Autoregressive transformers for data-driven spatiotemporal learning of turbulent flows
A convolutional encoder–decoder-based transformer model is proposed for autoregressively training on spatiotemporal data of turbulent flows. The prediction of future fluid flow fields is based on the previously predicted fluid flow field to ensure long-term predictions without diverging. A combinati...
Main Authors: | Aakash Patil, Jonathan Viquerat, Elie Hachem |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2023-12-01
|
Series: | APL Machine Learning |
Online Access: | http://dx.doi.org/10.1063/5.0152212 |
Similar Items
-
Parallel Bootstrap-Based On-Policy Deep Reinforcement Learning for Continuous Fluid Flow Control Applications
by: Jonathan Viquerat, et al.
Published: (2023-07-01) -
A robust autoregressive long-term spatiotemporal forecasting framework for surrogate-based turbulent combustion modeling via deep learning
by: Sipei Wu, et al.
Published: (2024-01-01) -
Turbulent Channel Flow: Direct Numerical Simulation-Data-Driven Modeling
by: Antonios Liakopoulos, et al.
Published: (2024-03-01) -
Spatiotemporal autoregressive model for Malaysian housing market analysis /
by: 513019 Nurul Hana Adi Maimun, et al.
Published: (2011) -
Turbulent Flow In An Active Wind-Driven Ventilation
Device
by: Abolfazl, Sousanabadi Farahani
Published: (2009)