Learning from the past: predicting critical transitions with machine learning trained on surrogates of historical data

TL;DR

This paper introduces a machine learning approach trained on surrogate data of past transitions to improve early warning signals for critical transitions across various complex systems, outperforming traditional generic indicators.

Contribution

The novel surrogate data-based machine learning (SDML) method leverages historical data for system-specific early warning signals, surpassing existing generic methods in sensitivity and specificity.

Findings

SDML outperforms variance and autocorrelation in early warning detection

Applicable across geology, climatology, sociology, and cardiology

Does not rely on local bifurcation assumptions

Abstract

Complex systems can undergo critical transitions, where slowly changing environmental conditions trigger a sudden shift to a new, potentially catastrophic state. Early warning signals for these events are crucial for decision-making in fields such as ecology, biology and climate science. Generic early warning signals motivated by dynamical systems theory have had mixed success on real noisy data. More recent studies found that deep learning classifiers trained on synthetic data could improve performance. However, neither of these methods take advantage of historical, system-specific data. Here, we introduce an approach that trains machine learning classifiers directly on surrogate data of past transitions, namely surrogate data-based machine learning (SDML). The approach provides early warning signals in empirical and experimental data from geology, climatology, sociology, and cardiology with higher sensitivity and specificity than two widely used generic early warning signals -- variance and lag-1 autocorrelation. Since the approach is trained directly on surrogates of historical data, it is not bound by the restricting assumption of a local bifurcation like previous methods. This system-specific approach can contribute to improved early warning signals to help humans better prepare for or avoid undesirable critical transitions.