Skip to main content
Springer Nature Link
Log in

Learning the coupled dynamics of global climate modes

  • Article
  • Published:
Save article
View saved research

From Nature Machine Intelligence

View current issue Submit your manuscript

Abstract

Global weather extremes, from monsoons to droughts, are shaped by a network of recurrent, coupled ocean–atmosphere patterns known as climate modes. These modes, spanning from the Pacific’s El Niño-Southern Oscillation to interconnected patterns in the Indian and Atlantic Oceans, form a dynamically linked global system governed by complex nonlinear interactions. Holistically forecasting this interconnected system—rather than treating modes in isolation or in simplified pairs as existing approaches do—remains a fundamental challenge in machine intelligence for complex systems. Here we introduce UniCM, a unified deep model for global climate modes forecasting. Its key innovation lies in a dual-branch architecture that learns the dynamics of a coupled system directly from data, achieving a truly unified prediction through the synergistic modelling of localized dynamics and their collective global couplings. UniCM achieves strong performance in unified global climate-mode forecasting, outperforming strong existing baselines and extending the skilful forecast lead time across multiple major climate modes. It successfully captured the diversity of historical events, from the extreme 1997–1998 El Niño to the prolonged and challenging 2020–2023 triple-dip La Niña. Beyond accuracy, UniCM offers interpretability; its internal attention mechanism identifies dynamic precursors and quantifies the structured inter-mode interactions that precede extreme climate events. Our results demonstrate that learning the coupled dynamics of climate modes as an interconnected system unlocks emergent predictability, laying a foundation for unified forecasting and data-driven insights that deepen our understanding of global ocean–atmosphere dynamics.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price includes VAT (Spain)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1: Overview of the UniCM architecture.
The alternative text for this image may have been generated using AI.
Fig. 2: ENSO forecast performance of UniCM.
The alternative text for this image may have been generated using AI.
Fig. 3: UniCM’s performance on forecasting global climate modes.
The alternative text for this image may have been generated using AI.
Fig. 4: Spatial prediction skill of SST across different lead times.
The alternative text for this image may have been generated using AI.
Fig. 5: UniCM’s attention mechanism reveals event-specific precursors to major ENSO events.
The alternative text for this image may have been generated using AI.

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

Data availability

All datasets used in this study are publicly available. The CMIP6 data are available from https://cds.climate.copernicus.eu/datasets/projections-cmip6; the ORAS5 data are available from the Climate Data Store (CDS) at https://cds.climate.copernicus.eu/datasets/reanalysis-oras5; the ERA5 data are available from CDS at https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels-monthly-means; the GODAS data are available from the National Oceanic Atmospheric Administration Physical Science Laboratory at https://psl.noaa.gov/data/gridded/data.godas.html; and the SODA data are available from the SODA project at https://soda.umd.edu/.

Code availability

The source code for UniCM is publicly available via GitHub at https://github.com/tsinghua-fib-lab/UniCM-Global-Climate-Modes and via Zenodo at https://doi.org/10.5281/zenodo.19173780 (ref. 67).

References

  1. Lobell, D. B., Schlenker, W. & Costa-Roberts, J. Climate trends and global crop production since 1980. Science 333, 616–620 (2011).

    Article  Google Scholar 

  2. Dettinger, M. D. & Diaz, H. F. Global characteristics of stream flow seasonality and variability. J. Hydrometeorol. 1, 289–310 (2000).

    Article  Google Scholar 

  3. Bracco, A. et al. Machine learning for the physics of climate. Nat. Rev. Phys. 7, 6–20 (2025).

    Article  Google Scholar 

  4. Philander, S. G. H. El Nino Southern Oscillation phenomena. Nature 302, 295–301 (1983).

    Article  Google Scholar 

  5. IPCC Climate Change 2021: The Physical Science Basis (eds Masson-Delmotte, V. et al.) (Cambridge Univ. Press, 2021).

  6. Deser, C., Alexander, M. A., Xie, S.-P. & Phillips, A. S. Sea surface temperature variability: patterns and mechanisms. Annu. Rev. Mar. Sci. 2, 115–143 (2010).

    Article  Google Scholar 

  7. McPhaden, M. J., Zebiak, S. E. & Glantz, M. H. ENSO as an integrating concept in earth science. Science 314, 1740–1745 (2006).

    Article  Google Scholar 

  8. Timmermann, A. et al. El Niño–Southern Oscillation complexity. Nature 559, 535–545 (2018).

    Article  Google Scholar 

  9. Cai, W. et al. Changing El Niño–Southern Oscillation in a warming climate. Nat. Rev. Earth Environ. 2, 628–644 (2021).

    Article  Google Scholar 

  10. Zhou, L. & Zhang, R.-H. A self-attention–based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions. Sci. Adv. 9, eadf2827 (2023).

    Article  Google Scholar 

  11. Saji, N., Goswami, B. N., Vinayachandran, P. & Yamagata, T. A dipole mode in the tropical Indian Ocean. Nature 401, 360–363 (1999).

    Article  Google Scholar 

  12. Webster, P. J., Moore, A. M., Loschnigg, J. P. & Leben, R. R. Coupled ocean–atmosphere dynamics in the Indian Ocean during 1997–98. Nature 401, 356–360 (1999).

    Article  Google Scholar 

  13. Zhao, S. et al. Explainable El Niño predictability from climate mode interactions. Nature 630, 891–898 (2024).

    Article  Google Scholar 

  14. Shaw, T. A. & Stevens, B. The other climate crisis. Nature 639, 877–887 (2025).

    Article  Google Scholar 

  15. Cai, W. et al. Pantropical climate interactions. Science 363, eaav4236 (2019).

    Article  Google Scholar 

  16. Jin, Y. et al. The Indian Ocean weakens the ENSO spring predictability barrier: role of the Indian Ocean basin and dipole modes. J. Clim. 36, 8331–8345 (2023).

    Article  Google Scholar 

  17. Jo, H.-S. et al. Southern Indian Ocean dipole as a trigger for Central Pacific El Niño since the 2000s. Nat. Commun. 13, 6965 (2022).

    Article  Google Scholar 

  18. Alexander, M. A., Shin, S.-I. & Battisti, D. S. The influence of the trend, basin interactions, and ocean dynamics on tropical ocean prediction. Geophys. Res. Lett. 49, e2021GL096120 (2022).

    Article  Google Scholar 

  19. Cai, W., Van Rensch, P., Cowan, T. & Hendon, H. H. Teleconnection pathways of ENSO and the IOD and the mechanisms for impacts on Australian rainfall. J. Clim. 24, 3910–3923 (2011).

    Article  Google Scholar 

  20. Dijkstra, H. A. Nonlinear Climate Dynamics (Cambridge Univ. Press, 2013).

  21. Chiang, J. C. & Vimont, D. J. Analogous Pacific and Atlantic meridional modes of tropical atmosphere–ocean variability. J. Clim. 17, 4143–4158 (2004).

    Article  Google Scholar 

  22. Vos, E., Huybers, P. & Tziperman, E. Climate change alters teleconnections. Geophys. Res. Lett. 53, e2025GL119307 (2026).

    Article  Google Scholar 

  23. Ling, F. et al. Multi-task machine learning improves multi-seasonal prediction of the Indian Ocean dipole. Nat. Commun. 13, 7681 (2022).

    Article  Google Scholar 

  24. Luo, J.-J. et al. Interaction between El Nino and extreme Indian Ocean dipole. J. Clim. 23, 726–742 (2010).

    Article  Google Scholar 

  25. Zhang, Z. et al. Enhancing the predictability limits of ENSO with physics-guided deep echo state networks. NPJ Clim. Atmos. Sci. 9, 92 (2026).

  26. Wang, B. et al. Understanding the recent increase in multiyear La Niñas. Nat. Clim. Change 13, 1075–1081 (2023).

    Article  Google Scholar 

  27. Heede, U. K. & Fedorov, A. V. Colder eastern Equatorial Pacific and stronger Walker circulation in the early 21st century: separating the forced response to global warming from natural variability. Geophys. Res. Lett. 50, e2022GL101020 (2023).

    Article  Google Scholar 

  28. Jiang, S., Zhu, C., Hu, Z.-Z., Jiang, N. & Zheng, F. Triple-dip La Niña in 2020–23: understanding the role of the annual cycle in tropical Pacific SST. Environ. Res. Lett. 18, 084002 (2023).

    Article  Google Scholar 

  29. Liang, Y., Xie, S.-P., Fedorov, A. & Yeager, S. G. North pacific meridional mode has larger impacts on El Niño evolution than the March Madden–Julian oscillation. Sci. Adv. 11, eadv8621 (2025).

    Article  Google Scholar 

  30. Bassett, D. S. & Sporns, O. Network neuroscience. Nat. Neurosci. 20, 353–364 (2017).

    Article  Google Scholar 

  31. Helbing, D. Globally networked risks and how to respond. Nature 497, 51–59 (2013).

    Article  Google Scholar 

  32. Allesina, S. & Tang, S. Stability criteria for complex ecosystems. Nature 483, 205–208 (2012).

    Article  Google Scholar 

  33. Reichstein, M. et al. Deep learning and process understanding for data-driven earth system science. Nature 566, 195–204 (2019).

    Article  Google Scholar 

  34. Ham, Y.-G., Kim, J.-H. & Luo, J.-J. Deep learning for multi-year ENSO forecasts. Nature 573, 568–572 (2019).

    Article  Google Scholar 

  35. Lyu, P. et al. Resonet: robust and explainable ENSO forecasts with hybrid convolution and transformer networks. Adv. Atmos. Sci. 41, 1289–1298 (2024).

    Article  Google Scholar 

  36. Duan, W., Liu, X., Zhu, K. & Mu, M. Exploring the initial errors that cause a significant ‘spring predictability barrier’ for El Niño events. J. Geophys. Res. Oceans 114, C04022 (2009).

    Article  Google Scholar 

  37. Jin, F.-F. An equatorial ocean recharge paradigm for ENSO. Part I: conceptual model. J. Atmos. Sci. 54, 811–829 (1997).

    Article  Google Scholar 

  38. Ashok, K., Behera, S. K., Rao, S. A., Weng, H. & Yamagata, T. El Niño Modoki and its possible teleconnection. J. Geophys. Res. Oceans 112, (2007).

  39. Kao, H.-Y. & Yu, J.-Y. Contrasting Eastern-Pacific and Central-Pacific types of ENSO. J. Clim. 22, 615–632 (2009).

    Article  Google Scholar 

  40. Simpson, I. R. et al. Confronting Earth system model trends with observations. Sci. Adv. 11, eadt8035 (2025).

    Article  Google Scholar 

  41. Ham, Y.-G., Kug, J.-S., Park, J.-Y. & Jin, F.-F. Sea surface temperature in the north tropical Atlantic as a trigger for El Niño/Southern Oscillation events. Nat. Geosci. 6, 112–116 (2013).

    Article  Google Scholar 

  42. Guo, F., Liu, Q., Yang, J. & Fan, L. Three types of Indian Ocean basin modes. Clim. Dyn. 51, 4357–4370 (2018).

    Article  Google Scholar 

  43. Zhang, H., Clement, A. & Di Nezio, P. The South Pacific meridional mode: a mechanism for ENSO-like variability. J. Clim. 27, 769–783 (2014).

    Article  Google Scholar 

  44. Chen, L. et al. A machine learning model that outperforms conventional global subseasonal forecast models. Nat. Commun. 15, 6425 (2024).

    Article  Google Scholar 

  45. Wang, L. et al. Cas-Canglong: a skillful 3D transformer model for sub-seasonal to seasonal global sea surface temperature prediction. Preprint at https://doi.org/10.48550/arXiv.2409.05369 (2024).

  46. Alexander, M. A. et al. The atmospheric bridge: the influence of ENSO teleconnections on air–sea interaction over the global oceans. J. Clim. 15, 2205–2231 (2002).

    Article  Google Scholar 

  47. Schwing, F. B., Murphree, T., deWitt, L. & Green, P. M. The evolution of oceanic and atmospheric anomalies in the Northeast Pacific during the El Niño and La Niña events of 1995–2001. Prog. Oceanogr. 54, 459–491 (2002).

    Article  Google Scholar 

  48. Fan, J., Meng, J., Ashkenazy, Y., Havlin, S. & Schellnhuber, H. J. Network analysis reveals strongly localized impacts of El Niño. Proc. Natl Acad. Sci. USA 114, 7543–7548 (2017).

    Article  Google Scholar 

  49. Meng, J. et al. Complexity-based approach for El Niño magnitude forecasting before the spring predictability barrier. Proc. Natl Acad. Sci. USA 117, 177–183 (2020).

    Article  Google Scholar 

  50. Chen, Y. et al. Combined dynamical-deep learning ENSO forecasts. Nat. Commun. 16, 3845 (2025).

    Article  Google Scholar 

  51. Zscheischler, J. et al. Future climate risk from compound events. Nat. Clim. Change 8, 469–477 (2018).

    Article  Google Scholar 

  52. AghaKouchak, A. et al. Climate extremes and compound hazards in a warming world. Annu. Rev. Earth Planet. Sci. 48, 519–548 (2020).

    Article  Google Scholar 

  53. Raymond, C. et al. Understanding and managing connected extreme events. Nat. Clim. Change 10, 611–621 (2020).

    Article  Google Scholar 

  54. McKenna, S., Santoso, A., Gupta, A. S., Taschetto, A. S. & Cai, W. Indian Ocean dipole in CMIP5 and CMIP6: characteristics, biases, and links to ENSO. Sci. Rep. 10, 11500 (2020).

    Article  Google Scholar 

  55. Yang, Y. et al. Seasonality and predictability of the Indian Ocean dipole mode: ENSO forcing and internal variability. J. Clim. 28, 8021–8036 (2015).

    Article  Google Scholar 

  56. Zhang, C. Madden–Julian oscillation. Rev. Geophys. 43, (2005).

  57. Rahmstorf, S. Ocean circulation and climate during the past 120,000 years. Nature 419, 207–214 (2002).

    Article  Google Scholar 

  58. Buckley, M. W. & Marshall, J. Observations, inferences, and mechanisms of the Atlantic meridional overturning circulation: a review. Rev. Geophys. 54, 5–63 (2016).

    Article  Google Scholar 

  59. Schmidt, M. & Lipson, H. Distilling free-form natural laws from experimental data. Science 324, 81–85 (2009).

    Article  Google Scholar 

  60. Udrescu, S.-M. & Tegmark, M. AI Feynman: a physics-inspired method for symbolic regression. Sci. Adv. 6, eaay2631 (2020).

    Article  Google Scholar 

  61. Camps-Valls, G. et al. Discovering causal relations and equations from data. Phys. Rep. 1044, 1–68 (2023).

    Article  MathSciNet  Google Scholar 

  62. Zanna, L. & Bolton, T. Data-driven equation discovery of ocean mesoscale closures. Geophys. Res. Lett. 47, e2020GL088376 (2020).

    Article  Google Scholar 

  63. Chinazzi, M. et al. The effect of travel restrictions on the spread of the 2019 novel coronavirus (COVID-19) outbreak. Science 368, 395–400 (2020).

    Article  Google Scholar 

  64. Rohr, R. P., Saavedra, S. & Bascompte, J. On the structural stability of mutualistic systems. Science 345, 1253497 (2014).

    Article  Google Scholar 

  65. Hirahara, S., Balmaseda, M. A., Boisseson, E. & Hersbach, H. Sea Surface Temperature and Sea Ice Concentration for ERA5 Vol. 26 (European Centre for Medium Range Weather Forecasts, 2016).

  66. Zuo, H., Balmaseda, M. A., Tietsche, S., Mogensen, K. & Mayer, M. The ECMWF operational ensemble reanalysis–analysis system for ocean and sea ice: a description of the system and assessment. Ocean Sci. 15, 779–808 (2019).

    Article  Google Scholar 

  67. Yuan, Y., Ding, J., Qiu, Z., Fan, J. & Li, Y. Code for learning the coupled dynamics of global climate modes. Zenodo https://doi.org/10.5281/zenodo.19173780 (2026).

Download references

Acknowledgements

This work was supported in part by the National Key Research and Development Program of China (grant no. 2024YFC3307603), the National Natural Science Foundation of China (grant no. 62476152) and the Tsinghua–Toyota Joint Research Institute Interdisciplinary Program to Y.L. and J.D. J.F. received support from the National Natural Science Foundation of China (grant nos. T2525011, 42450183, 12275020, 12135003 and 42461144209) and the National Key R&D Program of China (grant no. 2025YFF0517203). J.F. acknowledges support from the Fundamental Research Funds for the Central Universities.

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, Tsinghua University, Beijing, China

    Yuan Yuan, Jingtao Ding & Yong Li

  2. Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China

    Yuan Yuan, Jingtao Ding & Yong Li

  3. School of Systems Science, Beijing Normal University, Beijing, China

    Zhongpu Qiu & Jingfang Fan

  4. Potsdam Institute for Climate Impact Research (PIK), Potsdam, Germany

    Jingfang Fan

Authors
  1. Yuan Yuan
    View author publications

    Search author on:PubMed Google Scholar

  2. Jingtao Ding
    View author publications

    Search author on:PubMed Google Scholar

  3. Zhongpu Qiu
    View author publications

    Search author on:PubMed Google Scholar

  4. Jingfang Fan
    View author publications

    Search author on:PubMed Google Scholar

  5. Yong Li
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Y.L. and J.F. conceived of the main theme of the research idea. Y.Y. collected the data, designed the model, conducted the experiments and wrote the first draft of the paper. J.D., Z.Q., J.F. and Y.L. provided crucial feedback. All authors reviewed, edited and approved the final version of the paper.

Corresponding authors

Correspondence to Jingfang Fan or Yong Li.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Annalisa Bracco, Maximilian Gelbrecht and Jing-Jia Luo for their contribution to the peer review of this work. Peer reviewer reports are available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information (download PDF )

Supplementary Notes (Sections 1–6), Tables 1–4, Figs. 1–41 and References.

Peer Review File (download PDF )

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yuan, Y., Ding, J., Qiu, Z. et al. Learning the coupled dynamics of global climate modes. Nat Mach Intell (2026). https://doi.org/10.1038/s42256-026-01245-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s42256-026-01245-5

  • Springer Nature Limited

Profiles

  1. Jingtao Ding View author profile
  2. Yong Li View author profile