Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator
With the growing demand for high-precision flow field simulations in computational science and engineering, the super-resolution reconstruction of physical fields has attracted considerable research interest. However, traditional numerical methods often entail high computational costs, involve compl...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Theoretical and Applied Mechanics Letters |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095034925000364 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849245759546851328 |
|---|---|
| author | Yanan Guo Junqiang Song Xiaoqun Cao Chuanfeng Zhao Hongze Leng |
| author_facet | Yanan Guo Junqiang Song Xiaoqun Cao Chuanfeng Zhao Hongze Leng |
| author_sort | Yanan Guo |
| collection | DOAJ |
| description | With the growing demand for high-precision flow field simulations in computational science and engineering, the super-resolution reconstruction of physical fields has attracted considerable research interest. However, traditional numerical methods often entail high computational costs, involve complex data processing, and struggle to capture fine-scale high-frequency details. To address these challenges, we propose an innovative super-resolution reconstruction framework that integrates a Fourier neural operator (FNO) with an enhanced diffusion model. The framework employs an adaptively weighted FNO to process low-resolution flow field inputs, effectively capturing global dependencies and high-frequency features. Furthermore, a residual-guided diffusion model is introduced to further improve reconstruction performance. This model uses a Markov chain for noise injection in physical fields and integrates a reverse denoising procedure, efficiently solved by an adaptive time-step ordinary differential equation solver, thereby ensuring both stability and computational efficiency. Experimental results demonstrate that the proposed framework significantly outperforms existing methods in terms of accuracy and efficiency, offering a promising solution for fine-grained data reconstruction in scientific simulations. |
| format | Article |
| id | doaj-art-eeb7c251bf01442c93fdf31fee29932d |
| institution | Kabale University |
| issn | 2095-0349 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Theoretical and Applied Mechanics Letters |
| spelling | doaj-art-eeb7c251bf01442c93fdf31fee29932d2025-08-20T03:58:41ZengElsevierTheoretical and Applied Mechanics Letters2095-03492025-09-0115510060410.1016/j.taml.2025.100604Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operatorYanan Guo0Junqiang Song1Xiaoqun Cao2Chuanfeng Zhao3Hongze Leng4College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China; College of Computer, National University of Defense Technology, Changsha 410073, China; Department of Atmospheric and Oceanic Sciences, School of Physics, Peking University, Beijing 100871, ChinaCorresponding author.; College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China; College of Computer, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China; College of Computer, National University of Defense Technology, Changsha 410073, ChinaDepartment of Atmospheric and Oceanic Sciences, School of Physics, Peking University, Beijing 100871, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China; College of Computer, National University of Defense Technology, Changsha 410073, ChinaWith the growing demand for high-precision flow field simulations in computational science and engineering, the super-resolution reconstruction of physical fields has attracted considerable research interest. However, traditional numerical methods often entail high computational costs, involve complex data processing, and struggle to capture fine-scale high-frequency details. To address these challenges, we propose an innovative super-resolution reconstruction framework that integrates a Fourier neural operator (FNO) with an enhanced diffusion model. The framework employs an adaptively weighted FNO to process low-resolution flow field inputs, effectively capturing global dependencies and high-frequency features. Furthermore, a residual-guided diffusion model is introduced to further improve reconstruction performance. This model uses a Markov chain for noise injection in physical fields and integrates a reverse denoising procedure, efficiently solved by an adaptive time-step ordinary differential equation solver, thereby ensuring both stability and computational efficiency. Experimental results demonstrate that the proposed framework significantly outperforms existing methods in terms of accuracy and efficiency, offering a promising solution for fine-grained data reconstruction in scientific simulations.http://www.sciencedirect.com/science/article/pii/S2095034925000364Fourier neural operatorDiffusion modelSuper-resolution reconstructionFlow field simulationScientific computing |
| spellingShingle | Yanan Guo Junqiang Song Xiaoqun Cao Chuanfeng Zhao Hongze Leng Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator Theoretical and Applied Mechanics Letters Fourier neural operator Diffusion model Super-resolution reconstruction Flow field simulation Scientific computing |
| title | Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator |
| title_full | Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator |
| title_fullStr | Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator |
| title_full_unstemmed | Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator |
| title_short | Physics field super-resolution reconstruction via enhanced diffusion model and fourier neural operator |
| title_sort | physics field super resolution reconstruction via enhanced diffusion model and fourier neural operator |
| topic | Fourier neural operator Diffusion model Super-resolution reconstruction Flow field simulation Scientific computing |
| url | http://www.sciencedirect.com/science/article/pii/S2095034925000364 |
| work_keys_str_mv | AT yananguo physicsfieldsuperresolutionreconstructionviaenhanceddiffusionmodelandfourierneuraloperator AT junqiangsong physicsfieldsuperresolutionreconstructionviaenhanceddiffusionmodelandfourierneuraloperator AT xiaoquncao physicsfieldsuperresolutionreconstructionviaenhanceddiffusionmodelandfourierneuraloperator AT chuanfengzhao physicsfieldsuperresolutionreconstructionviaenhanceddiffusionmodelandfourierneuraloperator AT hongzeleng physicsfieldsuperresolutionreconstructionviaenhanceddiffusionmodelandfourierneuraloperator |