aiqbench analysis
This study applies HistGradientBoosting to analyze how dynamical noise redistributes predictability for extreme events across different forecast horizons in chaotic systems. The findings demonstrate that while low-amplitude noise can artificially inflate short-term prediction scores, it simultaneously degrades skill at intermediate horizons, a phenomenon termed noise-induced predictability redistribution (NIPR). These results offer critical insights into the robustness of machine learning models when applied to noisy time-series data in complex dynamical systems.
Noise-Induced Predictability Redistribution Across Forecast Horizons of Extreme Events in Chaotic Dynamics
arXiv:2609.27877v1 Announce Type: cross Abstract: Extreme events (EEs) in chaotic dynamics are rare broad excursions whose forecastability can be altered by dynamical noise. We investigate how noise changes EE occurrence and prediction skill across forecast horizons in a third-order autonomous chaotic flow. A single clean-data threshold is frozen for all realizations, broad events are defined by one maximum per excursion, and a future window W=15 is predicted from a 15-time-unit history using HistGradientBoosting with chronological data separation. As the forecast gap G between the observed history and the future event window increases, the clean Matthews correlation coefficient (MCC) decreases from 0.641 at G=0 to 0.165 at G=15. Noise dependence is evaluated with ten paired realizations at eight amplitudes. The mean short-horizon score increases from 0.456 in clean data to 0.546 at sigma=0.007; the paired gain is 0.0895 (95% CI 0.0494-0.1295; Holm-adjusted p=0.0234). Noise strongly increases EE occurrence while event amplitude and width remain comparatively stable. Equalizing positive training counts across noise levels substantially attenuates the short-horizon gain, whereas strong noise reduces intermediate-horizon skill. We term this horizon-dependent, nonuniform change in forecast skill noise-induced predictability redistribution (NIPR).
Abstract:Extreme events (EEs) in chaotic dynamics are rare broad excursions whose forecastability can be altered by dynamical noise. We investigate how noise changes EE occurrence and prediction skill across forecast horizons in a third-order autonomous chaotic flow. A single clean-data threshold is frozen for all realizations, broad events are defined by one maximum per excursion, and a future window W=15 is predicted from a 15-time-unit history using HistGradientBoosting with chronological data separation. As the forecast gap G between the observed history and the future event window increases, the clean Matthews correlation coefficient (MCC) decreases from 0.641 at G=0 to 0.165 at G=15. Noise dependence is evaluated with ten paired realizations at eight amplitudes. The mean short-horizon score increases from 0.456 in clean data to 0.546 at sigma=0.007; the paired gain is 0.0895 (95% CI 0.0494-0.1295; Holm-adjusted p=0.0234). Noise strongly increases EE occurrence while event amplitude and width remain comparatively stable. Equalizing positive training counts across noise levels substantially attenuates the short-horizon gain, whereas strong noise reduces intermediate-horizon skill. We term this horizon-dependent, nonuniform change in forecast skill noise-induced predictability redistribution (NIPR).
Chaotic Dynamics (nlin.CD); Machine Learning (cs.LG); Data Analysis, Statistics and Probability (physics.data-an)
arXiv:2609.27877 [nlin.CD]
(or arXiv:2609.27877v1 [nlin.CD] for this version)
https://doi.org/10.48550/arXiv.2609.27877 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 284 words
Related coverage
Forecasting space weather risks on power grids
Microsoft Research · Sep 30, 2026
Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC
Latent Space · Sep 16, 2026
Why do models task game?
AI Alignment Forum · Aug 6, 2026
SACQ: Structured Decoding with Memory-Conditioned Refinement for Long-Horizon Forecasting
arXiv · Oct 9, 2026