Extreme Event Precursor Prediction in Turbulent Dynamical Systems via CNN-Augmented Recurrence Analysis

TL;DR

This paper introduces a CNN-augmented recurrence analysis framework for predicting extreme events in turbulent systems, achieving high detection rates and generalization across diverse models without subjective parameter tuning.

Contribution

The authors develop a novel, threshold-free method combining phase-space reconstruction, recurrence matrices, and CNNs for robust extreme event prediction in turbulent systems.

Findings

96% detection rate in triad turbulent model with 1.8 time units lead time

96% detection rate in stochastic turbulent flow with 6.1 time units lead time

93% detection rate in Kolmogorov flow with 22.7 units lead time

Abstract

We present a general framework to predict precursors to extreme events in turbulent dynamical systems. The approach combines phase-space reconstruction techniques with recurrence matrices and convolutional neural networks to identify precursors to extreme events. We evaluate the framework across three distinct testbed systems: a triad turbulent interaction model, a prototype stochastic anisotropic turbulent flow, and the Kolmogorov flow. This method offers three key advantages: (1) a threshold-free classification strategy that eliminates subjective parameter tuning, (2) efficient training using only $\mathcal{O}(100)$ recurrence matrices, and (3) ability to generalize to unseen systems. The results demonstrate robust predictive performance across all test systems: 96\% detection rate for the triad model with a mean lead time of 1.8 time units, 96\% for the anisotropic turbulent flow with a mean lead time of 6.1 time units, and 93\% for the Kolmogorov flow with a mean lead time of 22.7 units.