Cover Image

Inpainting physics: self-supervised learning for context-driven fluid simulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Weidner, Jonas, Martin-Ruisanchez, Yeray, Rueckert, Daniel, Wiestler, Benedikt, Suk, Julian
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Fluid Dynamics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prospects of federated machine learning in fluid dynamics
by: San, Omer, et al.
Published: (2022)

Inpainting Computational Fluid Dynamics with Deep Learning
by: Shu, Dule, et al.
Published: (2024)

XRePIT: A deep learning-computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations
by: Baral, Shilaj, et al.
Published: (2025)

On the locality of local neural operator in learning fluid dynamics
by: Ye, Ximeng, et al.
Published: (2023)

Physics-informed deep-learning applications to experimental fluid mechanics
by: Eivazi, Hamidreza, et al.
Published: (2022)

RheOFormer: A generative transformer model for simulation of complex fluids and flows
by: Saberi, Maedeh, et al.
Published: (2025)

Analysis of accuracy and efficiency of neural networks to simulate Navier-Stokes fluid flows with obstacles
by: Hespanha, Rui, et al.
Published: (2025)

Hybrid machine learning models based on physical patterns to accelerate CFD simulations: a short guide on autoregressive models
by: Sengupta, Arindam, et al.
Published: (2025)

Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models
by: Haouari, Zeineb, et al.
Published: (2025)

Equation identification for fluid flows via physics-informed neural networks
by: New, Alexander, et al.
Published: (2024)

Improving CFD simulations by local machine-learned correction
by: Mitra, Peetak, et al.
Published: (2023)

Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
by: Sedykh, Alexandr, et al.
Published: (2023)

Method of data forward generation with partial differential equations for machine learning modeling in fluid mechanics
by: Chen, Ruilin
Published: (2025)

Generalization capabilities and robustness of hybrid models grounded in physics compared to purely deep learning models
by: Abadía-Heredia, Rodrigo, et al.
Published: (2024)

Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics
by: Kim, Hojin, et al.
Published: (2023)

Unsupervised simulation of incompressible flows with physics- and equality- constrained artificial neural networks
by: Hu, Qifeng, et al.
Published: (2025)

Interpreting and generalizing deep learning in physics-based problems with functional linear models
by: Arzani, Amirhossein, et al.
Published: (2023)

Rapid aerodynamic prediction of swept wings via physics-embedded transfer learning
by: Yang, Yunjia, et al.
Published: (2024)

Explainable deep learning reveals the physical mechanisms behind the turbulent kinetic energy equation
by: Alcántara-Ávila, Francisco, et al.
Published: (2026)

CFDTwin: An open-source GUI and Python toolkit for POD-NN surrogate modeling of ANSYS Fluent simulations
by: Curl, Daniel, et al.
Published: (2026)

A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training data
by: Sorensen, Benedikt Barthel, et al.
Published: (2024)

Predicting fluid-structure interaction with graph neural networks
by: Gao, Rui, et al.
Published: (2022)

Data-driven Mori-Zwanzig modeling of Lagrangian particle dynamics in turbulent flows
by: de Wit, Xander, et al.
Published: (2025)

Accelerating Bayesian inverse design in computational fluid dynamics using neural operators
by: Tiwari, Bipin, et al.
Published: (2026)

Reduced-order modeling of unsteady fluid flow using neural network ensembles
by: Halder, Rakesh, et al.
Published: (2024)

oRANS: Online optimisation of RANS machine learning models with embedded DNS data generation
by: Dehtyriov, Daniel, et al.
Published: (2025)

Transfer learning strategies for accelerating reinforcement-learning-based flow control
by: Salehi, Saeed
Published: (2025)

A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
by: Agrawal, Atul, et al.
Published: (2023)

RoseNNa: A performant, portable library for neural network inference with application to computational fluid dynamics
by: Bati, Ajay, et al.
Published: (2023)

HFNO: an interpretable data-driven decomposition strategy for turbulent flows
by: Cayuela, Marco, et al.
Published: (2025)

Equation-informed data-driven identification of flow budgets and dynamics
by: Sevryugina, Nataliya, et al.
Published: (2024)

Mixture of neural operator experts for learning boundary conditions and model selection
by: Deighan, Dwyer, et al.
Published: (2025)

Data-driven low-dimensional model of a sedimenting flexible fiber
by: Fox, Andrew J, et al.
Published: (2024)

Smart navigation of a gravity-driven glider with adjustable centre-of-mass
by: Jiang, X., et al.
Published: (2025)

A note on the error analysis of data-driven closure models for large eddy simulations of turbulence
by: Chakraborty, Dibyajyoti, et al.
Published: (2024)

Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
by: McGreivy, Nick, et al.
Published: (2024)

Data-driven Learning of Probabilistic Model of Binary Droplet Collision for Spray Simulation
by: Xu, Weiming, et al.
Published: (2026)

Data-informed lifting line theory
by: Sharma, Arjun, et al.
Published: (2026)

FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation
by: Wang, Haixin, et al.
Published: (2025)

Filtered Partial Differential Equations: a robust surrogate constraint in physics-informed deep learning framework
by: Zhang, Dashan, et al.
Published: (2023)