[A-TT35] Machine Learning Techniques in Weather, Climate, Ocean, Hydrology and Disease Predictions

[ATT35-10] Real-time predictions of the 2023–2025 climate conditions in the tropical Pacific using a purely data-driven Transformer model

*Rong-Hua Zhang¹、Lu Zhou¹、Jiaxiang Gao¹、Hai Zhi¹、Lingjiang Tao¹ (1.Nanjing University of Information Science and Technology)

キーワード：Transformer model, 3D-Geoformer, coupling representation, the 2023–2024 El Niño, real-time prediction, performance and evaluation

Following triple La Niña events during 2020–2022, the future evolution of climate conditions over the tropical Pacific has been a focused interest in ENSO-related communities. Observations and modeling studies indicate that an El Niño event is occurring in 2023; however, large uncertainties remain in terms of its detailed evolution, and the factors affecting its resultant amplitude remain to be understood. Here, a novel deep learning-based Transformer model is adopted to make real-time predictions for the 2023–2025 climate conditions in the tropical Pacific. Several key fields vital to the El Niño and Southern Oscillation (ENSO) in the tropical Pacific are collectively and simultaneously utilized in model training and in making predictions; therefore, this purely data-driven model is configured in both training and predicting procedures such that the coupled ocean-atmosphere interactions are adequately represented. Also similar to dynamic models, the prediction procedure is executed in a rolling manner to allow ocean-atmosphere anomaly exchanges month by month; the related key fields during multi-month time intervals (TIs) prior to prediction target months are taken as input predictors, serving as initial conditions to precondition the future evolution more effectively. Real-time predictions indicate that the climate conditions in the tropical Pacific are surely to develop into an El Niño state in late 2023. Furthermore, sensitivity experiments are conducted to examine how prediction skills are affected by the input predictor specifications, including TIs during which information on initial conditions is retained for making predictions. A comparison with other dynamic coupled models is also made to demonstrate the prediction performance for the 2023-2024 El Niño event.