Hierarchy of extreme-event predictability in turbulence revealed by machine learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yuxuan, Dong, Chenyu, Mengaldo, Gianmarco
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908886046343168
author Yang, Yuxuan
Dong, Chenyu
Mengaldo, Gianmarco
author_facet Yang, Yuxuan
Dong, Chenyu
Mengaldo, Gianmarco
contents Extreme-event predictability in turbulence is strongly state dependent, yet event-by-event predictability horizons are difficult to quantify without access to governing equations or costly perturbation ensembles. Here we train an autoregressive conditional diffusion model on direct numerical simulations of the two-dimensional Kolmogorov flow and use a CRPS-based skill score to define an event-wise predictability horizon. Enstrophy extremes exhibit a pronounced hierarchy: forecast skill persists from $\approx 1$ to $> 4$ Lyapunov times across events. Spectral filtering shows that these horizons are controlled predominantly by large-scale structures. Extremes are preceded by intense strain cores organizing quadrupolar vortex packets, whose lifetime sharply separates long- from short-horizon events. These results identify coherent-structure persistence as a governing mechanism for the predictability of turbulence extremes and provide a data-driven route to diagnose predictability limits from observations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13789
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchy of extreme-event predictability in turbulence revealed by machine learning
Yang, Yuxuan
Dong, Chenyu
Mengaldo, Gianmarco
Chaotic Dynamics
Machine Learning
Dynamical Systems
Computational Physics
Fluid Dynamics
Extreme-event predictability in turbulence is strongly state dependent, yet event-by-event predictability horizons are difficult to quantify without access to governing equations or costly perturbation ensembles. Here we train an autoregressive conditional diffusion model on direct numerical simulations of the two-dimensional Kolmogorov flow and use a CRPS-based skill score to define an event-wise predictability horizon. Enstrophy extremes exhibit a pronounced hierarchy: forecast skill persists from $\approx 1$ to $> 4$ Lyapunov times across events. Spectral filtering shows that these horizons are controlled predominantly by large-scale structures. Extremes are preceded by intense strain cores organizing quadrupolar vortex packets, whose lifetime sharply separates long- from short-horizon events. These results identify coherent-structure persistence as a governing mechanism for the predictability of turbulence extremes and provide a data-driven route to diagnose predictability limits from observations.
title Hierarchy of extreme-event predictability in turbulence revealed by machine learning
topic Chaotic Dynamics
Machine Learning
Dynamical Systems
Computational Physics
Fluid Dynamics
url https://arxiv.org/abs/2603.13789