Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models

Accurate characterization of complex dynamical systems is crucial for understanding their intrinsic behavior, and retrospective prediction provides a promising solution. However, traditional methods often fail to effectively predict dissipative terms, which are key in dissipative dynamical systems....

Full description

Saved in:
Bibliographic Details
Main Authors: Meng Zhang, Mustafa Z. Yousif, Linqi Yu, Hee-Chang Lim
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024018401
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846115725999079424
author Meng Zhang
Mustafa Z. Yousif
Linqi Yu
Hee-Chang Lim
author_facet Meng Zhang
Mustafa Z. Yousif
Linqi Yu
Hee-Chang Lim
author_sort Meng Zhang
collection DOAJ
description Accurate characterization of complex dynamical systems is crucial for understanding their intrinsic behavior, and retrospective prediction provides a promising solution. However, traditional methods often fail to effectively predict dissipative terms, which are key in dissipative dynamical systems. This study introduces a deep learning method (DLM) that combines a Transformer model with a multiscale enhanced super-resolution generative adversarial network (MS-ESRGAN) to improve retrospective predictions by extracting implicit information from temporal evolution data. The Transformer excels at capturing past dynamics, while MS-ESRGAN refines the predicted fields, achieving resolutions on par with ground truth data. The effectiveness of the DLM is demonstrated using two canonical flow cases: forced isotropic turbulence and a transitional boundary layer. The model closely matches the velocity fields of the ground truth, with only minor deviations attributed to the nonlinearity of the governing equations and the inherent difficulty in resolving small-scale structures. In addition, the DLM has been applied to National Oceanic and Atmospheric Administration (NOAA) sea surface temperature (SST) data, demonstrating its practical utility for climate science. Despite the challenges associated with capturing small-scale structures, the data-driven DLM outperforms traditional numerical methods that either neglect the dissipative term or utilize negative dissipative coefficients, representing a significant advancement in retrospective predictions.
format Article
id doaj-art-459704b6249e44d39b0d0f971af91c7e
institution Kabale University
issn 2590-1230
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-459704b6249e44d39b0d0f971af91c7e2024-12-19T11:00:05ZengElsevierResults in Engineering2590-12302024-12-0124103597Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN modelsMeng Zhang0Mustafa Z. Yousif1Linqi Yu2Hee-Chang Lim3School of Mechanical Engineering, Pusan National University, 2, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan, 46241, Republic of KoreaSchool of Mechanical Engineering, Pusan National University, 2, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan, 46241, Republic of KoreaSchool of Mechanical Engineering, Pusan National University, 2, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan, 46241, Republic of KoreaCorresponding author.; School of Mechanical Engineering, Pusan National University, 2, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan, 46241, Republic of KoreaAccurate characterization of complex dynamical systems is crucial for understanding their intrinsic behavior, and retrospective prediction provides a promising solution. However, traditional methods often fail to effectively predict dissipative terms, which are key in dissipative dynamical systems. This study introduces a deep learning method (DLM) that combines a Transformer model with a multiscale enhanced super-resolution generative adversarial network (MS-ESRGAN) to improve retrospective predictions by extracting implicit information from temporal evolution data. The Transformer excels at capturing past dynamics, while MS-ESRGAN refines the predicted fields, achieving resolutions on par with ground truth data. The effectiveness of the DLM is demonstrated using two canonical flow cases: forced isotropic turbulence and a transitional boundary layer. The model closely matches the velocity fields of the ground truth, with only minor deviations attributed to the nonlinearity of the governing equations and the inherent difficulty in resolving small-scale structures. In addition, the DLM has been applied to National Oceanic and Atmospheric Administration (NOAA) sea surface temperature (SST) data, demonstrating its practical utility for climate science. Despite the challenges associated with capturing small-scale structures, the data-driven DLM outperforms traditional numerical methods that either neglect the dissipative term or utilize negative dissipative coefficients, representing a significant advancement in retrospective predictions.http://www.sciencedirect.com/science/article/pii/S2590123024018401Retrospective predictionDeep learningTransformerGenerative adversarial networkDissipative dynamical systems
spellingShingle Meng Zhang
Mustafa Z. Yousif
Linqi Yu
Hee-Chang Lim
Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models
Results in Engineering
Retrospective prediction
Deep learning
Transformer
Generative adversarial network
Dissipative dynamical systems
title Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models
title_full Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models
title_fullStr Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models
title_full_unstemmed Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models
title_short Enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi-scale ESRGAN models
title_sort enhanced retrospective forecasting in dissipative dynamical systems using transformer and multi scale esrgan models
topic Retrospective prediction
Deep learning
Transformer
Generative adversarial network
Dissipative dynamical systems
url http://www.sciencedirect.com/science/article/pii/S2590123024018401
work_keys_str_mv AT mengzhang enhancedretrospectiveforecastingindissipativedynamicalsystemsusingtransformerandmultiscaleesrganmodels
AT mustafazyousif enhancedretrospectiveforecastingindissipativedynamicalsystemsusingtransformerandmultiscaleesrganmodels
AT linqiyu enhancedretrospectiveforecastingindissipativedynamicalsystemsusingtransformerandmultiscaleesrganmodels
AT heechanglim enhancedretrospectiveforecastingindissipativedynamicalsystemsusingtransformerandmultiscaleesrganmodels