El Nino-Southern Oscillation Prediction Research Articles

ENSO‐Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer‐Based Deep Learning Model in the Tropical Pacific

AbstractRecent studies have demonstrated great values of deep‐learning (DL) methods for improving El Niño‐Southern Oscillation (ENSO) predictions. However, the black‐box nature of DL makes it challenging to physically interpret mechanisms responsible for successful ENSO predictions. Here, we demonstrate an interpretable method by performing perturbation experiments to predictors and quantifying input‐output relationships in predictions by using a transformer‐based model; ENSO‐related thermal precursors serving as initial conditions during multi‐month time intervals (TIs) are identified in the equatorial‐northern Pacific, acting to precondition input predictors to provide for long‐lead ENSO predictability. Results reveal the existence of upper‐ocean temperature anomaly pathways and consistent phase propagations of thermal precursors around the tropical Pacific. It is illustrated that three‐dimensional thermal fields and their basinwide evolution during long TIs act to enhance long‐lead prediction skills of ENSO. These physically explainable results indicate that neural networks can adequately represent predictable precursors in the input predictors for successful ENSO predictions.

On the Divergent Evolution of ENSO After the Coastal El Niños in 2017 and 2023

AbstractCoastal El Niño is an extreme situation of El Niño‐Southern Oscillation (ENSO) with sea surface temperature warming confined in the far‐eastern equatorial Pacific. Some coastal El Niños evolve into a basin scale El Niño, and some don't, implying a diversity in ENSO evolutions after a coastal El Niño event. In this study, the coastal El Niños in 2017 and 2023 are selected to examine their subsequent evolution. Both coastal El Niños developed after a La Niña, with the former followed by a La Niña and the latter by a basin‐scale El Niño. The cold (warm) subsurface temperatures in 2017 (2023) were key factors leading to the divergent ENSO evolution. Convection over the western tropical Pacific and the atmospheric circulation anomalies across the equatorial Pacific also contributed to the differences. Model predictions suggest that differences in ENSO evolution after a coastal El Niño are associated with differences in ENSO predictability.

Skillful prediction of length of day one year ahead in multiple decadal prediction systems

Despite a small amplitude, Length of Day (LOD) change, which varies from one year to another due to changes in Atmospheric Angular Momentum (AAM), determines the accuracy of Global Positioning System (GPS) time calculation. In this study, we examine the prediction skill of LOD and AAM in nine decadal prediction systems archived for the Decadal Climate Prediction Project. A persistence and rebound in LOD prediction skill at one year or longer lead time is found in most models. A poleward propagation of AAM anomaly via wave-mean flow interaction is also qualitatively well reproduced. This long-lead prediction of LOD and AAM is attributed to reliable predictions of the El Niño–Southern Oscillation (ENSO) and the Quasi-Biennial Oscillation (QBO), the former being more systematically related than the latter. This result indicates that the improved ENSO prediction and atmospheric wave-mean flow interaction may lead to better prediction of LOD, AAM and related extratropical climate in the decadal prediction systems.

Quantifying the Relative Contributions of the Global Oceans to ENSO Predictability With Deep Learning

AbstractWe propose a unified statistical method based on deep learning and analysis to quantify the relative contributions of the global oceans to El Niño–Southern Oscillation (ENSO) predictability. By incorporating subsurface signals in the Indian Ocean and Atlantic, the forecast lead can be skillfully extended by about one season. This skill enhancement mainly originates from the tropical Indian Ocean, presumably related to signals of the Indian Ocean Dipole passing to the tropical Pacific through the Indonesian Throughflow. The sea surface temperature anomaly (SSTA) in the Indian Ocean accounts for nearly 50% of surface contributions to both El Niño and La Niña predictions at a 15‐month lead. The north tropical Atlantic SSTA has a moderate impact on La Niña at a 9‐month lead. The Pacific Meridional Mode plays a significant role in both ENSO phases at a 12‐month lead. Thus, our study suggests that trans‐basin effects for ENSO are more vigorous than previously thought.

Multi-scale spatial features and temporal attention mechanisms: advancing the accuracy of ENSO prediction

The exponential progression in oceanic observational technology has fostered the accumulation of substantial time series data pivotal for predictions in ocean meteorology. Foremost among the phenomena observed is El Niño-Southern Oscillation (ENSO), a critical determinant in the interplay of global ocean atmosphere interactions, with its severe manifestations inducing extreme meteorological conditions. Therefore, precisely predicting ENSO events carries immense gravitas. Historically, predictions hinged primarily on dynamic models and statistical approaches; however, the intricate and multifaceted spatiotemporal dynamics of ENSO events have often impeded the accuracy of these traditional methodologies. A notable lacuna in contemporary research is the insufficient exploration of long-term dependencies within oceanic data and the suboptimal integration of spatial information derived from spatiotemporal data. To address these limitations, this study introduces a forward-thinking ENSO prediction framework synergizing multiscale spatial features with temporal attention mechanisms. This innovation facilitates a more profound exploration of temporal and spatial domains, enhancing the retention of extensive-period data while optimizing the use of spatial information. Preliminary analyses executed on the global ocean data assimilation system dataset attest to the superior efficacy of the proposed method, underscoring a substantial improvement over established methods including SA-convolutional long short-term memory, particularly in facilitating long-term predictions.The source code and datasets are provided. The code is available at https://github.com/tse1998/ENSO-prediction.

Enhancing ENSO predictions with self-attention ConvLSTM and temporal embeddings

El Niño-Southern Oscillation (ENSO), a cyclic climate phenomenon spanning interannual and decadal timescales, exerts substantial impacts on the global weather patterns and ecosystems. Recently, deep learning has brought considerable advances in the accurate prediction of ENSO occurrence. However, the current models are insufficient to characterize the evolutionary behavior of the ENSO, particularly lacking comprehensive modeling of local-range and longrange spatiotemporal interdependencies, and the incorporation of calendar monthly and seasonal properties. To make up this gap, we propose a Two-Stage SpatioTemporal (TSST) autoregressive model that couples the meteorological factor prediction with ENSO indicator prediction. The first stage predicts the meteorological time series by leveraging self-attention ConvLSTM network which captures both the local and the global spatial-temporal dependencies. The temporal embeddings of calendar months and seasonal information are further incorporated to preserves repeatedly-occurring-yet-hidden patterns in meteorological series. The second stage uses multiple layers to extract higher level of features from predicted meteorological factors progressively to generate ENSO indicators. The results demonstrate that our model outperforms the state-of-the-art ENSO prediction models, effectively predicting ENSO up to 24 months and mitigating the spring predictability barrier.

Evaluating the Performance of the North Pacific Victoria Mode as an ENSO Predictor Based on Multimodel Ensemble Hindcasts

Abstract The Victoria mode (VM), similar to the Pacific meridional mode (PMM), is forced by North Pacific Oscillation atmospheric variability. Both the boreal spring VM and PMM can trigger the onset of El Niño–Southern Oscillation (ENSO) events in the following winter. Previous studies have examined the precursor relationship between the PMM and ENSO based on a subset of models drawn from the North American Multimodel Ensemble (NMME) system. They suggested that the PMM can act as a precursor to El Niño events, whereas it fails to predict La Niña events. Utilizing the hindcasts of these models from NMME, this study further investigates the role of the VM as an ENSO predictor to examine the real usefulness of the VM for ENSO prediction. When compared with the PMM, the VM can predict both El Niño and La Niña events with some skill, showing that the VM seems to be a more reliable predictor of ENSO. We found that the unique role of the VM in ENSO prediction originates from the symmetric impact of the VM on ENSO events. The VM, as a basin-scale sea surface temperature (SST) pattern, combines the role of the SST over the subtropical northeastern Pacific that is similar to the PMM in initializing El Niño events with that of the SST over the western North Pacific that is different from PMM in initializing La Niña events, resulting in the symmetric effect of the VM on ENSO prediction. Thus, it is useful to consider VM variability as a reference for ENSO prediction. Significance Statement We aim to investigate whether the robust relationship between the boreal spring Victoria mode (VM) and the following winter ENSO in observations and climate models has any real predictive use, thus bridging the gap between theory and practical application. Our analyses based mainly on model hindcast datasets examine the forecasting skill of the VM for El Niño and La Niña events. We also reveal the symmetric impact of VM on ENSO through the analysis of observations, which explains the VM’s skill in predicting both El Niño and La Niña events. This study deepens our understanding of the effect of North Pacific SST variability on ENSO.

Improved prediction of extreme ENSO events using an artificial neural network with weighted loss functions

The El Niño–Southern Oscillation (ENSO) causes a wide array of abnormal climates and extreme events, including severe droughts and floods, which have a major impact on humanity. With the development of artificial neural network techniques, various attempts are being made to predict ENSO more accurately. However, there are still limitations in accurately predicting ENSO beyond 6 months, especially for abnormal years with less frequent but greater impact, such as strong El Niño or La Niña, mainly due to insufficient and imbalanced training data. Here, we propose a new weighted loss function to improve ENSO prediction for abnormal years, in which the original (vanilla) loss function is multiplied by the weight function that relatively reduces the weight of high-frequency normal events. The new method applied to recurrent neural networks shows significant improvement in ENSO predictions for all lead times from 1 month to 12 months compared to using the vanilla loss function; in particular, the longer the prediction lead time, the greater the prediction improvement. This method can be applied to a variety of other extreme weather and climate events of low frequency but high impact.

A new subsurface precursor across the spring predictability barrier for the ENSO prediction

Despite decades of research on forecasting the El Niño–Southern Oscillation (ENSO) in the past decades, skillfully predicting the ENSO across the spring predictability barrier remains challenging. In this study, we utilize the ensemble of four model products to identify a new subsurface precursor consisting of the anomalous equatorial zonal velocity over 180°–150°W and 140–180 m and potential temperature in the western Pacific (over 120°–140°E and 120–160 m), which could predict the ENSO before spring by applying regression analysis. Such a precursor can predict the Niño 3.4 index in December at a lead time of 13 months with a regressed correlation of 0.79. The anomalous subsurface zonal velocity in the central Pacific favors the eastward migration of the warm water during the development of El Niño. Further validations with diverse training and application periods indicate that for initialization in November, this new precursor shows high skills in predicting the Niño 3.4 index at a lead time of 6–18 months over 1993–2016, outperforming counterparts for the other traditional precursors. Our study can help highlight the importance of subsurface processes in the ENSO development, improving our general ability to predict the ENSO, and enabling better preparedness for the implications of its occurrence.

Sea Surface Salinity Strongly Weakens ENSO Spring Predictability Barrier

AbstractPrevious studies suggested that tropical sea surface salinity (SSS) can influence tropical Pacific sea surface temperature (SST) through mixing and entrainment and thus it may be a signal for El Niño‐Southern Oscillation (ENSO) prediction. This paper explores the influence of SSS on ENSO spring predictability barrier (SPB) using an empirical dynamic model ‐ Linear Inverse Model (LIM). By coupling and decoupling SSS in the LIM, we find that tropical Pacific SSS plays a significant role in weakening both Central‐Pacific and Eastern‐Pacific ENSO SPB. The evolution of optimal initial structure also shows the importance of SSS dynamics in ENSO. We found an SSS mode that plays the dominant role in SSS impacting ENSO prediction. By the analysis of lead‐lag correlation, we find that this mode can induce easterlies during the spring, which finally leads to a La Niña‐like SST pattern in the winter through zonal advective and thermocline feedbacks.

Explained predictions of strong eastern Pacific El Niño events using deep learning

Global and regional impacts of El Niño-Southern Oscillation (ENSO) are sensitive to the details of the pattern of anomalous ocean warming and cooling, such as the contrasts between the eastern and central Pacific. However, skillful prediction of such ENSO diversity remains a challenge even a few months in advance. Here, we present an experimental forecast with a deep learning model (IGP-UHM AI model v1.0) for the E (eastern Pacific) and C (central Pacific) ENSO diversity indices, specialized on the onset of strong eastern Pacific El Niño events by including a classification output. We find that higher ENSO nonlinearity is associated with better skill, with potential implications for ENSO predictability in a warming climate. When initialized in May 2023, our model predicts the persistence of El Niño conditions in the eastern Pacific into 2024, but with decreasing strength, similar to 2015–2016 but much weaker than 1997–1998. In contrast to the more typical El Niño development in 1997 and 2015, in addition to the ongoing eastern Pacific warming, an eXplainable Artificial Intelligence analysis for 2023 identifies weak warm surface, increased sea level and westerly wind anomalies in the western Pacific as precursors, countered by warm surface and southerly wind anomalies in the northern Atlantic.

Improvement of an extended ensemble coupled data Assimilation–Forecast system and its application in El Niño diversity predictions

The El Niño–Southern Oscillation (ENSO) can cause climate anomalies on a global scale, and further affect human life and activities in coastal zones. Therefore, its forecast is of great significance for early disaster warning and coastal management. However, the frequent occurrence of central Pacific (CP) El Niño events increases the diversity and complexity of ENSO, severely reducing its prediction efficiency. In this study, an extended ensemble coupled data assimilation–forecast system was employed to investigate the prediction of different types of El Niño events, including eastern Pacific (EP) and CP events. The extended system was based on the fifth-generation Lamont–Doherty Earth Observation (LDEO5) model, in which an advanced ensemble Kalman filter was used to construct a multisource data assimilation system, and a stochastic optimal method was used to measure the influence of atmospheric stochastic processes on model prediction errors. The extended system was used to predict two types of El Niño events that occurred between January 1950 and December 2018. The results showed that the extended system was generally able to predict EP events with a higher accuracy than CP events for all lead times. The extended system successfully predicted the mature phase of EP events up to 12 months in advance but could only predict the mature phase of CP events up to 6 months in advance. The extended system was also able to depict the evolution of both EP and CP events, although the sea surface temperature anomalies were underestimated. The extended system not only provides a useful platform for improving ENSO prediction accuracies in association with El Niño diversity but also provides an important tool for disaster early warning and coastal management.

The Pacific Meridional Mode Influences ENSO by Inducing Springtime Near-Equatorial TCs in the Western North Pacific

Abstract Previous research has shown that tropical cyclones in the near-equatorial western North Pacific (NE-WNP TCs) in boreal spring are associated with the onset of El Niño–Southern Oscillation (ENSO). However, the cause of these TCs is unclear. Here, we find that the interannual activity of the springtime NE-WNP TCs is insensitive to the simultaneous ENSO intensity but is closely related to the springtime Pacific meridional mode (PMM). The lead–lag correlation between PMM and NE-WNP TCs is high from January to April, and the evolution of the SST anomaly associated with the NE-WNP TCs strongly manifests the seasonal footprint of the PMM. Analysis using AGCM experiments confirms that the positive PMM tends to reduce the vertical shear of zonal wind and sea level pressure and to increase vertical velocity in the middle atmosphere and surface humidity in the WNP. All of these conditions are favorable for NE-WNP TC genesis. We conducted CGCM experiments to validate that the NE-WNP TCs significantly influence ENSO development. A statistical regression model with respect to the impact of PMM on NE-WNP TCs and further on ENSO intensity was also conducted. The results imply that modulating the springtime NE-WNP TCs is another effective way in which the PMM influences ENSO. Significance Statement Some studies have found that springtime near-equatorial western North Pacific (NE-WNP) tropical cyclones (TCs) heavily impact ENSO development. Using observations and AGCM experiments, we showed that the genesis of these TCs is closely associated with the Pacific meridional mode (PMM), presumably because the PMM provides favorable conditions for TC genesis. We further showed that including the PMM-induced NE-WNP TCs in a CGCM leads to an El Niño–like response. The linkage between the PMM and NE-WNP TCs not only supplements the existing theories about tropical–subtropical interactions but also provides a new way to improve ENSO simulation and prediction.

CNN‐Based ENSO Forecasts With a Focus on SSTA Zonal Pattern and Physical Interpretation

AbstractDeep learning (DL) has achieved notable success in El Niño‐Southern Oscillation (ENSO) forecasts. Most DL‐based models focused on forecasting ENSO indices while the zonal distribution of sea surface temperature anomalies (SSTA) over the equatorial Pacific was overlooked. To provide accurate predictions for the SSTA zonal pattern, this study developed a model through leveraging the merits of the cosine distance in constructing the convolutional neural network. This model can skillfully predict the SSTA zonal pattern over the equatorial Pacific 1 year in advance, remarkably outperforming current dynamical models. Moreover, the physical interpretation of the model prediction reveals that the sources for ENSO predictability at different lead times are distinct. For the 10‐month‐lead predictions, the precursors in the north Pacific, south Pacific and tropical Atlantic play critical roles in determining the model behaviors; while for the 16‐month‐lead predictions, the initial signals in the tropical Pacific associated with the discharge‐recharge cycle are essential.

Assessment of Inflation Schemes on Parameter Estimation and Their Application in ENSO Prediction in an OSSE Framework

The ensemble Kalman filter is often used in parameter estimation, which plays an essential role in reducing model errors. However, filter divergence is often encountered in an estimation process, resulting in the convergence of parameters to the improper value and finally in parameter estimation failure. To alleviate this degeneration, various covariance inflation schemes have been proposed. In this study, I examined six currently used inflation schemes: fixed inflation, conditional covariance inflation, modified estimated parameter ensemble spread, relaxation-to-prior perturbations, relaxation-to-prior spread, and new conditional covariance inflation. The six schemes were thoroughly explored using the Zebiak–Cane model and the local ensemble transform Kalman filter in the observing system simulation experiment framework. Emphasis was placed on the comparison of these schemes when it came to estimating single and multiple parameters in terms of oceanic analyses and resultant El Niño–Southern Oscillation (ENSO) predictions. The results showed that the new conditional covariance inflation scheme had the best results in terms of the estimated parameters, resultant state analyses, and ENSO predictions. In addition, the results suggested that better parameter estimation yields better state simulations, resulting in improved predictions. Overall, this study provides viable information for selecting inflation schemes for parameter estimation, offering theoretical guidance for constructing operational assimilation systems.

Enhanced joint impact of western hemispheric precursors increases extreme El Niño frequency under greenhouse warming

Sea surface temperature variability over the north tropical Atlantic (NTA) and over the subtropical northeast Pacific (SNP), which is referred to as the North Pacific Meridional Mode, during the early boreal spring is known to trigger El Niño–Southern Oscillation (ENSO) events. The future changes of the influence of those northwestern hemispheric precursors on ENSO are usually examined separately, even though their joint impacts significantly differ from the individual impacts. Here, we show that the impacts of both NTA and SNP on ENSO significantly increase under greenhouse warming and that the degrees of enhancement are closely linked. The wetter mean state over the off-equatorial eastern Pacific is a single contributor that controls the impacts of both NTA and SNP on ENSO. The enhanced joint impacts of the northwestern hemispheric precursors on ENSO increase the occurrences of extreme El Niño events and the ENSO predictability under greenhouse warming.

Key to ENSO phase-locking simulation: effects of sea surface temperature diurnal amplitude

The tendency of El Niño/Southern Oscillation (ENSO) events to peak during boreal winter is known as ENSO phase-locking, whose accurate simulation is essential for ENSO prediction. However, the simulated peaks of ENSO events usually occur outside boreal winter in state-of-the-art climate models. Based on the Coupled Model Intercomparison Project Phase 6 (CMIP6) models, the model with a more reasonable diurnal amplitude (DA) in the sea surface temperature (SST) had a better simulation ability for ENSO phase-locking compared with other models. Further experiments based on the earth system model revealed that the DA is vital for ENSO phase-locking simulation primarily due to the spatial inhomogeneities in seasonal DA anomaly variations in ENSO years with positive/negative DA anomalies in the central equatorial Pacific and negative/positive in the western or eastern Pacific during El Niño/La Niña. Our findings indicate that DA simulation in climate models is crucial for resolving the long-standing failure associated with the ENSO phase-locking simulation accuracy.

ENSO Spread Caused by Uncertainties in Initial Condition and High-Frequency Perturbations in the Tropical Pacific

Abstract Uncertainties both in the initial condition (IC) and surface wind high-frequency perturbations (HFPs) contribute to the prediction spread of El Niño–Southern Oscillation (ENSO), yet the relative roles of the two are hard to separate, mostly due to the nonlinearity in ENSO dynamics. In this study, we conducted two ensemble experiments using the CESM model to analyze the source of ENSO spread arising from the tropical Pacific. The HFPs were precluded using an online low-pass-filtering scheme in one experiment. Results showed that the uncertainty in ENSO prediction depends on both the IC and HFPs. By comparing simulations with and without HFPs, it is found that the predicted ENSO spread decreased in magnitude when HFPs are removed, especially in the first four prediction months. At integration time longer than that, the additional impact of HFPs cannot be detected on top of that of the uncertainty in IC. To the ENSO spread anomaly, we found that it is tightly associated with uncertainty in the sea surface temperature and surface wind in the central-eastern equatorial Pacific at the short integration time, and associated with the HFPs in the western equatorial Pacific at the long integration time. When the HFPs are removed, the precursor of the ENSO spread anomaly at the long lead time emerges in the northeastern tropical Pacific, the area where the Pacific meridional mode originates from. Our results indicate that the uncertainty in ENSO prediction depends primarily on IC, and the HFPs in the western equatorial Pacific play the secondary role.

An ENSO Prediction Model Based on Backtracking Multiple Initial Values: Ordinary Differential Equations–Memory Kernel Function

This article presents a new prediction model, the ordinary differential equations–memory kernel function (ODE–MKF), constructed from multiple backtracking initial values (MBIV). The model is similar to a simplified numerical model after spatial dimension reduction and has both nonlinear characteristics and the low-cost advantage of a time series model. The ODE–MKF focuses on utilizing more temporal information and includes machine learning to solve complex mathematical inverse problems to establish a predictive model. This study first validates the feasibility of the ODE–MKF via experiments using the Lorenz system. The results demonstrate that the ODE–MKF prediction model could describe the nonlinear characteristics of complex systems and exhibited ideal predictive robustness. The prediction of the El Niño-Southern Oscillation (ENSO) index further demonstrates its effectiveness, as it achieved 24-month lead predictions and effectively improved nonlinear problems. Furthermore, the reliability of the model was also tested, and approximately 18 months of prediction were achieved, which was verified with the Clouds and the Earth’s Radiant Energy System (CERES) Energy Balanced and Filled (EBAF) radiation fluxes. The short-term memory index Southern Oscillation (SO) was further used to examine the applicability of ODE–MKF. A six-month lead prediction of the SO trend was achieved, indicating that the predictability of complex systems is related to their inherent memory scales.

Multi-decadal variation of ENSO forecast skill since the late 1800s

Diagnosing El Niño-Southern Oscillation (ENSO) predictability within operational forecast models is hindered by computational expense and the need for initialization with three-dimensional fields generated by global data assimilation. We instead examine multi-year ENSO predictability since the late 1800s using the model-analog technique, which has neither limitation. We first draw global coupled model states from pre-industrial control simulations, from the Coupled Model Intercomparison Project Phase 6, that are chosen to initially match observed monthly sea surface temperature and height anomalies in the Tropics. Their subsequent 36-month model evolution are the hindcasts, whose 20th century ENSO skill is comparable to twice-yearly hindcasts generated by a state-of-the-art European operational forecasting system. Despite the so-called spring predictability barrier, present throughout the record, there is substantial second-year ENSO skill, especially after 1960. Overall, ENSO exhibited notably high values of both amplitude and skill towards the end of the 19th century, and again in recent decades.