A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network

S Xu, Z Sun, R Huang, D Guo, G Yang, S Ju - Acta Mechanica Sinica, 2023 - Springer
High-resolution flow field reconstruction is prevalently recognized as a difficult task in the
field of experimental fluid mechanics, since the measured data are usually sparse and …

Deep learning methods for partial differential equations and related parameter identification problems

DN Tanyu, J Ning, T Freudenberg… - Inverse …, 2023 - iopscience.iop.org
Recent years have witnessed a growth in mathematics for deep learning—which seeks a
deeper understanding of the concepts of deep learning with mathematics and explores how …

Gaussian process priors for systems of linear partial differential equations with constant coefficients

M Harkonen, M Lange-Hegermann… - … on machine learning, 2023 - proceedings.mlr.press
Partial differential equations (PDEs) are important tools to model physical systems and
including them into machine learning models is an important way of incorporating physical …

Conditional neural field latent diffusion model for generating spatiotemporal turbulence

P Du, MH Parikh, X Fan, XY Liu, JX Wang - Nature Communications, 2024 - nature.com
Eddy-resolving turbulence simulations are essential for understanding and controlling
complex unsteady fluid dynamics, with significant implications for engineering and scientific …

Constraining Gaussian processes to systems of linear ordinary differential equations

A Besginow… - Advances in Neural …, 2022 - proceedings.neurips.cc
Data in many applications follows systems of Ordinary Differential Equations (ODEs). This
paper presents a novel algorithmic and symbolic construction for covariance functions of …

Bayesian conditional diffusion models for versatile spatiotemporal turbulence generation

H Gao, X Han, X Fan, L Sun, LP Liu, L Duan… - Computer Methods in …, 2024 - Elsevier
Turbulent flows, characterized by their chaotic and stochastic nature, have historically
presented formidable challenges to predictive computational modeling. Traditional eddy …

A probabilistic digital twin for leak localization in water distribution networks using generative deep learning

NT Mücke, P Pandey, S Jain, SM Bohté, CW Oosterlee - Sensors, 2023 - mdpi.com
Localizing leakages in large water distribution systems is an important and ever-present
problem. Due to the complexity originating from water pipeline networks, too few sensors …

From zero to turbulence: Generative modeling for 3d flow simulation

M Lienen, D Lüdke, J Hansen-Palmus… - arXiv preprint arXiv …, 2023 - arxiv.org
Simulations of turbulent flows in 3D are one of the most expensive simulations in
computational fluid dynamics (CFD). Many works have been written on surrogate models to …

A denoising diffusion model for fluid field prediction

G Yang, S Sommer - arXiv preprint arXiv:2301.11661, 2023 - arxiv.org
We propose a novel denoising diffusion generative model for predicting nonlinear fluid fields
named FluidDiff. By performing a diffusion process, the model is able to learn a complex …

Physics-enhanced deep surrogates for partial differential equations

R Pestourie, Y Mroueh, C Rackauckas, P Das… - Nature Machine …, 2023 - nature.com
Many physics and engineering applications demand partial differential equations (PDE)
property evaluations that are traditionally computed with resource-intensive high-fidelity …