Conditional neural field for spatial dimension reduction of turbulence data: a comparison study

• URL: http://arxiv.org/abs/2510.25135v1
• Date: Wed, 29 Oct 2025 03:29:10 GMT
• Title: Conditional neural field for spatial dimension reduction of turbulence data: a comparison study
• Authors: Junyi Guo, Pan Du, Xiantao Fan, Yahui Li, Jian-Xun Wang,
• Abstract summary: conditional neural fields (CNFs) are mesh-agnostic, coordinate-based decoders conditioned on a low-dimensional latent.<n>We benchmark CNFs against proper Orthogonal Decomposition and a convolutional autoencoder within a unified encoding-decoding framework.<n>We introduce a novel domain-decomposed CNF that localizes complexities.
• Score: 3.1190164503669684
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate conditional neural fields (CNFs), mesh-agnostic, coordinate-based decoders conditioned on a low-dimensional latent, for spatial dimensionality reduction of turbulent flows. CNFs are benchmarked against Proper Orthogonal Decomposition and a convolutional autoencoder within a unified encoding-decoding framework and a common evaluation protocol that explicitly separates in-range (interpolative) from out-of-range (strict extrapolative) testing beyond the training horizon, with identical preprocessing, metrics, and fixed splits across all baselines. We examine three conditioning mechanisms: (i) activation-only modulation (often termed FiLM), (ii) low-rank weight and bias modulation (termed FP), and (iii) last-layer inner-product coupling, and introduce a novel domain-decomposed CNF that localizes complexities. Across representative turbulence datasets (WMLES channel inflow, DNS channel inflow, and wall pressure fluctuations over turbulent boundary layers), CNF-FP achieves the lowest training and in-range testing errors, while CNF-FiLM generalizes best for out-of-range scenarios once moderate latent capacity is available. Domain decomposition significantly improves out-of-range accuracy, especially for the more demanding datasets. The study provides a rigorous, physics-aware basis for selecting conditioning, capacity, and domain decomposition when using CNFs for turbulence compression and reconstruction.

Related papers

• Multi-Preconditioned LBFGS for Training Finite-Basis PINNs [35.66877569643008]
  The MP-LBFGS algorithm is introduced for training finite-basis physics-informed neural networks (FBPINNs)<n>A key feature is a novel nonlinear multi-preconditioning mechanism, in which subdomain corrections are optimally combined through the solution of a low-dimensional subspace minimization problem.<n> Numerical experiments indicate that MP-LBFGS can improve convergence speed, as well as model accuracy over standard LBFGS while incurring lower communication overhead.
  arXiv  Detail & Related papers  (2026-01-13T16:38:15Z)
• Bayesian Fully-Connected Tensor Network for Hyperspectral-Multispectral Image Fusion [20.64193953092791]
  We present the Fully-Connected Network (BFCTN) decomposition method for hyperspectral-multispectral image fusion.<n>BFCTN not only achieves state-of-the-art fusion accuracy and strong robustness but also exhibits practical applicability in complex real-world scenarios.
  arXiv  Detail & Related papers  (2025-10-21T08:19:54Z)
• Representing Flow Fields with Divergence-Free Kernels for Reconstruction [26.098802942143642]
  We introduce a novel flow field reconstruction framework based on divergence-free kernels (DFKs)<n>DFKs-Wen4 is the optimal form of analytically divergence-free approximation for velocity fields.
  arXiv  Detail & Related papers  (2025-04-02T17:13:59Z)
• Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference [47.460898983429374]
  We introduce an ensemble Kalman filter (EnKF) into the non-mean-field (NMF) variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO) We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-12-10T15:22:30Z)
• Over-the-Air Federated Learning and Optimization [52.5188988624998]
  We focus on Federated learning (FL) via edge-the-air computation (AirComp) We describe the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both convex and non- convex settings. For different types of local updates that can be transmitted by edge devices (i.e., model, gradient, model difference), we reveal that transmitting in AirFedAvg may cause an aggregation error. In addition, we consider more practical signal processing schemes to improve the communication efficiency and extend the convergence analysis to different forms of model aggregation error caused by these signal processing schemes.
  arXiv  Detail & Related papers  (2023-10-16T05:49:28Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• ManiFlow: Implicitly Representing Manifolds with Normalizing Flows [145.9820993054072]
  Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. We propose an optimization objective that recovers the most likely point on the manifold given a sample from the perturbed distribution. Finally, we focus on 3D point clouds for which we utilize the explicit nature of NFs, i.e. surface normals extracted from the gradient of the log-likelihood and the log-likelihood itself.
  arXiv  Detail & Related papers  (2022-08-18T16:07:59Z)
• Probabilistic partition of unity networks: clustering based deep approximation [0.0]
  Partition of unity networks (POU-Nets) have been shown capable of realizing algebraic convergence rates for regression and solution of PDEs. We enrich POU-Nets with a Gaussian noise model to obtain a probabilistic generalization amenable to gradient-based generalizations of a maximum likelihood loss. We provide benchmarks quantifying performance in high/low-dimensions, demonstrating that convergence rates depend only on the latent dimension of data within high-dimensional space.
  arXiv  Detail & Related papers  (2021-07-07T08:02:00Z)
• Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks [0.0]
  We show how to use local approximate process regression to predict stress outputs at particular strain space locations. A modified Newton-Raphson approach is proposed to accommodate for the local nature of the laGPR approximation when solving the global structural problem in a FE setting.
  arXiv  Detail & Related papers  (2021-05-07T14:49:28Z)
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment [52.02794488304448]
  We propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
  arXiv  Detail & Related papers  (2020-03-26T22:10:04Z)
• Learning Likelihoods with Conditional Normalizing Flows [54.60456010771409]
  Conditional normalizing flows (CNFs) are efficient in sampling and inference. We present a study of CNFs where the base density to output space mapping is conditioned on an input x, to model conditional densities p(y|x)
  arXiv  Detail & Related papers  (2019-11-29T19:17:58Z)

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.