mlsanityData to 14 Oct 2026

Towards Long-Range ENSO Prediction with an Explainable Deep Learning Model

arXiv 2503.19502 ↗First posted 25 Mar 2025physics.geo-ph cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

El Ni~no-Southern Oscillation (ENSO) is a prominent mode of interannual climate variability with far-reaching global impacts. Its evolution is governed by intricate air-sea interactions, posing significant challenges for long-term prediction. In this study, we introduce CTEFNet, a multivariate deep learning model that synergizes convolutional neural networks and transformers to enhance ENSO forecasting. By integrating multiple oceanic and atmospheric predictors, CTEFNet extends the effective forecast lead time to 20 months while mitigating the impact of the spring predictability barrier, outperforming both dynamical models and state-of-the-art deep learning approaches. Furthermore, CTEFNet offers physically meaningful and statistically significant insights through gradient-based sensitivity analysis, revealing the key precursor signals that govern ENSO dynamics, which align with well-established theories and reveal new insights about inter-basin interactions among the Pacific, Atlantic, and Indian Oceans. The CTEFNet's superior predictive skill and interpretable sensitivity assessments underscore its potential for advancing climate prediction. Our findings highlight the importance of multivariate coupling in ENSO evolution and demonstrate the promise of deep learning in capturing complex climate dynamics with enhanced interpretability.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 11 of its 80 references that are in the map. First posted on arXiv 25 Mar 2025.

Builds on

11 of 80 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  5. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  6. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  7. 2023Theoretical Analysis of Inductive Biases in Deep Convolutional Networkscited by 21
  8. 2021A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applicationscited by 15
  9. 2020NeuralSens: Sensitivity Analysis of Neural Networkscited by 14
  10. 2023LEFormer: A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagerycited by 5
  11. 2023ResoNet: Robust and Explainable ENSO Forecasts with Hybrid Convolution and Transformer Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026Distillation and Interpretability of Ensemble Forecasts of ENSO Phase using Entropic Learningcited by 1
  2. 2025Leveraging GNN to Enhance MEF Method in Predicting ENSOcited by 0
  3. 2025Distillation of CNN Ensemble Results for Enhanced Long-Term Prediction of the ENSO Phenomenoncited by 0
  4. 2026Sensitivity Fidelity Reveals Physical Dependencies Beyond Forecast Accuracy in Deep-Learning Earth-System Modelscited by 0