Using Diffusion Models for Reducing Spatiotemporal Errors of Deep Learning Based Urban Microclimate Predictions at Post-Processing Stage
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913642524442624 |
|---|---|
| author | Tahmasebi, Sepehrdad Tian, Geng Qin, Shaoxiang Marey, Ahmed Wang, Liangzhu Leon Rayegan, Saeed |
| author_facet | Tahmasebi, Sepehrdad Tian, Geng Qin, Shaoxiang Marey, Ahmed Wang, Liangzhu Leon Rayegan, Saeed |
| contents | Computational fluid dynamics (CFD) is a powerful tool for modeling turbulent flow and is commonly used for urban microclimate simulations. However, traditional CFD methods are computationally intensive, requiring substantial hardware resources for high-fidelity simulations. Deep learning (DL) models are becoming popular as efficient alternatives as they require less computational resources to model complex non-linear interactions in fluid flow simulations. A major drawback of DL models is that they are prone to error accumulation in long-term temporal predictions, often compromising their accuracy and reliability. To address this shortcoming, this study investigates the use of a denoising diffusion probabilistic model (DDPM) as a novel post-processing technique to mitigate error propagation in DL models' sequential predictions. To address this, we employ convolutional autoencoder (CAE) and U-Net architectures to predict airflow dynamics around a cubic structure. The DDPM is then applied to the models' predictions, refining the reconstructed flow fields to better align with high-fidelity statistical results obtained from large-eddy simulations. Results demonstrate that, although deep learning models provide significant computational advantages over traditional numerical solvers, they are susceptible to error accumulation in sequential predictions; however, utilizing DDPM as a post-processing step enhances the accuracy of DL models by up to 65% while maintaining a 3 times speedup compared to traditional numerical solvers. These findings highlight the potential of integrating denoising diffusion probabilistic models as a transformative approach to improving the reliability and accuracy of deep learning-based urban microclimate simulations, paving the way for more efficient and scalable fluid dynamics modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04847 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Using Diffusion Models for Reducing Spatiotemporal Errors of Deep Learning Based Urban Microclimate Predictions at Post-Processing Stage Tahmasebi, Sepehrdad Tian, Geng Qin, Shaoxiang Marey, Ahmed Wang, Liangzhu Leon Rayegan, Saeed Fluid Dynamics Computational fluid dynamics (CFD) is a powerful tool for modeling turbulent flow and is commonly used for urban microclimate simulations. However, traditional CFD methods are computationally intensive, requiring substantial hardware resources for high-fidelity simulations. Deep learning (DL) models are becoming popular as efficient alternatives as they require less computational resources to model complex non-linear interactions in fluid flow simulations. A major drawback of DL models is that they are prone to error accumulation in long-term temporal predictions, often compromising their accuracy and reliability. To address this shortcoming, this study investigates the use of a denoising diffusion probabilistic model (DDPM) as a novel post-processing technique to mitigate error propagation in DL models' sequential predictions. To address this, we employ convolutional autoencoder (CAE) and U-Net architectures to predict airflow dynamics around a cubic structure. The DDPM is then applied to the models' predictions, refining the reconstructed flow fields to better align with high-fidelity statistical results obtained from large-eddy simulations. Results demonstrate that, although deep learning models provide significant computational advantages over traditional numerical solvers, they are susceptible to error accumulation in sequential predictions; however, utilizing DDPM as a post-processing step enhances the accuracy of DL models by up to 65% while maintaining a 3 times speedup compared to traditional numerical solvers. These findings highlight the potential of integrating denoising diffusion probabilistic models as a transformative approach to improving the reliability and accuracy of deep learning-based urban microclimate simulations, paving the way for more efficient and scalable fluid dynamics modeling. |
| title | Using Diffusion Models for Reducing Spatiotemporal Errors of Deep Learning Based Urban Microclimate Predictions at Post-Processing Stage |
| topic | Fluid Dynamics |
| url | https://arxiv.org/abs/2501.04847 |