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

TL;DR

This study evaluates conditional neural fields for turbulence data reduction, comparing various conditioning mechanisms and domain decomposition, demonstrating their effectiveness in both interpolative and extrapolative scenarios across multiple turbulence datasets.

Contribution

It introduces a comprehensive benchmarking framework for CNFs in turbulence data reduction, compares different conditioning strategies, and proposes a novel domain-decomposed CNF approach.

Findings

CNF-FP achieves lowest training and in-range errors.

CNF-FiLM best for out-of-range generalization with moderate capacity.

Domain decomposition enhances out-of-range accuracy significantly.

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.