Autonomous Chaotic Time Series Prediction using Physical Neuromorphic Networks
Abstract
Physical reservoir computing (PRC) with neuromorphic networks offers a promising approach to brain-inspired information processing, exploiting emergent nonlinear dynamics of physical neural networks as a computational resource. This study demonstrates fully autonomous closed-loop prediction of the Mackey--Glass (MG) chaotic time series using a simulated neuromorphic nanowire network as the physical reservoir. Two strategies are evaluated: the virtual node (VN) method, which expands the feature space by temporal multiplexing of reservoir states, and a non-VN approach that uses all physical node readouts directly without temporal multiplexing. Results are reported for two values of the MG time delay parameter, τ= 18 and τ= 21, the latter representing a more complex chaotic regime not previously evaluated for this class of physical reservoir. Over a short prediction horizon of T = 100 timesteps, the VN approach achieves autonomous prediction accuracies of $90.4$% and $89.7$% at τ= 18 and τ= 21, respectively, while the non-VN approach achieves $81.5$% and $76.2$%. Long-horizon analysis over T = 500 timesteps shows that both approaches reproduce the qualitative attractor structure and dominant spectral content of the true MG signal, with trajectories remaining bounded throughout. These results suggest that the intrinsic dynamics of neuromorphic nanowire networks are sufficient to support meaningful autonomous chaotic time series prediction without virtual node augmentation, and that performance may improve further as physical network sizes scale to the millions of nodes achievable in hardware. As this study uses simulated networks, extrapolation to physically fabricated large-scale arrays remains to be validated experimentally.
Related
- Self-averaging enables reconstruction of higher-order chaotic networks
- Digital Twins of Networked Dynamical Systems: Machine Learning Prediction of Synchronization Transitions in Coupled Chaotic Oscillators
- Chaotic Griffiths phase in neuron map networks
- Online training of Echo State Networks to predict chaotic dynamical systems
- Partial Multistep Prediction of Chaotic Time Series: What Remains Predictable beyond the Horizon of Predictability?
BibTeX
@misc{rajesh2026autonomous,
title = {{Autonomous Chaotic Time Series Prediction using Physical Neuromorphic Networks}},
author = {Akshaya Rajesh and Yinhao Xu and Wave Ngampruetikorn and Zdenka Kuncic},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.06395},
eprint = {2609.06395},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06395},
}
RIS
TY - UNPB
TI - Autonomous Chaotic Time Series Prediction using Physical Neuromorphic Networks
AU - Akshaya Rajesh
AU - Yinhao Xu
AU - Wave Ngampruetikorn
AU - Zdenka Kuncic
PY - 2026
DA - 2026/09/06
PB - arXiv
DO - 10.48550/arxiv.2609.06395
UR - https://arxiv.org/abs/2609.06395
AB - Physical reservoir computing (PRC) with neuromorphic networks offers a promising approach to brain-inspired information processing, exploiting emergent nonlinear dynamics of physical neural networks as a computational resource. This study demonstrates fully autonomous closed-loop prediction of the Mackey--Glass (MG) chaotic time series using a simulated neuromorphic nanowire network as the physical reservoir. Two strategies are evaluated: the virtual node (VN) method, which expands the feature space by temporal multiplexing of reservoir states, and a non-VN approach that uses all physical node readouts directly without temporal multiplexing. Results are reported for two values of the MG time delay parameter, τ= 18 and τ= 21, the latter representing a more complex chaotic regime not previously evaluated for this class of physical reservoir. Over a short prediction horizon of T = 100 timesteps, the VN approach achieves autonomous prediction accuracies of $90.4$% and $89.7$% at τ= 18 and τ= 21, respectively, while the non-VN approach achieves $81.5$% and $76.2$%. Long-horizon analysis over T = 500 timesteps shows that both approaches reproduce the qualitative attractor structure and dominant spectral content of the true MG signal, with trajectories remaining bounded throughout. These results suggest that the intrinsic dynamics of neuromorphic nanowire networks are sufficient to support meaningful autonomous chaotic time series prediction without virtual node augmentation, and that performance may improve further as physical network sizes scale to the millions of nodes achievable in hardware. As this study uses simulated networks, extrapolation to physically fabricated large-scale arrays remains to be validated experimentally.
ER -