machine learning to flow problems","volume":"49","author":"Seryo","year":"2021","journal-title":"Nihon Reoroji Gakkaishi"},{"key":"mlstad0286bib28","doi-asserted-by":"publisher","DOI":"10.1063\/5.0156272","article-title":"Machine-learned constitutive relations for multi-scale simulations of well-entangled polymer melts","volume":"35","author":"Miyamoto","year":"2023","journal-title":"Phys. Fluids"},{"key":"mlstad0286bib29","doi-asserted-by":"publisher","first-page":"A172","DOI":"10.1137\/17M1120762","article-title":"Numerical gaussian processes for time-dependent and nonlinear partial differential equations","volume":"40","author":"Raissi","year":"2018","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstad0286bib30","article-title":"Symplectic spectrum Gaussian processes: learning Hamiltonians from noisy and sparse data","author":"Tanaka","year":"2022"},{"key":"mlstad0286bib31","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.jcp.2017.11.039","article-title":"Hidden physics models: machine learning of nonlinear partial differential equations","volume":"357","author":"Raissi","year":"2018","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib32","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1016\/j.jcp.2017.01.060","article-title":"Inferring solutions of differential equations using noisy multi-fidelity data","volume":"335","author":"Raissi","year":"2017","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib33","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1016\/j.jcp.2017.07.050","article-title":"Machine learning of linear differential equations using Gaussian processes","volume":"348","author":"Raissi","year":"2017","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib34","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2016.0751","article-title":"Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling","volume":"473","author":"Perdikaris","year":"2017","journal-title":"Proc. R. Soc. A"},{"key":"mlstad0286bib35","article-title":"Physics-informed gaussian process regression generalizes linear PDE solvers","author":"Pf\u00f6rtner","year":"2022"},{"key":"mlstad0286bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113097","article-title":"Enforcing boundary conditions on physical fields in Bayesian inversion","volume":"367","author":"Michel\u00e9n Str\u00f6fer","year":"2020","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"mlstad0286bib37","article-title":"Gaussian process priors for systems of linear partial differential equations with constant coefficients","author":"H\u00e4rk\u00f6nen"},{"key":"mlstad0286bib38","first-page":"pp 370","article-title":"DeepKernel Learning","author":"Wilson","year":"2016"},{"key":"mlstad0286bib39","first-page":"pp 1206","article-title":"The promises and pitfalls of deep kernel learning","author":"Ober","year":"2021"},{"key":"mlstad0286bib40","author":"Petersen","year":"2012"},{"key":"mlstad0286bib41","author":"Jaynes","year":"2003"},{"key":"mlstad0286bib42","author":"Sivia","year":"2006"},{"key":"mlstad0286bib43","author":"Happel","year":"1983","edition":"2nd edn"},{"key":"mlstad0286bib44","author":"Batchelor","year":"2000","edition":"2nd edn"},{"key":"mlstad0286bib45","author":"Landau","year":"2011","edition":"2nd edn"},{"key":"mlstad0286bib46","author":"von der Linden","year":"2014"},{"key":"mlstad0286bib47","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1023\/A:1006575028391","article-title":"Stokes flow in a slowly varying two-dimensional periodic pore","volume":"26","author":"Kitanidis","year":"1997","journal-title":"Transp. Porous Media"},{"key":"mlstad0286bib48","article-title":"Stokes flow between sinusoidal walls","volume":"vol 36","author":"Bizzarri","year":"2002","edition":"ed"},{"key":"mlstad0286bib49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3524456","article-title":"Construction of arbitrary order finite element degree-of-freedom maps on polygonal and polyhedral cell meshes","volume":"48","author":"Scroggs","year":"2022","journal-title":"ACM Trans. Math. Softw."},{"key":"mlstad0286bib50","doi-asserted-by":"publisher","first-page":"3982","DOI":"10.21105\/joss.03982","article-title":"Basix: a runtime finite element basis evaluation library","volume":"7","author":"Scroggs","year":"2022","journal-title":"J. Open Source Softw."},{"key":"mlstad0286bib51","doi-asserted-by":"publisher","first-page":"4226","DOI":"10.1039\/D0SM02210A","article-title":"Smoothed profile method for direct numerical simulations of hydrodynamically interacting particles","volume":"17","author":"Yamamoto","year":"2021","journal-title":"Soft Matter"},{"key":"mlstad0286bib52","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1016\/j.jcp.2008.11.006","article-title":"Smoothed profile method for particulate flows: error analysis and simulations","volume":"228","author":"Luo","year":"2009","journal-title":"J. Comput. Phys."},{"key":"mlstad0286bib53","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1146\/annurev.fl.23.010191.001401","article-title":"Particle-imaging techniques for experimental fluid mechanics","volume":"23","author":"Adrian","year":"1991","journal-title":"Annu. Rev. Fluid Mech."},{"key":"mlstad0286bib54","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1146\/annurev-fluid-120710-101204","article-title":"Particle image velocimetry for complex and turbulent flows","volume":"45","author":"Westerweel","year":"2013","journal-title":"Annu. Rev. Fluid Mech."},{"key":"mlstad0286bib55","first-page":"pp 7587","article-title":"GPyTorch: blackbox matrix-matrix Gaussian process inference with GPU acceleration","author":"Gardner","year":"2018","edition":"ed"},{"key":"mlstad0286bib56","article-title":"JAX: composable transformations of Python+Numpy programs","author":"Bradbury","year":"2018","unstructured":"Bradbury J et al 2018 JAX: composable transformations of Python+Numpy programs (available at: https:\/\/github.com\/google\/jax )"},{"key":"mlstad0286bib57","article-title":"Adam: a method forstochastic optimization","author":"Kingma","year":"2017"},{"key":"mlstad0286bib58","article-title":"The DeepMind JAX Ecosystem","author":"Babuschkin","year":"2020","unstructured":"Babuschkin I et al 2020 The DeepMind JAX Ecosystem (available at: https:\/\/github.com\/google-deepmind )"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T12:58:30Z","timestamp":1705669110000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad0286"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,20]]},"references-count":58,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,10,20]]},"published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad0286","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,20]]},"assertion":[{"value":"Stokesian processes : inferring Stokes flows using physics-informed Gaussian processes","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-06-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-10-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-10-20","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}