Preprint · 2026 · Open access

Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning

Yu Weng, Xiefei Zhi, Jingyu Wang, Ling Zhang, Yang Lyu, Yan Ji, Yunchang Cao, Shoupeng Zhu, Klaus Fraedrich, Dexuan Kong, Liqun Zhou

Research Square · Published 31 March 2026 · DOI 10.21203/rs.3.rs-9268042/v1

Open PDFView at the publisherCite this paper

In brief

“Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning” is a 2026 preprint by Yu Weng and 10 co-authors, published in Research Square. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.

Citations
0
References
86
Authors
11

Abstract

Deep learning (DL) has emerged as a transformative tool in atmospheric science, demonstrating particular efficacy in El Niño-Southern Oscillation (ENSO) prediction by achieving accurate forecasts with a notable lead time. Nevertheless, the adoption of DL-based ENSO forecasting models remains constrained by insufficient physical interpretability. In this study, we leveraged the linkage between sea subsurface temperature (SUBT) propagation and ENSO development—namely, a propagation loop in equatorial/extra-equatorial Pacific subsurface temperatures where anomaly signals propagate over timescales matching ENSO interannual recurrence—to develop two physically constrained, lightweight, and generalizable DL models for ENSO prediction: (i) a Convolutional Neural Network (CNN) architecture integrated with a Convolutional Block Attention Module (CBAM), and (ii) a ConvTransformer model built upon this CNN framework. These models effectively reconstruct SUBT anomaly propagation and skillfully forecast the Niño3.4 index at 18-month lead times. Guided by the physical interpretation of the ConvTransformer model using Integrated Gradients, we proposed a novel ENSO stage partitioning scheme that is physically consistent with the propagation of SUBT anomaly, providing a robust explanation for the onset, evolution, and transition of El Niño and La Niña events within a unified dynamical framework. This DL-derived scheme not only enhances forecast reliability but also offers new insights into the subsurface-driven mechanisms underlying ENSO variability and predictability.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Weng, Y., Zhi, X., Wang, J., Zhang, L., Lyu, Y., Ji, Y., Cao, Y., Zhu, S., Fraedrich, K., Kong, D., & Zhou, L. (2026). Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning. Research Square. https://doi.org/10.21203/rs.3.rs-9268042/v1

MLA 9

Weng, Yu, et al. “Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-9268042/v1.

Chicago

Weng, Yu, Xiefei Zhi, Jingyu Wang, Ling Zhang, Yang Lyu, Yan Ji, Yunchang Cao, et al. 2026. “Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning.” Research Square. https://doi.org/10.21203/rs.3.rs-9268042/v1.

Harvard

Weng, Y. et al. (2026) ‘Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning’, Research Square. doi:10.21203/rs.3.rs-9268042/v1.

IEEE

Y. Weng et al., “Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning,” Research Square, 2026, doi: 10.21203/rs.3.rs-9268042/v1.

BibTeX

@misc{weng2026extending,
  title     = {{Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning}},
  author    = {Weng, Yu and Zhi, Xiefei and Wang, Jingyu and Zhang, Ling and Lyu, Yang and Ji, Yan and Cao, Yunchang and Zhu, Shoupeng and Fraedrich, Klaus and Kong, Dexuan and Zhou, Liqun},
  howpublished = {Research Square},
  year      = {2026},
  doi       = {10.21203/rs.3.rs-9268042/v1},
  url       = {https://doi.org/10.21203/rs.3.rs-9268042/v1}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models

  • ENSO prediction
  • ENSO
  • Niño 3.4 index
  • long lead time forecasting
  • integrated gradients
  • El Niño/La Niña

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Weng, Y., Zhi, X., Wang, J., Zhang, L., Lyu, Y., Ji, Y., Cao, Y., Zhu, S., Fraedrich, K., Kong, D., & Zhou, L. (2026). Extending ENSO Prediction beyond 18 Months through Stage-consistent Ocean Internal Dynamics Based on Deep Learning. Research Square. https://doi.org/10.21203/rs.3.rs-9268042/v1

How many times has this paper been cited?

0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Research Square: sign in and open the PDF from this page.

Who wrote this paper?

Yu Weng, Xiefei Zhi, Jingyu Wang, Ling Zhang, Yang Lyu, Yan Ji, Yunchang Cao, Shoupeng Zhu, Klaus Fraedrich, Dexuan Kong, Liqun Zhou.

What is the DOI of this paper?

10.21203/rs.3.rs-9268042/v1, permanently at https://doi.org/10.21203/rs.3.rs-9268042/v1. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.