# Comparison of CNN-based deep learning architectures for unsteady CFD acceleration on small datasets

arXiv: https://arxiv.org/abs/2502.06837 · HTML: https://mlsanity.com/paper/2502.06837/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Machine learning accelerated computational fluid dynamics](https://mlsanity.com/paper/2102.01010/) (2021)
- [A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction](https://mlsanity.com/paper/2211.14680/) (2022)
- [Physics-informed neural networks for solving Reynolds-averaged Navierunicodex2013Stokes equations](https://mlsanity.com/paper/2107.10711/) (2021)
- [CFDNet: a deep learning-based accelerator for fluid simulations](https://mlsanity.com/paper/2005.04485/) (2020)
- [Deep Neural Networks for Data-Driven Turbulence Models](https://mlsanity.com/paper/1806.04482/) (2018)
- [Residual-based physics-informed transfer learning: A hybrid method for accelerating long-term CFD simulations via deep learning](https://mlsanity.com/paper/2206.06817/) (2022)
- [Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows](https://mlsanity.com/paper/2105.03332/) (2021)

## Built on by (most cited first, 3 of 3)

- [Node Assigned physics-informed neural networks for thermal-hydraulic system simulation: CVH/FL module](https://mlsanity.com/paper/2504.16447/) (2025)
- [A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation](https://mlsanity.com/paper/2604.02663/) (2026)
- [APPSolver: Adaptive Patch Partitioning for Point-Wise Ship Flow Prediction on Unstructured Meshes](https://mlsanity.com/paper/2608.29355/) (2026)

## Abstract (arXiv)

CFD acceleration for virtual nuclear reactors or digital twin technology is a primary goal in the nuclear industry. This study compares advanced convolutional neural network (CNN) architectures for accelerating unsteady computational fluid dynamics (CFD) simulations using small datasets based on a challenging natural convection flow dataset. The advanced architectures such as autoencoders, UNet, and ConvLSTM-UNet, were evaluated under identical conditions to determine their predictive accuracy and robustness in autoregressive time-series predictions. ConvLSTM-UNet consistently outperformed other models, particularly in difference value calculation, achieving lower maximum errors and stable residuals. However, error accumulation remains a challenge, limiting reliable predictions to approximately 10 timesteps. This highlights the need for enhanced strategies to improve long-term prediction stability. The novelty of this work lies in its fair comparison of state-of-the-art CNN models within the RePIT framework, demonstrating their potential for accelerating CFD simulations while identifying limitations under small data conditions. Future research will focus on exploring alternative models, such as graph neural networks and implicit neural representations. These efforts aim to develop a robust hybrid approach for long-term unsteady CFD acceleration, contributing to practical applications in virtual nuclear reactor.