Parametric Dynamic Mode Decomposition with multi-linear interpolation for prediction of thermal fields of Al2O3-water nanofluid flows at unseen parameters

• URL: http://arxiv.org/abs/2503.18571v1
• Date: Mon, 24 Mar 2025 11:27:34 GMT
• Title: Parametric Dynamic Mode Decomposition with multi-linear interpolation for prediction of thermal fields of Al2O3-water nanofluid flows at unseen parameters
• Authors: Abhijith M S, Sandra S,
• Abstract summary: The study employs an in-house-based solver to predict the thermal fields of Al$$O$_3$-water nano flow.<n>The performance of two models operating in one- and two-dimensional parametric spaces are investigated.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The study proposes a data-driven model which combines the Dynamic Mode Decomposition with multi-linear interpolation to predict the thermal fields of nanofluid flows at unseen Reynolds numbers (Re) and particle volume concentrations ($\epsilon$). The flow, considered for the study, is laminar and incompressible. The study employs an in-house Fortran-based solver to predict the thermal fields of Al$_2$O$_3$-water nanofluid flow through a two-dimensional rectangular channel, with the bottom wall subjected to a uniform heat flux. The performance of two models operating in one- and two-dimensional parametric spaces are investigated. Initially, a DMD with linear interpolation (DMD-LI) based solver is used for prediction of temperature of the nanofluid at any Re $>$ 100. The DMD-LI based model, predicts temperature fields with a maximum percentage difference of just 0.0273\%, in comparison with the CFD-based solver at Re =960, and $\epsilon$ = 1.0\%. The corresponding difference in the average Nusselt numbers is only 0.39\%. Following that a DMD with bi-linear interpolation (DMD-BLI) based solver is used for prediction of temperature of the nanofluid at any Re $>$ 100 and $\epsilon$ $>$ 0.5\%. The performance of two different ways of stacking the data are also examined. When compared to the CFD-based model, the DMD-BLI-based model predicts the temperature fields with a maximum percentage difference of 0.21 \%, at Re = 800 and $\epsilon$ = 1.35\%. And the corresponding percentage difference in the average Nusselt number prediction is only 6.08\%. All the results are reported in detail. Along side the important conclusions, the future scope of the study is also listed.

Related papers

• Prediction of Diffusion Coefficients in Mixtures with Tensor Completion [0.5039813366558306]
  We present a hybrid tensor completion method (TCM) for predicting temperature-dependent diffusion coefficients at infinite dilution in binary mixtures.<n>The TCM extrapolates linearly to any temperature between 268 K and 378 K, achieving markedly improved prediction accuracy.<n>To further enhance predictive performance, the experimental database was expanded using active learning strategies.
  arXiv  Detail & Related papers  (2026-02-26T16:08:50Z)
• Numerical PDE solvers outperform neural PDE solvers [5.303553599778495]
  DeepFDM is a finite-difference framework for learning spatially varying coefficients in time-dependent partial differential equations.<n>It enforces stability and first-order convergence via CFL-compliant coefficient parameterizations.<n>It attains normalized mean-squared errors one to two orders of magnitude smaller than Fourier Neural Operators, U-Nets and ResNets.
  arXiv  Detail & Related papers  (2025-07-28T18:50:37Z)
• Scale-Consistent Learning for Partial Differential Equations [79.48661503591943]
  We propose a data augmentation scheme based on scale-consistency properties of PDEs.<n>We then design a scale-informed neural operator that can model a wide range of scales.<n>With scale-consistency, the model trained on $Re$ of 1000 can generalize to $Re$ ranging from 250 to 10000.
  arXiv  Detail & Related papers  (2025-07-24T21:29:52Z)
• Physics-informed reduced order model with conditional neural fields [4.5355909674008865]
  This study presents the conditional neural fields for reduced-order modeling (CNF-ROM) framework to approximate solutions of parametrized partial differential equations (PDEs)<n>The approach combines a parametric neural ODE for modeling latent dynamics over time with a decoder that reconstructs PDE solutions from the corresponding latent states.
  arXiv  Detail & Related papers  (2024-12-06T18:04:33Z)
• Evaluating probabilistic and data-driven inference models for fiber-coupled NV-diamond temperature sensors [0.7140163200313723]
  We evaluate the impact of inference model on uncertainties when using continuous wave Optically Detected Magnetic Resonance (ODMR) measurements to infer temperature. This model effectively utilizes the temperature dependence of spin Hamiltonian parameters to infer temperature from spectral features in the ODMR data.
  arXiv  Detail & Related papers  (2024-09-14T17:23:20Z)
• Score-based Diffusion Models in Function Space [137.70916238028306]
  Diffusion models have recently emerged as a powerful framework for generative modeling.<n>This work introduces a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.<n>We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
  arXiv  Detail & Related papers  (2023-02-14T23:50:53Z)
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation [59.45669299295436]
  We propose a Monte Carlo PDE solver for training unsupervised neural solvers.<n>We use the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles.<n>Our experiments on convection-diffusion, Allen-Cahn, and Navier-Stokes equations demonstrate significant improvements in accuracy and efficiency.
  arXiv  Detail & Related papers  (2023-02-10T08:05:19Z)
• Gibbs-Helmholtz Graph Neural Network: capturing the temperature dependency of activity coefficients at infinite dilution [1.290382979353427]
  We develop the Gibbs-Helmholtz Graph Neural Network (GH-GNN) model for predicting $ln gamma_ijinfty$ of molecular systems at different temperatures. We analyze the performance of GH-GNN for continuous and discrete inter/extrapolation and give indications for the model's applicability domain and expected accuracy.
  arXiv  Detail & Related papers  (2022-12-02T14:25:58Z)
• Neural Basis Functions for Accelerating Solutions to High Mach Euler Equations [63.8376359764052]
  We propose an approach to solving partial differential equations (PDEs) using a set of neural networks. We regress a set of neural networks onto a reduced order Proper Orthogonal Decomposition (POD) basis. These networks are then used in combination with a branch network that ingests the parameters of the prescribed PDE to compute a reduced order approximation to the PDE.
  arXiv  Detail & Related papers  (2022-08-02T18:27:13Z)
• Computational Fluid Dynamics and Machine Learning as tools for Optimization of Micromixers geometry [0.0]
  This work explores a new approach for optimization in the field of microfluidics, using the combination of CFD (Computational Fluid Dynamics) and Machine Learning techniques. The initial geometry is inspired in a Y-type micromixer with cylindrical grooves on the surface of the main channel and obstructions inside it. The effects of obstruction diameter (OD), and offset (OF) in the range of mixing ($varphi$), pressure drop ($Delta P$) and energy cost ($Delta P/varphi$) were investigated.
  arXiv  Detail & Related papers  (2022-03-04T18:53:13Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Inverting brain grey matter models with likelihood-free inference: a tool for trustable cytoarchitecture measurements [62.997667081978825]
  characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in dMRI. We propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells. We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model.
  arXiv  Detail & Related papers  (2021-11-15T09:08:27Z)
• Deep learning for surrogate modelling of 2D mantle convection [1.7499351967216341]
  We show that deep learning techniques can produce reliable parameterized surrogates of partial differential equations. We first use convolutional autoencoders to compress the temperature fields by a factor of 142. We then use FNN and long-short term memory networks (LSTM) to predict the compressed fields.
  arXiv  Detail & Related papers  (2021-08-23T12:13:04Z)
• Physics-Informed Machine Learning Method for Large-Scale Data Assimilation Problems [48.7576911714538]
  We extend the physics-informed conditional Karhunen-Lo'eve expansion (PICKLE) method for modeling subsurface flow with unknown flux (Neumann) and varying head (Dirichlet) boundary conditions. We demonstrate that the PICKLE method is comparable in accuracy with the standard maximum a posteriori (MAP) method, but is significantly faster than MAP for large-scale problems.
  arXiv  Detail & Related papers  (2021-07-30T18:43:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.