Lazy diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.11.2026 · 36 (11)
DOI: 10.1063/5.0350593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 19.11.2026. Verfasst von Anish Sambamurthy und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Gefördert von: National Science Foundation, National Center for Atmospheric Research.
Abstract (Originalsprache)
Turbulent flows possess broadband, power-law spectra in which multiscale interactions couple high-wavenumber fluctuations to large-scale dynamics. Although diffusion-based generative models offer a principled probabilistic forecasting framework, we show that linear-schedule denoising diffusion probabilistic models exhibit spectral collapse: a Fourier-space analysis of the forward stochastic differential equation reveals a closed-form, mode-wise signal-to-noise ratio that decays monotonically in wavenumber |k|. For spectra S(k) ∝ |k|−λ, this renders high-wavenumber modes noise dominated earlier and produces an intrinsic spectral bias. We reinterpret the noise schedule as a spectral regularizer and study power-law schedules β(τ)∝τγ that preserve fine-scale structure deeper into diffusion time, along with lazy diffusion, a one-step retraining method that reuses the pretrained score network to bypass long reverse-time trajectories. Applied to high-Reynolds-number 2D Kolmogorov turbulence and 1/12° Gulf of Mexico ocean reanalysis, these methods mitigate spectral collapse, stabilize long-horizon autoregression, and restore physically realistic inertial-range scaling. Together, they show that naïve Gaussian scheduling can impair long-term spectral fidelity in turbulent flows and that physics-aware diffusion processes can yield accurate, efficient, and fully probabilistic surrogates for multiscale dynamical systems.
Förderung
- National Science Foundation
- National Center for Atmospheric Research
Zitieren
APA
Sambamurthy, A., & Chattopadhyay, A. (2026). Lazy diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(11). https://doi.org/10.1063/5.0350593
Vancouver
Sambamurthy A, Chattopadhyay A. Lazy diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(11). doi:10.1063/5.0350593
BibTeX
@article{Sambamurthy2026,
author = {Sambamurthy, Anish and Chattopadhyay, Ashesh},
title = {Lazy diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {11},
doi = {10.1063/5.0350593}
}
EUVIMED