Copertina

Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	McGreivy, Nick, Hakim, Ammar
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Numerical Analysis Machine Learning Fluid Dynamics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Generative AI for fast and accurate statistical computation of fluids
di: Molinaro, Roberto, et al.
Pubblicazione: (2024)

Spatially dependent node regularity in meshless approximation of partial differential equations
di: Rot, Miha, et al.
Pubblicazione: (2024)

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

Equilibrium-distribution-function based mesoscopic finite-difference methods for partial differential equations: Modeling and Analysis
di: shi, Baochang, et al.
Pubblicazione: (2025)

Koopman neural operator as a mesh-free solver of non-linear partial differential equations
di: Xiong, Wei, et al.
Pubblicazione: (2023)

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

Neural network-based Godunov corrections for approximate Riemann solvers using bi-fidelity learning
di: Thakur, Akshay, et al.
Pubblicazione: (2025)

Machine learning enhanced real-time aerodynamic forces prediction based on sparse pressure sensor inputs
di: Duan, Junming, et al.
Pubblicazione: (2023)

Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics
di: Schmöcker, Robin, et al.
Pubblicazione: (2024)

A Machine Learning-Enhanced Hopf-Cole Formulation for Nonlinear Gas Flow in Porous Media
di: Maduru, V. S., et al.
Pubblicazione: (2026)

Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition
di: Deo, Indu Kant, et al.
Pubblicazione: (2025)

Targeted Digital Twin via Flow Map Learning and Its Application to Fluid Dynamics
di: Chen, Qifan, et al.
Pubblicazione: (2025)

Learning Mesh-Free Discrete Differential Operators with Self-Supervised Graph Neural Networks
di: Starepravo, Lucas Gerken, et al.
Pubblicazione: (2026)

Structure-preserving Randomized Neural Networks for Incompressible Magnetohydrodynamics Equations
di: Li, Yunlong, et al.
Pubblicazione: (2026)

Geometry-aware PINNs for Turbulent Flow Prediction
di: Ghosh, Shinjan, et al.
Pubblicazione: (2024)

Symbolic Regression of Data-Driven Reduced Order Model Closures for Under-Resolved, Convection-Dominated Flows
di: Manti, Simone, et al.
Pubblicazione: (2025)

VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction
di: Cao, Yadi, et al.
Pubblicazione: (2024)

Preconditioned FEM-based Neural Networks for Solving Incompressible Fluid Flows and Related Inverse Problems
di: Griese, Franziska, et al.
Pubblicazione: (2024)

An Adaptive Machine Learning Framework for Fluid Flow in Dual-Network Porous Media
di: Maduri, V. S., et al.
Pubblicazione: (2026)

PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics
di: Liu, Yuxuan, et al.
Pubblicazione: (2024)

EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale
di: Du, Yiheng, et al.
Pubblicazione: (2025)

Operator learning regularization for macroscopic permeability prediction in dual-scale flow problem
di: Runkel, Christina, et al.
Pubblicazione: (2024)

Surrogate normal-forms for the numerical bifurcation and stability analysis of navier-stokes flows via machine learning
di: Della Pia, Alessandro, et al.
Pubblicazione: (2025)

Differentiable Programming for Computational Plasma Physics
di: McGreivy, Nick
Pubblicazione: (2024)

A solver-in-the-loop framework for end-to-end differentiable coastal hydrodynamics
di: Cardoso-Bihlo, Elsa, et al.
Pubblicazione: (2026)

A unified constraint formulation of immersed body techniques for coupled fluid-solid motion: continuous equations and numerical algorithms
di: Bhalla, Amneet Pal Singh, et al.
Pubblicazione: (2024)

Unified description of fluids and solids in Smoothed Particle Hydrodynamics
di: Kincl, Ondřej, et al.
Pubblicazione: (2022)

New approach method for solving nonlinear differential equations of blood flow with nanoparticle in presence of magnetic field
di: Pahnehkolaei, Seyed Morteza Hamzeh, et al.
Pubblicazione: (2024)

Covering convection with thermal blankets: fluid-structure interactions in thermal convection
di: Mac Huang, Jinzi
Pubblicazione: (2024)

A fully-integrated lattice Boltzmann method for fluid-structure interaction
di: Sun, Yue, et al.
Pubblicazione: (2024)

Adaptive coupling of 3D and 2D fluid flow models
di: Suchde, Pratik
Pubblicazione: (2024)

A differentiable software suite for accelerated simulation of turbulent flows
di: Agdestein, Syver Døving, et al.
Pubblicazione: (2026)

A finite element method for a non-Newtonian dilute polymer fluid
di: Ashby, Ben S., et al.
Pubblicazione: (2025)

Numerical simulations of a stochastic dynamics leading to cascades and loss of regularity: applications to fluid turbulence and generation of fractional Gaussian fields
di: Beck, Geoffrey, et al.
Pubblicazione: (2024)

A p-adaptive high-order mesh-free framework for fluid simulations in complex geometries
di: Feng, Ruofeng, et al.
Pubblicazione: (2025)

Shock equations and jump conditions for the 2D Adjoint Euler equations
di: Lozano, Carlos, et al.
Pubblicazione: (2024)

A hybrid reduced-order model for segregated fluid-structure interaction solvers in an ALE approach at high Reynolds number
di: Ngan, Valentin Nkana, et al.
Pubblicazione: (2024)

A Mixture of Experts Gating Network for Enhanced Surrogate Modeling in External Aerodynamics
di: Nabian, Mohammad Amin, et al.
Pubblicazione: (2025)

Multiscale Graph Neural Network for Turbulent Flow-Thermal Prediction Around a Complex-Shaped Pin-Fin
di: Raut, Riddhiman, et al.
Pubblicazione: (2025)

Asymptotic-Preserving Neural Networks for Viscoelastic Parameter Identification in Multiscale Blood Flow Modeling
di: Bertaglia, Giulia, et al.
Pubblicazione: (2026)