From Basins to safe sets: a machine learning perspective on chaotic dynamics

TL;DR

This paper explores how machine learning techniques like CNNs and transformers can efficiently analyze chaotic systems, estimate basin metrics, and enable real-time control, advancing the intersection of nonlinear dynamics and AI.

Contribution

It demonstrates the effectiveness of data-driven machine learning methods in accelerating classical chaos analysis and control tasks, offering scalable and robust solutions.

Findings

CNNs reproduce basin metrics with low bias and cost

Transformers compute safety functions rapidly, bypassing traditional methods

ML approaches enable real-time interventions in chaotic systems

Abstract

The study of chaos has long relied on computationally intensive methods to quantify unpredictability and design control strategies. Recent advances in machine learning, from convolutional neural networks to transformer architectures, provide new ways to analyze complex phase space structures and enable real time action in chaotic dynamics. In this perspective article, we highlight how data driven approaches can accelerate classical tasks such as estimating basin characterization metrics, or partial control of transient chaos, while opening new possibilities for scalable and robust interventions in chaotic systems. In recent studies, convolutional networks have reproduced classical basin metrics with negligible bias and low computational cost, while transformer based surrogates have computed accurate safety functions within seconds, bypassing the recursive procedures required by traditional methods. We discuss current opportunities, remaining challenges, and future directions at the intersection of nonlinear dynamics and artificial intelligence.