Information transfer as a new indicator of approaching local bifurcations: saddle-node, pitchfork and Hopf bifurcations
Abstract
Early warning signals are key tools for anticipating qualitative changes in the dynamics of complex systems. In this work, we investigate whether an information-theoretic measure designed to characterize directional causal dependencies between observables can provide early warning of the approach to bifurcations. The measure considered is the rate of information transfer, which has been successfully applied to characterize directional dependencies in a broad range of fields, from economics to climate science. Three fundamental local bifurcations are considered: saddle-node, pitchfork, and Hopf bifurcations. We first investigate idealized (quasi-)potential stochastic systems for which analytical expressions for the rate of information transfer can be derived. Distinct signatures are found for the three bifurcation types. In particular, the rate of information transfer displays a strong increase and divergence when approaching the saddle-node bifurcation, whereas smoother but systematic changes are found near the pitchfork and Hopf bifurcations. The approach is then tested using low-order climate models exhibiting the same types of bifurcations. The results confirm that changes in the rate of information transfer can precede the corresponding dynamical transitions, suggesting that directional information transfer provides a useful complementary early-warning indicator for detecting the approach to critical transitions in nonlinear stochastic systems.
Related
- Adaptive Information Mining: Approaching the Quantum Limit of Super-Resolution Imaging
- Fixed-Point Bifurcations and Path-Information Bounds in Nonlinear Exceptional-Point Sensing
- Universal scaling of electrochemical information transfer at solid-liquid interfaces
- Distinct Modes of Quantum Information Transfer in Power-Law Long-Range Spin Networks
- Cortical information transfer reveals conserved hemispherical network dynamics across human handedness
BibTeX
@misc{vannitsem2026information,
title = {{Information transfer as a new indicator of approaching local bifurcations: saddle-node, pitchfork and Hopf bifurcations}},
author = {Stéphane Vannitsem and Carlos A. Pires and X. San Liang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17529},
eprint = {2610.17529},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17529},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Information transfer as a new indicator of approaching local bifurcations: saddle-node, pitchfork and Hopf bifurcations
AU - Stéphane Vannitsem
AU - Carlos A. Pires
AU - X. San Liang
PY - 2026
DA - 2026/10/13
PB - arXiv
DO - 10.48550/arxiv.2610.17529
UR - https://arxiv.org/abs/2610.17529
AB - Early warning signals are key tools for anticipating qualitative changes in the dynamics of complex systems. In this work, we investigate whether an information-theoretic measure designed to characterize directional causal dependencies between observables can provide early warning of the approach to bifurcations. The measure considered is the rate of information transfer, which has been successfully applied to characterize directional dependencies in a broad range of fields, from economics to climate science. Three fundamental local bifurcations are considered: saddle-node, pitchfork, and Hopf bifurcations. We first investigate idealized (quasi-)potential stochastic systems for which analytical expressions for the rate of information transfer can be derived. Distinct signatures are found for the three bifurcation types. In particular, the rate of information transfer displays a strong increase and divergence when approaching the saddle-node bifurcation, whereas smoother but systematic changes are found near the pitchfork and Hopf bifurcations. The approach is then tested using low-order climate models exhibiting the same types of bifurcations. The results confirm that changes in the rate of information transfer can precede the corresponding dynamical transitions, suggesting that directional information transfer provides a useful complementary early-warning indicator for detecting the approach to critical transitions in nonlinear stochastic systems.
ER -