Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are trained with a time series of direct numerical simulation (DNS) d...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2024-04 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Asaka, Tomoki Yoshimatsu, Katsunori Schneider, Kai |
| description | A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are trained with a time series of direct numerical simulation (DNS) data of homogeneous isotropic turbulence at the Taylor microscale Reynolds number 92. The predicted results are assessed by using flow visualization of vorticity and statistics, e.g., probability density functions of vorticity and enstrophy spectra. It is found that the predicted results are in good agreement with DNS results. The small-scale flow topology considering the second and third invariant of the velocity gradient tensor likewise shows an approximate match. Furthermore, we apply the pre-trained neural networks to coarse-grained vorticity data using superresolution. It is shown that the superresolved flow field well agrees with the reference DNS field and thus small-scale information and vortex tubes are well regenerated. |
| doi_str_mv | 10.48550/arxiv.2404.02256 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2404_02256</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3032812261</sourcerecordid><originalsourceid>FETCH-LOGICAL-a521-1e2581d2ad613ce6630dd5cb31a90b497d215efc6205a45336b8675993bdae353</originalsourceid><addsrcrecordid>eNo1kF9LwzAUxYMgOKYfwCcDPncmN03WPsrwH0x82XtJk7sto0tq0laHX95u06cDl3PPOfwIueVslhdSsgcdv90wg5zlMwYg1QWZgBA8K3KAK3KT0o4xBmoOUooJ-XnXZus80gZ19M5vslontHQIsXPGdQeKQ2j6zgVPtbc09S3GiOn_FtZ0G_Zhgx5Dn6hLoYuhdYZ2faz7Br1B2qcxl37pARvsaBvDDs3x-ZpcrnWT8OZPp2T1_LRavGbLj5e3xeMy0xJ4xhFkwS1oq7gwqJRg1kpTC65LVufl3AKXuDYKmNS5FELVhZrLshS11SikmJK7c-yJTNVGt9fxUB0JVSdCo-P-7Bi3ffaYumoX-ujHTZVgAgoOMHb_ArXtbIE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3032812261</pqid></control><display><type>article</type><title>Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Asaka, Tomoki ; Yoshimatsu, Katsunori ; Schneider, Kai</creator><creatorcontrib>Asaka, Tomoki ; Yoshimatsu, Katsunori ; Schneider, Kai</creatorcontrib><description>A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are trained with a time series of direct numerical simulation (DNS) data of homogeneous isotropic turbulence at the Taylor microscale Reynolds number 92. The predicted results are assessed by using flow visualization of vorticity and statistics, e.g., probability density functions of vorticity and enstrophy spectra. It is found that the predicted results are in good agreement with DNS results. The small-scale flow topology considering the second and third invariant of the velocity gradient tensor likewise shows an approximate match. Furthermore, we apply the pre-trained neural networks to coarse-grained vorticity data using superresolution. It is shown that the superresolved flow field well agrees with the reference DNS field and thus small-scale information and vortex tubes are well regenerated.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2404.02256</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Direct numerical simulation ; Evolution ; Flow visualization ; Fluid flow ; Isotropic turbulence ; Machine learning ; Mathematical analysis ; Physics - Computational Physics ; Physics - Fluid Dynamics ; Probability density functions ; Reynolds number ; Tensors ; Topology ; Tubes ; Turbulent flow ; Velocity gradient ; Vorticity</subject><ispartof>arXiv.org, 2024-04</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27924</link.rule.ids><backlink>$$Uhttps://doi.org/10.1063/5.0185165$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2404.02256$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Asaka, Tomoki</creatorcontrib><creatorcontrib>Yoshimatsu, Katsunori</creatorcontrib><creatorcontrib>Schneider, Kai</creatorcontrib><title>Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection</title><title>arXiv.org</title><description>A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are trained with a time series of direct numerical simulation (DNS) data of homogeneous isotropic turbulence at the Taylor microscale Reynolds number 92. The predicted results are assessed by using flow visualization of vorticity and statistics, e.g., probability density functions of vorticity and enstrophy spectra. It is found that the predicted results are in good agreement with DNS results. The small-scale flow topology considering the second and third invariant of the velocity gradient tensor likewise shows an approximate match. Furthermore, we apply the pre-trained neural networks to coarse-grained vorticity data using superresolution. It is shown that the superresolved flow field well agrees with the reference DNS field and thus small-scale information and vortex tubes are well regenerated.</description><subject>Artificial neural networks</subject><subject>Direct numerical simulation</subject><subject>Evolution</subject><subject>Flow visualization</subject><subject>Fluid flow</subject><subject>Isotropic turbulence</subject><subject>Machine learning</subject><subject>Mathematical analysis</subject><subject>Physics - Computational Physics</subject><subject>Physics - Fluid Dynamics</subject><subject>Probability density functions</subject><subject>Reynolds number</subject><subject>Tensors</subject><subject>Topology</subject><subject>Tubes</subject><subject>Turbulent flow</subject><subject>Velocity gradient</subject><subject>Vorticity</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNo1kF9LwzAUxYMgOKYfwCcDPncmN03WPsrwH0x82XtJk7sto0tq0laHX95u06cDl3PPOfwIueVslhdSsgcdv90wg5zlMwYg1QWZgBA8K3KAK3KT0o4xBmoOUooJ-XnXZus80gZ19M5vslontHQIsXPGdQeKQ2j6zgVPtbc09S3GiOn_FtZ0G_Zhgx5Dn6hLoYuhdYZ2faz7Br1B2qcxl37pARvsaBvDDs3x-ZpcrnWT8OZPp2T1_LRavGbLj5e3xeMy0xJ4xhFkwS1oq7gwqJRg1kpTC65LVufl3AKXuDYKmNS5FELVhZrLshS11SikmJK7c-yJTNVGt9fxUB0JVSdCo-P-7Bi3ffaYumoX-ujHTZVgAgoOMHb_ArXtbIE</recordid><startdate>20240402</startdate><enddate>20240402</enddate><creator>Asaka, Tomoki</creator><creator>Yoshimatsu, Katsunori</creator><creator>Schneider, Kai</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>GOX</scope></search><sort><creationdate>20240402</creationdate><title>Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection</title><author>Asaka, Tomoki ; Yoshimatsu, Katsunori ; Schneider, Kai</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a521-1e2581d2ad613ce6630dd5cb31a90b497d215efc6205a45336b8675993bdae353</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>Direct numerical simulation</topic><topic>Evolution</topic><topic>Flow visualization</topic><topic>Fluid flow</topic><topic>Isotropic turbulence</topic><topic>Machine learning</topic><topic>Mathematical analysis</topic><topic>Physics - Computational Physics</topic><topic>Physics - Fluid Dynamics</topic><topic>Probability density functions</topic><topic>Reynolds number</topic><topic>Tensors</topic><topic>Topology</topic><topic>Tubes</topic><topic>Turbulent flow</topic><topic>Velocity gradient</topic><topic>Vorticity</topic><toplevel>online_resources</toplevel><creatorcontrib>Asaka, Tomoki</creatorcontrib><creatorcontrib>Yoshimatsu, Katsunori</creatorcontrib><creatorcontrib>Schneider, Kai</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Asaka, Tomoki</au><au>Yoshimatsu, Katsunori</au><au>Schneider, Kai</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection</atitle><jtitle>arXiv.org</jtitle><date>2024-04-02</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are trained with a time series of direct numerical simulation (DNS) data of homogeneous isotropic turbulence at the Taylor microscale Reynolds number 92. The predicted results are assessed by using flow visualization of vorticity and statistics, e.g., probability density functions of vorticity and enstrophy spectra. It is found that the predicted results are in good agreement with DNS results. The small-scale flow topology considering the second and third invariant of the velocity gradient tensor likewise shows an approximate match. Furthermore, we apply the pre-trained neural networks to coarse-grained vorticity data using superresolution. It is shown that the superresolved flow field well agrees with the reference DNS field and thus small-scale information and vortex tubes are well regenerated.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2404.02256</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2024-04 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2404_02256 |
| source | arXiv.org; Free E- Journals |
| subjects | Artificial neural networks Direct numerical simulation Evolution Flow visualization Fluid flow Isotropic turbulence Machine learning Mathematical analysis Physics - Computational Physics Physics - Fluid Dynamics Probability density functions Reynolds number Tensors Topology Tubes Turbulent flow Velocity gradient Vorticity |
| title | Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T08%3A09%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20learning-based%20vorticity%20evolution%20and%20superresolution%20of%20homogeneous%20isotropic%20turbulence%20using%20wavelet%20projection&rft.jtitle=arXiv.org&rft.au=Asaka,%20Tomoki&rft.date=2024-04-02&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2404.02256&rft_dat=%3Cproquest_arxiv%3E3032812261%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3032812261&rft_id=info:pmid/&rfr_iscdi=true |