Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows
Not on the map. Why?
Abstract (arXiv)
Simulation of fluid flows is crucial for modeling physical phenomena like meteorology, aerodynamics, and biomedicine. Classical numerical solvers often require fine spatiotemporal grids to satisfy stability, consistency, and convergence conditions, leading to substantial computational costs. Although machine learning has demonstrated better efficiency, they typically suffer from issues of interpretability, generalizability, and data dependency. Hence, we propose a learnable and differentiable finite volume solver, called LDSolver, designed for efficient and accurate simulation of fluid flows on spatiotemporal coarse grids. LDSolver comprises two key components: (1) a differentiable finite volume solver, and (2) an learnable module providing equivalent approximation for fluxes (derivatives and interpolations), and temporal error correction on coarse grids. Even with limited training data (e.g., only a few trajectories), our model could accelerate the simulation while maintaining a high accuracy with superior generalizability. Experiments on different flow systems (e.g., Burgers, decaying, forced and shear flows) show that LDSolver achieves state-of-the-art performance, surpassing baseline models with notable margins.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 60 references that are in the map. First posted on arXiv 23 Jun 2025.
Builds on
35 of 60 references.
References · 35
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
- 2021Machine learning accelerated computational fluid dynamicscited by 471
- 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
- 2019Machine Learning for Fluid Mechanicscited by 385
- 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
- 2017PDE-Net: Learning PDEs from Datacited by 311
- 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
- 2021Multiwavelet-based Operator Learning for Differential Equationscited by 234
- 2018PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Networkcited by 210
23 more
- 2020Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solverscited by 205
- 2019Towards Physics-informed Deep Learning for Turbulent Flow Predictioncited by 204
- 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
- 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 197
- 2020PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domaincited by 174
- 2020Physics-informed learning of governing equations from scarce datacited by 167
- 2023Scalable Transformer for PDE Surrogate Modelingcited by 128
- 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 126
- 2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 98
- 2022Deep transfer operator learning for partial differential equations under conditional shiftcited by 83
- 2020Physics informed deep learning for computational elastodynamics without labeled datacited by 80
- 2021Encoding physics to learn reaction-diffusion processescited by 61
- 2020Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structurescited by 52
- 2022Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamicscited by 44
- 2020Hypersolvers: Toward Fast Continuous-Depth Modelscited by 33
- 2022Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learningcited by 24
- 2023A Neural PDE Solver with Temporal Stencil Modelingcited by 22
- 2023Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEscited by 18
- 2024PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systemscited by 18
- 2024Graph Neural PDE Solvers with Conservation and Similarity-Equivariancecited by 17
- 2024P2C2Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamicscited by 13
- 2022Thermodynamics-informed neural networks for physically realistic mixed realitycited by 9
- 2022Neural Solvers for Fast and Accurate Numerical Optimal Controlcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.