Joint Forecasting of Extreme Events through Dual-Stage Cascade Reservoir Computing
Abstract
Reservoir computing (RC) offers an efficient data-driven approach for forecasting extreme events (EEs), which correspond to rare and large-amplitude dynamical occurrences. We propose a dual-stage cascade framework that jointly predicts both the timing and peak intensity of upcoming EEs. A traditional RC branch integrates long-term precursor dynamics to support stable detection and long-horizon prediction, while an NGRC branch captures local nonlinear waveform geometry to improve fine-grained time-to-peak localization and complement peak-intensity estimation. The fused features then feed a ridge classifier that issues a binary alarm upon detecting precursors. Only then do two ridge regressors, trained on true-positive snapshots, estimate time-to-peak and peak intensity. This classify-then-regress design addresses severe class imbalance without data resampling. Evaluated on simulated pump-modulated VCSEL data, the hybrid model achieves a SEDI value >0.8, with MAEs around 0.2 ns and 0.2 a. u., maintaining performance up to a 20 ns warning horizon. The framework advances extreme-event forecasting from binary warnings to fully quantitative dual-objective prediction.
Related
- Optical Reservoir Computing with Structural Nonlinearity for Forecasting Chaotic Time Series
- Hardware-Aware Design and Layout Selection in Quantum Reservoir Computing for Insurance Claims Forecasting
- Reservoir computing generalized: Exploiting complex dynamics via time-invariant transformation
- Nonlinear pluggable optics: Digital signal processing-free Intensity Modulated Direct Detection links using analog photonic Next Generation Reservoir Computing
- Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing
BibTeX
@misc{wang2026joint,
title = {{Joint Forecasting of Extreme Events through Dual-Stage Cascade Reservoir Computing}},
author = {Yueyang Wang and Juncheng Huang. Hanxu Zhou and Tao Wang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04229},
eprint = {2610.04229},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04229},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Joint Forecasting of Extreme Events through Dual-Stage Cascade Reservoir Computing
AU - Yueyang Wang
AU - Juncheng Huang. Hanxu Zhou
AU - Tao Wang
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2610.04229
UR - https://arxiv.org/abs/2610.04229
AB - Reservoir computing (RC) offers an efficient data-driven approach for forecasting extreme events (EEs), which correspond to rare and large-amplitude dynamical occurrences. We propose a dual-stage cascade framework that jointly predicts both the timing and peak intensity of upcoming EEs. A traditional RC branch integrates long-term precursor dynamics to support stable detection and long-horizon prediction, while an NGRC branch captures local nonlinear waveform geometry to improve fine-grained time-to-peak localization and complement peak-intensity estimation. The fused features then feed a ridge classifier that issues a binary alarm upon detecting precursors. Only then do two ridge regressors, trained on true-positive snapshots, estimate time-to-peak and peak intensity. This classify-then-regress design addresses severe class imbalance without data resampling. Evaluated on simulated pump-modulated VCSEL data, the hybrid model achieves a SEDI value >0.8, with MAEs around 0.2 ns and 0.2 a. u., maintaining performance up to a 20 ns warning horizon. The framework advances extreme-event forecasting from binary warnings to fully quantitative dual-objective prediction.
ER -