Seasonal forecast of sea surface temperatures via Neural ODEs
Machine Learning: Earth · 01.12.2026 · 2 (2) · 02LT01
DOI: 10.1088/3049-4753/ae7447 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Earth, online erschienen am 17.06.2026. Verfasst von Jonghan Lee und 2 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education.
Abstract (Originalsprache)
Global meteorological agencies provide seasonal forecasts based on indicators such as El Niño–Southern Oscillation and Indian Ocean variability. The NOAA operates forecasts up to 9 months, while the ECMWF offers extended predictions up to 13 months. However, these physics-based forecasting systems suffer from the chaotic nature of the atmosphere, leading to a rapid decline in forecast accuracy as the lead times increase. This study proposes a novel seasonal forecasting framework utilizing neural ordinary differential equations (Neural ODEs). Through comparative experiments with the North American Multi-Model Ensemble model, we demonstrate that Neural ODEs significantly reduce computational costs and mitigate cumulative errors, thereby enhancing long-term forecasting capability. Furthermore, we employ multifractal detrended fluctuation analysis to quantify the memory characteristics, revealing the intrinsic limits of predictability in the climate system.
Förderung
- Ministry of Education
Zitieren
APA
Lee, J., Moon, W., & Ham, Y. (2026). Seasonal forecast of sea surface temperatures via Neural ODEs. Machine Learning: Earth, 2(2), 02LT01. https://doi.org/10.1088/3049-4753/ae7447
Vancouver
Lee J, Moon W, Ham Y. Seasonal forecast of sea surface temperatures via Neural ODEs. Machine Learning: Earth. 2026;2(2):02LT01. doi:10.1088/3049-4753/ae7447
BibTeX
@article{Lee2026,
author = {Lee, Jonghan and Moon, Woosok and Ham, Yoo-Geun},
title = {Seasonal forecast of sea surface temperatures via Neural ODEs},
journal = {Machine Learning: Earth},
year = {2026},
volume = {2},
number = {2},
pages = {02LT01},
doi = {10.1088/3049-4753/ae7447}
}
EUVIMED