Accurate and robust real-time prediction of September Arctic sea ice
Abstract
We describe the real-time forecasting of September 2024 Arctic sea ice extent using a theory-guided machine learning method based on data-adaptive harmonic decomposition and frequency-based nonlinear stochastic modeling, as part of the Sea Ice Outlook. Compared to standard statistical and machine learning models, this method adeptly accounts for non-linear behavior, effectively incorporates memory effects, and handles a wide range of time scale variations, from synoptic (stochastic-like) weather effects to low-frequency (red-noise like) variability, significantly enhancing the accuracy and reliability of sea ice prediction.
Fields of Study & Subjects
Arctic and Antarctic ice dynamics
Climate variability and models
Cryospheric studies and observations
Publication details
- Journal / source
- Chaos An Interdisciplinary Journal of Nonlinear Science
- Publisher
- AIP Publishing
- Volume
- 36
- Issue
- 2
- Publication date
- 1 February 2026
- Language
- EN