Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory.
Saved in:
| Title: | Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory. |
|---|---|
| Authors: | Wu, Hua-Lin1 (AUTHOR), Xu, Ao1,2 (AUTHOR) axu@nwpu.edu.cn, Xi, Heng-Dong1,2 (AUTHOR) |
| Source: | Journal of Fluid Mechanics. 1/10/2026, Vol. 1026, p1-32. 32p. |
| Subjects: | Turbulent flow, Deep learning, Artificial neural networks, Particle motion, Transformer models, Convolutional neural networks, Rayleigh-Bénard convection |
| Abstract: | We studied the reconstruction of turbulent flow fields from trajectory data recorded by actively migrating Lagrangian agents. We propose a deep-learning model, track-to-flow (T2F), which employs a vision transformer as the encoder to capture the spatiotemporal features of a single agent trajectory, and a convolutional neural network as the decoder to reconstruct the flow field. To enhance the physical consistency of the T2F model, we further incorporate a physics-informed loss function inspired by the framework of physics-informed neural network (PINN), yielding a variant model referred to as T2F+PINN. We first evaluate both models in a laminar cylinder wake flow at a Reynolds number of $\textit{Re} = 800$ as a proof of concept. The results show that the T2F model achieves velocity reconstruction accuracy comparable to that of existing flow reconstruction methods, while the T2F+PINN model reduces the normalised error in vorticity reconstruction relative to the T2F model. We then apply the models in turbulent Rayleigh–Bénard convection at a Rayleigh number of $Ra = 10^{8}$ and a Prandtl number of $\textit{Pr} = 0.71$. The results show that the T2F model accurately reconstructs both the velocity and temperature fields, whereas the T2F+PINN model further improves the reconstruction accuracy of gradient-related physical quantities, such as temperature gradients, vorticity and the $Q$ value, with a maximum improvement of approximately 60 % compared to the T2F model. Overall, the T2F model is better suited for reconstructing primitive flow variables, while the T2F+PINN model provides advantages in reconstructing gradient-related quantities. Our models open a promising avenue for accurate flow reconstruction from a single Lagrangian trajectory. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Fluid Mechanics is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191390027 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wu%2C+Hua-Lin%22">Wu, Hua-Lin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Ao%22">Xu, Ao</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> axu@nwpu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Xi%2C+Heng-Dong%22">Xi, Heng-Dong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Fluid+Mechanics%22">Journal of Fluid Mechanics</searchLink>. 1/10/2026, Vol. 1026, p1-32. 32p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Turbulent+flow%22">Turbulent flow</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Particle+motion%22">Particle motion</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Rayleigh-Bénard+convection%22">Rayleigh-Bénard convection</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: We studied the reconstruction of turbulent flow fields from trajectory data recorded by actively migrating Lagrangian agents. We propose a deep-learning model, track-to-flow (T2F), which employs a vision transformer as the encoder to capture the spatiotemporal features of a single agent trajectory, and a convolutional neural network as the decoder to reconstruct the flow field. To enhance the physical consistency of the T2F model, we further incorporate a physics-informed loss function inspired by the framework of physics-informed neural network (PINN), yielding a variant model referred to as T2F+PINN. We first evaluate both models in a laminar cylinder wake flow at a Reynolds number of $\textit{Re} = 800$ as a proof of concept. The results show that the T2F model achieves velocity reconstruction accuracy comparable to that of existing flow reconstruction methods, while the T2F+PINN model reduces the normalised error in vorticity reconstruction relative to the T2F model. We then apply the models in turbulent Rayleigh–Bénard convection at a Rayleigh number of $Ra = 10^{8}$ and a Prandtl number of $\textit{Pr} = 0.71$. The results show that the T2F model accurately reconstructs both the velocity and temperature fields, whereas the T2F+PINN model further improves the reconstruction accuracy of gradient-related physical quantities, such as temperature gradients, vorticity and the $Q$ value, with a maximum improvement of approximately 60 % compared to the T2F model. Overall, the T2F model is better suited for reconstructing primitive flow variables, while the T2F+PINN model provides advantages in reconstructing gradient-related quantities. Our models open a promising avenue for accurate flow reconstruction from a single Lagrangian trajectory. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Fluid Mechanics is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191390027 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1017/jfm.2025.11033 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 32 StartPage: 1 Subjects: – SubjectFull: Turbulent flow Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Particle motion Type: general – SubjectFull: Transformer models Type: general – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Rayleigh-Bénard convection Type: general Titles: – TitleFull: Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wu, Hua-Lin – PersonEntity: Name: NameFull: Xu, Ao – PersonEntity: Name: NameFull: Xi, Heng-Dong IsPartOfRelationships: – BibEntity: Dates: – D: 10 M: 01 Text: 1/10/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 00221120 Numbering: – Type: volume Value: 1026 Titles: – TitleFull: Journal of Fluid Mechanics Type: main |
| ResultId | 1 |
