{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:59Z","timestamp":1772137919755,"version":"3.50.1"},"reference-count":37,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100007569","name":"Carl-Zeiss-Stiftung","doi-asserted-by":"crossref","award":["P 2018-02-001"],"award-info":[{"award-number":["P 2018-02-001"]}],"id":[{"id":"10.13039\/100007569","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":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study aims at the prediction of the turbulent flow behind cylinder arrays by the application of Echo State Networks (ESN). Three different arrangements of arrays of seven cylinders are chosen for the current study. These represent different flow regimes: single bluff body flow, transient flow, and co-shedding flow. This allows the investigation of turbulent flows that fundamentally originate from wake flows yet exhibit highly diverse dynamics. The data is reduced by Proper Orthogonal Decomposition (POD) which is optimal in terms of kinetic energy. The Time Coefficients of the POD Modes (TCPM) are predicted by the ESN. The network architecture is optimized with respect to its three main hyperparameters, Input Scaling (INS), Spectral Radius (SR), and Leaking Rate (LR), in order to produce the best predictions in terms of Weighted Prediction Score (WPS), a metric leveling statistic and deterministic prediction. In general, the ESN is capable of imitating the complex dynamics of turbulent flows even for longer periods of several vortex shedding cycles. Furthermore, the mutual interdependencies of the TCPM are well preserved. However, optimal hyperparameters depend strongly on the flow characteristics. Generally, as flow dynamics become faster and more intermittent, larger LR and INS values result in better predictions, whereas less clear trends for SR are observable.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad5414","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T18:42:11Z","timestamp":1717526531000},"page":"035005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["On the prediction of the turbulent flow behind cylinder arrays via echo state networks"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5885-4138","authenticated-orcid":true,"given":"M Sharifi","family":"Ghazijahani","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8464-5513","authenticated-orcid":true,"given":"C","family":"Cierpka","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,7,5]]},"reference":[{"key":"mlstad5414bib1","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1146\/annurev-fluid-010719-060214","article-title":"Machine learning for fluid mechanics","volume":"52","author":"Brunton","year":"2020","journal-title":"Annu. Rev. Fluid Mech."},{"key":"mlstad5414bib2","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.1007\/s10409-021-01143-6","article-title":"Applying machine learning to study fluid mechanics","volume":"37","author":"Brunton","year":"2021","journal-title":"Acta Mech. Sin."},{"key":"mlstad5414bib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevFluids.4.100501","article-title":"Perspective on machine learning for advancing fluid mechanics","volume":"4","author":"Brenner","year":"2019","journal-title":"Phys. Rev. Fluids"},{"key":"mlstad5414bib4","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1007\/s10409-021-01154-3","article-title":"Artificial intelligence in fluid mechanics","volume":"37","author":"Zhang","year":"2021","journal-title":"Acta Mech. Sin."},{"key":"mlstad5414bib5","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1080\/14685248.2020.1757685","article-title":"A perspective on machine learning in turbulent flows","volume":"21","author":"Pandey","year":"2020","journal-title":"J. Turbul."},{"key":"mlstad5414bib6","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.202100002","article-title":"A perspective on machine learning methods in turbulence modeling","volume":"44","author":"Beck","year":"2021","journal-title":"GAMM-Mitt."},{"key":"mlstad5414bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42254-023-00622-y","article-title":"The transformative potential of machine learning for experiments in fluid mechanics","volume":"5","author":"Vinuesa","year":"2023","journal-title":"Nat. Rev. Phys."},{"key":"mlstad5414bib8","doi-asserted-by":"publisher","DOI":"10.1063\/1.4836815","article-title":"Compressive sensing based machine learning strategy for characterizing the flow around a cylinder with limited pressure measurements","volume":"25","author":"Bright","year":"2013","journal-title":"Phys. Fluids"},{"key":"mlstad5414bib9","doi-asserted-by":"publisher","DOI":"10.1063\/5.0161305","article-title":"Estimation of cavitation velocity fields based on limited pressure data through improved U-shaped neural network","volume":"35","author":"Xu","year":"2023","journal-title":"Phys. Fluids"},{"key":"mlstad5414bib10","doi-asserted-by":"publisher","DOI":"10.1063\/5.0161305","article-title":"Flow reconstruction from sparse sensors based on reduced-order autoencoder state estimation","volume":"35","author":"Luo","year":"2023","journal-title":"Phys. Fluids"},{"key":"mlstad5414bib11","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":"mlstad5414bib12","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1038\/s41598-023-29525-9","article-title":"A deep-learning approach for reconstructing 3D turbulent flows from 2D observation data","volume":"13","author":"Yousif","year":"2023","journal-title":"Sci. Rep."},{"key":"mlstad5414bib13","doi-asserted-by":"publisher","DOI":"10.1063\/1.5094943","article-title":"Fast flow field prediction over airfoils using deep learning approach","volume":"31","author":"Sekar","year":"2019","journal-title":"Phys. Fluids"},{"key":"mlstad5414bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevFluids.4.054603","article-title":"Predictions of turbulent shear flows using deep neural networks","volume":"4","author":"Srinivasan","year":"2019","journal-title":"Phys. Rev. Fluids"},{"key":"mlstad5414bib15","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":"mlstad5414bib16","first-page":"pp 1457","article-title":"Towards physics-informed deep learning for turbulent flow prediction","author":"Wang","year":"2020"},{"key":"mlstad5414bib17","doi-asserted-by":"publisher","first-page":"2343","DOI":"10.3390\/en16052343","article-title":"A review of physics-informed machine learning in fluid mechanics","volume":"16","author":"Sharma","year":"2023","journal-title":"Energies"},{"key":"mlstad5414bib18","first-page":"pp 471","article-title":"An overview of reservoir computing: theory, applications and implementations","author":"Schrauwen","year":"2007"},{"key":"mlstad5414bib19","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.neunet.2019.03.005","article-title":"Recent advances in physical reservoir computing: a review","volume":"115","author":"Tanaka","year":"2019","journal-title":"Neural Netw."},{"key":"mlstad5414bib20","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/TAI.2022.3225780","article-title":"A systematic review of echo state networks from design to application","volume":"5","author":"Sun","year":"2022","journal-title":"IEEE Trans. Artif. Intell."},{"key":"mlstad5414bib21","first-page":"148","article-title":"The \u2018echo state\u2019 approach to analysing and training recurrent neural networks","author":"Jaeger","year":"2001"},{"key":"mlstad5414bib22","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.cosrev.2009.03.005","article-title":"Reservoir computing approaches to recurrent neural network training","volume":"3","author":"Luko\u0161evi\u010dius","year":"2009","journal-title":"Comput. Sci. Rev."},{"key":"mlstad5414bib23","article-title":"Memory in reservoirs for high dimensional input","volume":"1","author":"Hermans","year":"2010"},{"key":"mlstad5414bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevFluids.5.113506","article-title":"Reservoir computing model of two-dimensional turbulent convection","volume":"5","author":"Pandey","year":"2020","journal-title":"Phys. Rev. Fluids"},{"key":"mlstad5414bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.103.053107","article-title":"Echo state network for two-dimensional turbulent moist Rayleigh-B\u00e9nard convection","volume":"103","author":"Heyder","year":"2021","journal-title":"Phys. Rev. E"},{"key":"mlstad5414bib26","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.106.055303","article-title":"Generalizability of reservoir computing for flux-driven two-dimensional convection","volume":"106","author":"Heyder","year":"2022","journal-title":"Phys. Rev. E"},{"key":"mlstad5414bib27","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevResearch.4.033176","article-title":"Hybrid quantum-classical reservoir computing of thermal convection flow","volume":"4","author":"Pfeffer","year":"2022","journal-title":"Phys. rev. res."},{"key":"mlstad5414bib28","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ac93a4","article-title":"On the benefits and limitations of echo state networks for turbulent flow prediction","volume":"34","author":"Ghazijahani","year":"2022","journal-title":"Meas. Sci. Technol."},{"key":"mlstad5414bib29","doi-asserted-by":"publisher","DOI":"10.1063\/5.0155102","article-title":"Flow structure and dynamics behind cylinder arrays at Reynolds number 100","volume":"35","author":"Sharifi Ghazijahani","year":"2023","journal-title":"Phys. Fluids"},{"key":"mlstad5414bib30","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1007\/s00348-005-0016-6","article-title":"universal outlier detection for PIV data","volume":"39","author":"Westerweel","year":"2005","journal-title":"Exp. Fluids"},{"key":"mlstad5414bib31","doi-asserted-by":"publisher","first-page":"1629","DOI":"10.1007\/s00348-012-1280-x","article-title":"On the resolution limit of digital particle image velocimetry","volume":"52","author":"K\u00e4hler","year":"2012","journal-title":"Exp. Fluids"},{"key":"mlstad5414bib32","author":"easyesn library v0.1.6.1."},{"key":"mlstad5414bib33","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1090\/qam\/910462","article-title":"Turbulence and the dynamics of coherent structures I. coherent structures","volume":"45","author":"Sirovich","year":"1987","journal-title":"Q. Appl. Math"},{"key":"mlstad5414bib34","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1063\/1.857881","article-title":"Low-dimensional models for complex geometry flows: application to grooved channels and circular cylinders","volume":"3","author":"Deane","year":"1991","journal-title":"Phys. Fluids A"},{"key":"mlstad5414bib35","doi-asserted-by":"publisher","DOI":"10.1063\/1.3466662","article-title":"Synchronized force and particle image velocimetry measurements on a NACA 0015 in poststall under control of time periodic electromagnetic forcing","volume":"22","author":"Cierpka","year":"2010","journal-title":"Phys. Fluids"},{"key":"mlstad5414bib36","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1515\/teme-2022-0121","article-title":"The SCALEX facility\u2013an apparatus for scaled fluid dynamical experiments","volume":"90","author":"Sharifi Ghazijahani","year":"2023","journal-title":"tm-Tech. Mess."},{"key":"mlstad5414bib37","article-title":"Spatio-temporal dynamics of superstructures and vortices in turbulent Rayleigh\u2013B\u00e9nard convection","volume":"36","author":"Sharifi Ghazijahani","year":"2024"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T03:23:30Z","timestamp":1723173810000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad5414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,5]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,7,5]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad5414","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3911885\/v1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,5]]},"assertion":[{"value":"On the prediction of the turbulent flow behind cylinder arrays via echo state networks","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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-01-30","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-04","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}