The accumulated remote sensing data of altimeters and scatterometers have provided new opportunities for ocean state forecasting and have improved our knowledge of ocean–atmosphere exchanges. Studies on multivariate, multistep, spatiotemporal sequence forecasts of sea level anomalies (SLA) for different modalities, however, remain problematic. In this paper, we present a novel hybrid and multivariate deep neural network, named HMnet3, which can be used for SLA forecasting in the South China Sea (SCS). First, a spatiotemporal sequence forecasting network is trained by an improved convolutional long short-term memory (ConvLSTM) network using a channelwise attention mechanism and multivariate data from 1993 to 2015. Then a time series forecasting network is trained by an improved long short-term memory (LSTM) network, which is realized by ensemble empirical mode decomposition (EEMD). Finally, the two networks are combined by a successive correction method to produce SLA forecasts for lead times of up to 15 days, with a special focus on the open sea and coastal regions of the SCS. During the testing period of 2016–18, the performance of HMnet3 with sea surface temperature anomaly (SSTA), wind speed anomaly (SPDA), and SLA data is much better than those of state-of-the-art dynamic and statistical (ConvLSTM, persistence, and climatology) forecast models. Stricter testbeds for trial simulation experiments with real-time datasets are investigated, where the eddy classification metrics of HMnet3 are favorable for all properties, especially for those of small-scale eddies.

Ocean forecasting is critical for various applications and is essential for understanding air–sea interactions, which contribute to mitigating the impacts of extreme events. While data-driven forecasting models have demonstrated considerable potential and speed, they often primarily focus on spatial variations while neglecting temporal dynamics. This paper presents the TSformer, a novel non-autoregressive spatio-temporal transformer designed for medium-range ocean eddy-resolving forecasting, enabling forecasts of up to 30 days in advance. We introduce an innovative hierarchical U-Net encoder–decoder architecture based on 3D Swin Transformer blocks, which extends the scope of local attention computation from spatial to spatio-temporal contexts to reduce accumulation errors. The TSformer is trained on 28 years of homogeneous, high-dimensional 3D ocean reanalysis datasets, supplemented by three 2D remote sensing datasets for surface forcing. Based on the near-real-time operational forecast results from 2023, comparative performance assessments against in situ profiles and satellite observation data indicate that the TSformer exhibits forecast performance comparable to leading numerical ocean forecasting models while being orders of magnitude faster. Unlike autoregressive models, the TSformer maintains 3D consistency in physical motion, ensuring long-term coherence and stability. Furthermore, the TSformer model, which incorporates surface auxiliary observational data, effectively simulates the vertical cooling and mixing effects induced by Super Typhoon Saola.

Ocean forecasting is critical for various applications and is essential for understanding air-sea interactions, which contribute to mitigating the impacts of extreme events. State-of-the-art ocean numerical forecasting systems can offer lead times of up to 10 days with a spatial resolution of 10 kilometers, although they are computationally expensive. While data-driven forecasting models have demonstrated considerable potential and speed, they often primarily focus on spatial variations while neglecting temporal dynamics. This paper presents TSformer, a novel non-autoregressive spatiotemporal transformer designed for medium-range ocean eddy-resolving forecasting, enabling forecasts of up to 30 days in advance. We introduce an innovative hierarchical U-Net encoder-decoder architecture based on 3D Swin Transformer blocks, which extends the scope of local attention computation from spatial to spatiotemporal contexts to reduce accumulation errors. TSformer is trained on 28 years of homogeneous, high-dimensional 3D ocean reanalysis datasets, supplemented by three 2D remote sensing datasets for surface forcing. Based on the near-real-time operational forecast results from 2023, comparative performance assessments against in situ profiles and satellite observation data indicate that, TSformer exhibits forecast performance comparable to leading numerical ocean forecasting models while being orders of magnitude faster. Unlike autoregressive models, TSformer maintains 3D consistency in physical motion, ensuring long-term coherence and stability in extended forecasts. Furthermore, the TSformer model, which incorporates surface auxiliary observational data, effectively simulates the vertical cooling and mixing effects induced by Super Typhoon Saola.

El Niño-Southern Oscillation (ENSO) is the dominant atmosphere-ocean coupled mode of year-to-year variations in the tropical Pacific. It shows diverse spatiotemporal characteristics and casts major influences on seasonal predictions of global weather-climate extrema. Despite numerous dynamical and statistical models for ENSO prediction and predictability studies, they are commonly subjected to one-to-three issues among less skillful simulation of El Niño diversity, huge requirements of computational resources and a low robustness in statistics. Here, an efficient deep-learning model involving nonlinear coupling of multiple variables is independently developed to study the predictability of two types of El Niño events related to initial uncertainty, which is the first kind of predictability problem. The model can skillfully simulate statistically robust features of observed El Niño diversity in terms of periodicity, amplitude, and seasonal phase-locking. Using this model, we have revealed mathematically several new types of fastest-growing initial errors in two types of El Niño predictions based on a novel concept of conditional nonlinear optimal perturbation (CNOP), especially including one that can strengthen central Pacific types of events, which is rarely investigated before. Moreover, CNOPs are superimposed into a numerical model, GFDL CM2p1, for comprehensive validation and growth mechanism mining, which demonstrates the consistent dynamical evolution of initial errors in both numerical and AI models. Our study represents the first attempt to explore the first kind of ENSO predictability problem from perspectives of nonlinear error-evolving dynamics using a data-driven model. This is of great importance as it offers us sufficient confidence to perform ENSO-related (such as the Madden-Julian Oscillation, etc) mechanisms and predictability studies in the future without strongly relying on dynamical numerical models.

Intraseasonal variations of sea surface temperature (SST) in the South China Sea (SCS) during winter are investigated by using atmospheric and oceanic reanalysis in this study. The dominant pattern of SST variations within the 10–90-day timescale is derived by empirical orthogonal function analysis, which features a basin-wide warming or cooling spatial pattern, with a cycle period of 30–35 days. Composite analysis and mixed-layer heat budget analysis are conducted to investigate the physical process controlling SST variability. The formation of intraseasonal SST variations is primarily attributable to the forcing of wind-related latent heat flux and shortwave radiation flux changes. During the warming (cooling) period, anomalous southerly (northerly) winds tend to weaken (enhance) climatological northerly winds. This, in turn, results in a weakening (enhancement) of wind speed, favoring a reduction (increase) in latent heat flux from the ocean into atmosphere, accompanied by an increase (decrease) in shortwave radiation flux. In addition to surface heat flux forcings, ocean zonal advection is the second most significant contributing factor, exerting a negative effect. Finally, the effect of the Madden–Julian Oscillation (MJO) on the SST is studied. The variations in wind anomalies and surface heat flux changes associated with SST intraseasonal variability are significantly related to the MJO activities. The anomalous anticyclone (cyclone) in the northwest Pacific Ocean is induced by MJO, with enhanced (depressed) convection occurring in the Indian Ocean and depressed (enhanced) convection over the Maritime Continent and western Pacific Ocean, which accounts for the anomalous southerly (northerly) winds and enhanced (depressed) shortwave radiation observed.