Kim et al. (2025) Multi‐Scale Decomposition for Skillful All‐Season MJO Prediction With Deep Learning

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Geophysical Research Letters
• Year: 2025
• Date: 2025-12-28
• Authors: Miae Kim, Daehyun Kang, Soo‐Jin Sohn, Gayoung Kim, Jinyoung Rhee, S. T. Kim
• DOI: 10.1029/2025gl117981

Research Groups

Not specified in abstract.

Short Summary

This study introduces a novel deep learning framework for Madden-Julian Oscillation (MJO) prediction that integrates background atmospheric fields alongside MJO anomalies, significantly enhancing prediction skill up to 29 days.

Objective

• To develop a new deep learning framework that explicitly incorporates background atmospheric fields as inputs, in addition to MJO anomaly variables, to improve MJO prediction skill.

Study Configuration

• Spatial Scale: Tropical regions.
• Temporal Scale: Intraseasonal to subseasonal (up to 29 days), considering seasonal and interannual variability.

Methodology and Data

• Models used: Deep learning framework.
• Data sources: MJO anomaly variables and background atmospheric fields (specific sources not detailed in abstract).

Main Results

• The new deep learning model improves MJO prediction skill up to 26 days in boreal winter.
• The model improves MJO prediction skill up to 29 days in boreal summer.
• Model interpretation analyses reveal the important role of background information in long-range MJO forecasts.

Contributions

• Presents a novel deep learning framework that explicitly incorporates background atmospheric fields into MJO prediction.
• Demonstrates significant improvement in MJO prediction skill by utilizing multi-scale decomposed inputs.
• Highlights the critical role of background information for advancing next-generation sub-seasonal forecasting models and enhancing global weather predictability.

Funding

Not specified in abstract.

Citation

@article{Kim2025MultiScale,
  author = {Kim, Miae and Kang, Daehyun and Sohn, Soo‐Jin and Kim, Gayoung and Rhee, Jinyoung and Kim, S. T.},
  title = {Multi‐Scale Decomposition for Skillful All‐Season MJO Prediction With Deep Learning},
  journal = {Geophysical Research Letters},
  year = {2025},
  doi = {10.1029/2025gl117981},
  url = {https://doi.org/10.1029/2025gl117981}
}