Articles | Volume 19, issue 5
https://doi.org/10.5194/gmd-19-1917-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-1917-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
06 Mar 2026
Model description paper |
| 06 Mar 2026
| 06 Mar 2026
Assessing seasonal climate predictability using a deep learning application: NN4CAST
Departamento de Física de la Tierra y Astrofísica, Universidad Complutense de Madrid, Madrid, Spain
Belén Rodríguez-Fonseca
CORRESPONDING AUTHOR
Departamento de Física de la Tierra y Astrofísica, Universidad Complutense de Madrid, Madrid, Spain
Instituto de Geociencias, Consejo Superior de Investigaciones Científicas, Madrid, Spain
Irene Polo
Departamento de Física de la Tierra y Astrofísica, Universidad Complutense de Madrid, Madrid, Spain
Marta Martín-Rey
Departamento de Física de la Tierra y Astrofísica, Universidad Complutense de Madrid, Madrid, Spain
María N. Moreno-García
Departamento de Informática y Automática, Universidad de Salamanca, Salamanca, Spain
Related authors
Víctor Galván Fraile, Belén Rodríguez-Fonseca, Irene Polo, Marta Martín-Rey, and María N. Moreno-García
EGUsphere, https://doi.org/10.5194/egusphere-2024-2897, https://doi.org/10.5194/egusphere-2024-2897, 2024
Preprint archived
Short summary
Short summary
Dynamical models often struggle with complex interactions in remote regions, leading to reduced accuracy. To address this, statistical models that identify relationships between predictors and predictands are valuable. NN4CAST, our deep learning model, enhances seasonal predictions by capturing these dynamics effectively, especially in challenging regions like the North Atlantic. This advancement could benefit critical sectors including marine ecosystems, public health, and energy management.
Pablo Duran-Fonseca and Belén Rodríguez-Fonseca
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-164, https://doi.org/10.5194/gmd-2024-164, 2024
Revised manuscript not accepted
Short summary
Short summary
This paper describes the first release of Spy4Cast, a python interface to run a maximum covariance analysis model to produce seasonal forecast. This API allows the user to increase automation and productivity, including determination of modes, crossvalidation hindcast and validation. It includes a visualisation module for the results as well as a preprocessing tool that can be also used for other climate variability studies.
Víctor Galván Fraile, Belén Rodríguez-Fonseca, Irene Polo, Marta Martín-Rey, and María N. Moreno-García
EGUsphere, https://doi.org/10.5194/egusphere-2024-2897, https://doi.org/10.5194/egusphere-2024-2897, 2024
Preprint archived
Short summary
Short summary
Dynamical models often struggle with complex interactions in remote regions, leading to reduced accuracy. To address this, statistical models that identify relationships between predictors and predictands are valuable. NN4CAST, our deep learning model, enhances seasonal predictions by capturing these dynamics effectively, especially in challenging regions like the North Atlantic. This advancement could benefit critical sectors including marine ecosystems, public health, and energy management.
Cited articles
Alexander, M. A., Bladé, I., Newman, M., Lanzante, J. R., Lau, N.-C., and Scott, J. D.: The atmospheric bridge: The influence of ENSO teleconnections on air–sea interaction over the global oceans, J. Climate, 15, 2205–2231, https://doi.org/10.1175/1520-0442(2002)015<2205:TABTIO>2.0.CO;2, 2002. a, b, c
Alvarez-Ramirez, J., Rodriguez, E., and Echeverría, J. C.: Detrending fluctuation analysis based on moving average filtering, Physica A, 354, 199–219, https://doi.org/10.1016/j.physa.2005.03.012, 2005. a
Bachèlery, M.-L., Brajard, J., Patacchiola, M., Illig, S., and Keenlyside, N.: Predicting Atlantic and Benguela Niño events with deep learning, Sci. Adv., 11, eads5185, https://doi.org/10.1126/sciadv.ads5185, 2025. a
Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., and Tian, Q.: Accurate medium-range global weather forecasting with 3D neural networks, Nature, 619, 533–538, https://doi.org/10.1038/s41586-023-06185-3, 2023. a
Branstator, G.: Circumglobal teleconnections, the jet stream waveguide, and the North Atlantic Oscillation, J. Climate, 15, 1893–1910, https://doi.org/10.1175/1520-0442(2002)015<1893:CTTJSW>2.0.CO;2, 2002. a
Calvo-Miguélez, E., Rodríguez-Fonseca, B., Galván-Fraile, V., and Gómara, I.: Predicting Chlorophyll-a in the Mauritanian–Senegalese Coastal Upwelling from Tropical Sea Surface Temperature, Oceans, 6, 81, https://doi.org/10.3390/oceans6040081, 2025. a
Chang, P., Ji, L., and Saravanan, R.: A hybrid coupled model study of tropical Atlantic variability, J. Climate, 14, 361–390, https://doi.org/10.1175/1520-0442(2001)013<0361:AHCMSO>2.0.CO;2, 2001. a
Cuomo, S., Di Cola, V. S., Giampaolo, F., Rozza, G., Raissi, M., and Piccialli, F.: Scientific machine learning through physics–informed neural networks: Where we are and what's next, J. Sci. Comput., 92, 88, https://doi.org/10.1007/s10915-022-01939-z, 2022. a
Czaja, A., Van der Vaart, P., and Marshall, J.: A diagnostic study of the role of remote forcing in tropical Atlantic variability, J. Climate, 15, 3280–3290, https://doi.org/10.1175/1520-0442(2002)015<3280:ADSOTR>2.0.CO;2, 2002. a, b
Doblas-Reyes, F. J., García-Serrano, J., Lienert, F., Biescas, A. P., and Rodrigues, L. R.: Seasonal climate predictability and forecasting: status and prospects, Wiley Interdisciplin. Rev.: Clim. Change, 4, 245–268, https://doi.org/10.1002/wcc.217, 2013. a, b
Enfield, D. B. and Mayer, D. A.: Tropical Atlantic sea surface temperature variability and its relation to El Niño-Southern Oscillation, J. Geophys. Res.-Oceans, 102, 929–945, https://doi.org/10.1029/96JC03296, 1997. a, b
Galván Fraile, V., Martín-Rey, M., Rodríguez-Fonseca, B., Polo, I., and Navarro-García, M.: NN4CASTv1.0.20, Zenodo [code], https://doi.org/10.5281/zenodo.14011998, 2024 (code also available at: (https://github.com/Victorgf00/nn4cast, last access: 4 March 2026). a
Galván Fraile, V., Martín-Rey, M., Rodríguez-Fonseca, B., Polo, I., and Navarro-García, M.: NN4CAST_manual, Zenodo [data set], https://doi.org/10.5281/zenodo.17287629, 2025. a
García-Serrano, J., Cassou, C., Douville, H., Giannini, A., and Doblas-Reyes, F. J.: Revisiting the ENSO teleconnection to the tropical North Atlantic, J. Climate, 30, 6945–6957, https://doi.org/10.1175/JCLI-D-16-0641.1, 2017. a, b, c
Géron, A.: Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly Media, Inc., ISBN 1492032646, 2022. a
Gill, A. E.: Some simple solutions for heat-induced tropical circulation, Q. J. Roy. Meteorol. Soc., 106, 447–462, https://doi.org/10.1002/qj.49710644905, 1980. a
Gleckler, P. J., Taylor, K. E., and Doutriaux, C.: Performance metrics for climate models, J. Geophys. Res., 113, https://doi.org/10.1029/2007JD008972, 2008. a
Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y.: Deep learning, in: vol. 1, MIT Press, Cambridge, ISBN 0262035618, 2016. a
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., and Pedreschi, D.: A survey of methods for explaining black box models, ACM Comput. Surv. (CSUR), 51, 1–42, https://doi.org/10.1145/3236009, 2018. a
Ham, Y.-G., Kim, J.-H., and Luo, J.-J.: Deep learning for multi-year ENSO forecasts, Nature, 573, 568–572, https://doi.org/10.1038/s41586-019-1559-7, 2019. a
Hargreaves, J. C.: Skill and uncertainty in climate models, Wiley Interdisciplin. Rev.: Clim. Change, 1, 556–564, https://doi.org/10.1002/wcc.58, 2010. a
Harris, I., Osborn, T. J., Jones, P., and Lister, D.: Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset, Sci. Data, 7, 109, https://doi.org/10.1038/s41597-020-0453-3, 2020. a
He, K., Zhang, X., Ren, S., and Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE international conference on computer vision, 1026–1034, https://doi.org/10.1109/ICCV.2015.123, 2015. a
Hinton, G. E. and Salakhutdinov, R. R.: Reducing the dimensionality of data with neural networks, Science, 313, 504–507, https://doi.org/10.1126/science.1127647, 2006. a
Horel, J. D. and Wallace, J. M.: Planetary-scale atmospheric phenomena associated with the Southern Oscillation, Mon. Weather Rev., 109, 813–829, https://doi.org/10.1175/1520-0493(1981)109<0813:PSAPAW>2.0.CO;2, 1981. a
Hou, J., Fang, Z., and Geng, X.: Recent Strengthening of the ENSO Influence on the Early Winter East Atlantic Pattern, Atmosphere, 14, 1809, https://doi.org/10.3390/atmos14121809, 2023. a
Ibebuchi, C. C. and Richman, M. B.: Deep learning with autoencoders and LSTM for ENSO forecasting, Clim. Dynam., 62, 5683–5697, https://doi.org/10.1007/s00382-024-07180-8, 2024. a
Ineson, S. and Scaife, A.: The role of the stratosphere in the European climate response to El Niño, Nat. Geosci., 2, 32–36, https://doi.org/10.1038/ngeo381, 2009. a
Johnson, S. J., Stockdale, T. N., Ferranti, L., Balmaseda, M. A., Molteni, F., Magnusson, L., Tietsche, S., Decremer, D., Weisheimer, A., and Balsamo, G.: SEAS5: the new ECMWF seasonal forecast system, Geosci. Model Dev., 12, 1087–1117, https://doi.org/10.5194/gmd-12-1087-2019, 2019. a
Kent, C., Scaife, A. A., Dunstone, N. J., Smith, D., Hardiman, S. C., Dunstan, T., and Watt-Meyer, O.: Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data, npj Clim. Atmos. Sci., 8, 314, https://doi.org/10.1038/s41612-025-01198-3, 2025. a
Kirtman, B. and Pirani, A.: The state of the art of seasonal prediction: Outcomes and recommendations from the First World Climate Research Program Workshop on Seasonal Prediction, B. Am. Meteorol. Soc., 90, 455–458, https://doi.org/10.1175/2008BAMS2707.1, 2009. a
Klein, S. A., Soden, B. J., and Lau, N.-C.: Remote sea surface temperature variations during ENSO: Evidence for a tropical atmospheric bridge, J. Climate, 12, 917–932, https://doi.org/10.1175/1520-0442(1999)012<0917:RSSTVD>2.0.CO;2, 1999. a
Kochkov, D., Yuval, J., Langmore, I., Norgaard, P., Smith, J., Mooers, G., Klöwer, M., Lottes, J., Rasp, S., and Düben, P.: Neural general circulation models for weather and climate, Nature, 632, 1060–1066, https://doi.org/10.1038/s41586-024-07744-y, 2024. a
Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., and Hu, W.: Learning skillful medium-range global weather forecasting, Science, 382, 1416–1421, https://doi.org/10.1126/science.adi2336, 2023. a
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015. a
Lee, S.-K., Enfield, D. B., and Wang, C.: Why do some El Niños have no impact on tropical North Atlantic SST?, Geophys. Res. Lett., 35, https://doi.org/10.1029/2008GL034734, 2008. a, b
López-Parages, J., Rodríguez-Fonseca, B., and Terray, L.: A mechanism for the multidecadal modulation of ENSO teleconnection with Europe, Clim. Dynam., 45, 867–880, https://doi.org/10.1007/s00382-014-2319-x, 2015. a, b
Mamalakis, A., Barnes, E. A., and Ebert-Uphoff, I.: Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience, Artif. Intel. Earth Syst., 1, e220012, https://doi.org/10.1175/AIES-D-22-0012.1, 2022. a
Michaelsen, J.: Cross-validation in statistical climate forecast models, J. Appl. Meteorol. Clim., 26, 1589–1600, https://doi.org/10.1175/1520-0450(1987)026<1589:CVISCF>2.0.CO;2, 1987. a
Pan, B., Anderson, G. J., Goncalves, A., Lucas, D. D., Bonfils, C. J., and Lee, J.: Improving seasonal forecast using probabilistic deep learning, J. Adv. Model. Earth Syst., 14, e2021MS002766, https://doi.org/10.1029/2021MS002766, 2022. a
Poli, P., Hersbach, H., Dee, D. P., Berrisford, P., Simmons, A. J., Vitart, F., Laloyaux, P., Tan, D. G., Peubey, C., and Thépaut, J.-N.: ERA-20C: An atmospheric reanalysis of the twentieth century, J. Climate, 29, 4083–4097, https://doi.org/10.1175/JCLI-D-15-0556.1, 2016. a, b
Raffalovich, L. E.: Detrending time series: A cautionary note, Sociol. Meth. Res., 22, 492–519, https://doi.org/10.1177/0049124194022004003, 1994. a
Rawat, W. and Wang, Z.: Deep convolutional neural networks for image classification: A comprehensive review, Neural Comput., 29, 2352–2449, https://doi.org/10.1162/neco_a_00990, 2017. a
Rayner, N., Parker, D. E., Horton, E., Folland, C. K., Alexander, L. V., Rowell, D., Kent, E. C., and Kaplan, A.: Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century, J. Geophys. Res., 108, https://doi.org/10.1029/2002JD002670, 2003. a, b
Rew, R., Hartnett, E., and Caron, J.: NetCDF-4: Software implementing an enhanced data model for the geosciences, in: vol. 6, 22nd International Conference on Interactive Information Processing Systems for Meteorology, Oceanograph, and Hydrology, abstract no. A412, 2006. a
Richter, I. and Tokinaga, H.: An overview of the performance of CMIP6 models in the tropical Atlantic: mean state, variability, and remote impacts, Clim. Dynam., 55, 2579–2601, https://doi.org/10.1007/s00382-020-05409-w, 2020. a
Rieger, N., Corral, Á., Olmedo, E., and Turiel, A.: Lagged teleconnections of climate variables identified via complex rotated maximum covariance analysis, J. Climate, 34, 9861–9878, https://doi.org/10.1175/JCLI-D-21-0244.1, 2021. a
Righi, M., Andela, B., Eyring, V., Lauer, A., Predoi, V., Schlund, M., Vegas-Regidor, J., Bock, L., Brötz, B., and de Mora, L.: Earth System model evaluation tool (ESMValTool) v2.0 – technical overview, Geosci. Model Dev., 13, 1179–1199, https://doi.org/10.5194/gmd-13-1179-2020, 2020. a
Roberts, C., Vitart, F., and Balmaseda, M.: Hemispheric impact of North Atlantic SSTs in subseasonal forecasts, Geophys. Res. Lett., 48, e2020GL0911446, https://doi.org/10.1029/2020GL091446, 2021. a
Rodríguez-Fonseca, B., Suárez-Moreno, R., Ayarzagüena, B., López-Parages, J., Gómara, I., Villamayor, J., Mohino, E., Losada, T., and Castaño-Tierno, A.: A review of ENSO influence on the North Atlantic. A non-stationary signal, Atmosphere, 7, 87, https://doi.org/10.3390/atmos7070087, 2016. a
Rodwell, M. J., Rowell, D. P., and Folland, C. K.: Oceanic forcing of the wintertime North Atlantic Oscillation and European climate, Nature, 398, 320–323, https://doi.org/10.1038/18648, 1999. a
Rogers, J. C.: North Atlantic storm track variability and its association to the North Atlantic Oscillation and climate variability of northern Europe, J. Climate, 10, 1635–1647, https://doi.org/10.1175/1520-0442(1997)010<1635:NASTVA>2.0.CO;2, 1997. a
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, in: Medical image computing and computer-assisted intervention – MICCAI 2015: 18th international conference, proceedings, part III 18, 5–9 October 2015, Munich, Germany, Springer, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a
Russell, S. J. and Norvig, P.: Artificial intelligence: a modern approach, Pearson, ISBN 0136042597, 2016. a
Samuel, A. L.: Some studies in machine learning using the game of checkers, IBM J. Res. Dev., 3, 210–229, https://doi.org/10.1147/rd.33.0210, 1959. a
Schulzweida, U., Kornblueh, L., and Quast, R.: CDO user guide, Zenodo [data set], https://doi.org/10.5281/zenodo.3539275, 2019. a
Shin, N.-Y., Ham, Y.-G., Kim, J.-H., Cho, M., and Kug, J.-S.: Application of deep learning to understanding ENSO dynamics, Artif. Intel. Earth Syst., 1, e210011, https://doi.org/10.1175/AIES-D-21-0011.1, 2022. a
Shuila, J. and Kinter, J. L.: Predictability of seasonal climate variations: A pedagogical review, in: Predictability of weather and climate, vol. 306, Cambridge University Press, Cambridge, 341 pp., https://doi.org/10.1017/CBO9780511617652.013, 2006. a
Suárez-Moreno, R. and Rodríguez-Fonseca, B.: S4CAST v2.0: sea surface temperature based statistical seasonal forecast model, Geosci. Model Dev., 8, 3639–3658, https://doi.org/10.5194/gmd-8-3639-2015, 2015. a
Sundararajan, M., Taly, A., and Yan, Q.: Axiomatic attribution for deep networks, in: International conference on machine learning, PMLR, arXiv [preprint], 3319–3328, https://doi.org/10.48550/arXiv.1703.01365, 2017. a
Trigo, R. M., Osborn, T. J., and Corte-Real, J. M.: The North Atlantic Oscillation influence on Europe: climate impacts and associated physical mechanisms, Clim. Res., 20, 9–17, https://doi.org/10.3354/cr020009, 2002. a
Wade, M., Rodríguez-Fonseca, B., Martín-Rey, M., Lazar, A., López-Parages, J., and Gaye, A. T.: Interdecadal changes in SST variability drivers in the Senegalese-upwelling: the impact of ENSO, Clim. Dynam., 60, 667–685, https://doi.org/10.1007/s00382-022-06311-3, 2023. a
Watt-Meyer, O., Henn, B., McGibbon, J., Clark, S. K., Kwa, A., Perkins, W. A., Wu, E., Harris, L., and Bretherton, C. S.: ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses, arXiv [preprint], arXiv:2411.11268, https://doi.org/10.48550/arXiv.2411.11268, 2024. a
Weisheimer, A., Schaller, N., O'Reilly, C., MacLeod, D. A., and Palmer, T.: Atmospheric seasonal forecasts of the twentieth century: multi-decadal variability in predictive skill of the winter North Atlantic Oscillation (NAO) and their potential value for extreme event attribution, Q. J. Roy. Meteorol. Soc., 143, 917–926, https://doi.org/10.1002/qj.2976, 2017. a
Wilks, D. S.: Improved statistical seasonal forecasts using extended training data, Int. J. Climatol., 28, 1589–1598, https://doi.org/10.1002/joc.1661, 2008. a
Wilks, D. S.: Statistical methods in the atmospheric sciences, in: vol. 100, Academic Press, https://doi.org/10.1016/C2017-0-03921-6, 2011. a, b
Wilks, D. S.: Comparison of probabilistic statistical forecast and trend adjustment methods for North American seasonal temperatures, J. Appl. Meteorol. Clim., 53, 935–949, https://doi.org/10.1175/JAMC-D-13-0262.1, 2014. a
Wu, R., Lin, M., and Sun, H.: Impacts of different types of El Niño and La Niña on northern tropical Atlantic sea surface temperature, Clim. Dynam., 54, 4147–4167, https://doi.org/10.1007/s00382-020-05220-7, 2020. a
Short summary
We present a new deep learning framework designed to assess seasonal climate predictability by identifying the key predictors that influence climate variability across different regions. This tool enhances understanding of how remote areas are connected through climate interactions and providing accurate and explainable seasonal predictions. Our results demonstrate its potential to support more reliable and informed climate services at both regional and global scales.
We present a new deep learning framework designed to assess seasonal climate predictability by...
