Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Haoyuan, Constantinescu, Emil, Rao, Vishwas, Stan, Cristiana
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908374829891584
author Chen, Haoyuan
Constantinescu, Emil
Rao, Vishwas
Stan, Cristiana
author_facet Chen, Haoyuan
Constantinescu, Emil
Rao, Vishwas
Stan, Cristiana
contents The Madden--Julian Oscillation (MJO) is an influential climate phenomenon that plays a vital role in modulating global weather patterns. In spite of the improvement in MJO predictions made by machine learning algorithms, such as neural networks, most of them cannot provide the uncertainty levels in the MJO forecasts directly. To address this problem, we develop a nonparametric strategy based on Gaussian process (GP) models. We calibrate GPs using empirical correlations and we propose a posteriori covariance correction. Numerical experiments demonstrate that our model has better prediction skills than the ANN models for the first five lead days. Additionally, our posteriori covariance correction extends the probabilistic coverage by more than three weeks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15934
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models
Chen, Haoyuan
Constantinescu, Emil
Rao, Vishwas
Stan, Cristiana
Numerical Analysis
Atmospheric and Oceanic Physics
Machine Learning
The Madden--Julian Oscillation (MJO) is an influential climate phenomenon that plays a vital role in modulating global weather patterns. In spite of the improvement in MJO predictions made by machine learning algorithms, such as neural networks, most of them cannot provide the uncertainty levels in the MJO forecasts directly. To address this problem, we develop a nonparametric strategy based on Gaussian process (GP) models. We calibrate GPs using empirical correlations and we propose a posteriori covariance correction. Numerical experiments demonstrate that our model has better prediction skills than the ANN models for the first five lead days. Additionally, our posteriori covariance correction extends the probabilistic coverage by more than three weeks.
title Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models
topic Numerical Analysis
Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2505.15934