Tracing Uncertainties of Extreme El Niño Prediction to Mesoscale Ocean Currents

Authors: Bo Qin, Zeyun Yang, Qiaofei Xue, Yanan Ding, Jinyu Wang, Chaopeng Ji, Shijin Yuan, Bin Mu, Wansuo Duan, Guokun Dai, Mu Mu, Yi Deng

arXiv: 2611.17854v1 (physics.ao-ph)
Submitted to arXiv on 13 Nov. 2026
License: CC BY 4.0
Abstract

The predictability of the El Niño-Southern Oscillation (ENSO) has historically been linked to large-scale errors in models' initial conditions such as heat content and surface wind stress. Here we demonstrate that these slowly evolving errors may ultimately originate from mesoscale errors in initial oceanic states that are common in current models and ocean observation systems. This hidden source of ENSO forecast uncertainty, in terms of mesoscale ocean-current errors, is convincingly exposed by the conditional nonlinear optimal perturbation (CNOP) method applied to a differentiable ocean AI model. The CNOP-identified most influential current errors are strongly event-dependent. For the 1997/98 El Niño, the initial current errors in the eastern Pacific results in the largest forecast error through locally suppressing original subsurface warming. For the 2015/16 event, the dominate error originates from the western Pacific, which reorganizes upper ocean temperature structure and affects the eastern Pacific through the equatorial waveguide. Further analysis reveals that these current errors perturb mesoscale eddy count and eddy kinetic energy triggering large-scale temperature errors that hinder El Niño development. The timing of the maximum growth rate of the obtained CNOP error is well aligned with the spring predictability barrier of ENSO, and the error structures are reflected in simulated analysis errors caused by unresolved mesoscale currents. These findings extend the potential source of ENSO predictability beyond large-scale thermal signals, reveal for the first time an uncharted route of ENSO forecast failure, and provide an important physical basis for targeted ocean observations and data assimilation in the future.

The papers around it, by date and closeness

Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper

How to read this map? Illustrated guide

Closest papers Prior work it builds on Papers that cite it

Papers around this one

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

  1. Close Another approach to the problem
    A Deep Learning Model for Forecasting Global Monthly Mean Sea Surface Temperature Anomalies
    John Taylor, Ming Feng · 2022 · Atmospheric and Oceanic Physics · cited 60 times · Not summarized yet

    The Unet-LSTM forecasts global monthly SST anomalies, including those linked to ENSO, whereas this study traces extreme El Niño forecast errors to mesoscale current perturbations.

    Abstract

    Sea surface temperature (SST) variability plays a key role in the global weather and climate system, with phenomena such as El Niño-Southern Oscillation regarded as a major source of interannual climate variability at the global scale. The ability to be able to make long-range forecasts of sea surface temperature anomalies, especially those associated with extreme marine heatwave events, has potentially significant economic and societal benefits. We have developed a deep learning time series prediction model (Unet-LSTM) based on more than 70 years (1950-2021) of ECMWF ERA5 monthly mean sea surface temperature and 2-metre air temperature data. The Unet-LSTM model is able to learn the underlyi…

  2. Related Broader context
    Tsallis nonextensive statistical mechanics of El Nino Southern Oscillation Index
    M. Ausloos, F. Petroni · 2006 · Physica A 373 (2007) 721 - 736 · cited 14 times · AI summary available

    The study models statistical distributions of the El Niño Southern Oscillation Index, while this paper investigates how mesoscale current errors affect extreme El Niño forecasts.

    Abstract

    The shape and tails of partial distribution functions (PDF) for a climatological signal, i.e. the El Nino SOI and the turbulent nature of the ocean-atmosphere variability are linked through a model encompassing Tsallis nonextensive statistics and leading to evolution equations of the Langevin and Fokker-Planck type. A model originally proposed to describe the intermittent behavior of turbulent flows describes the behavior of the normalized variability for such a climatological index, for small and large time windows, both for small and large variability. This normalized variabil- ity distributions can be sufficiently well fitted with a chi-square-distribution. The transition between the smal…

  3. Related Broader context
    Exploring the Potential of Hybrid Machine-Learning/Physics-Based Modeling for Atmospheric/Oceanic Prediction Beyond the Medium Range
    Dhruvit Patel, Troy Arcomano, Brian Hunt et al. · 2024 · Atmospheric and Oceanic Physics · cited 2 times · AI summary available

    The paper tests hybrid machine-learning and physics-based models for atmospheric and oceanic prediction, while this study uses a differentiable ocean model to trace ENSO forecast uncertainty.

    Abstract

    This paper explores the potential of a hybrid modeling approach that combines machine learning (ML) with conventional physics-based modeling for weather prediction beyond the medium range. It extends the work of Arcomano et al. (2022), which tested the approach for short- and medium-range weather prediction, and the work of Arcomano et al. (2023), which investigated its potential for climate modeling. The hybrid model used for the forecast experiments of the paper is based on the low-resolution, simplified parameterization atmospheric general circulation model (AGCM) SPEEDY. In addition to the hybridized prognostic variables of SPEEDY, the current version of the model has three purely ML-bas…

  4. Related Broader context
    Reducing Uncertainty in Sea-level Rise Prediction: A Spatial-variability-aware Approach
    Subhankar Ghosh, Shuai An, Arun Sharma et al. · 2023 · Atmospheric and Oceanic Physics · preprint, not peer reviewed · cited 4 times · AI summary available

    The study reduces uncertainty in spatially varying sea-level-rise projections, while this paper examines current-error sources of uncertainty in extreme El Niño forecasts.

    Abstract

    Given multi-model ensemble climate projections, the goal is to accurately and reliably predict future sea-level rise while lowering the uncertainty. This problem is important because sea-level rise affects millions of people in coastal communities and beyond due to climate change's impacts on polar ice sheets and the ocean. This problem is challenging due to spatial variability and unknowns such as possible tipping points (e.g., collapse of Greenland or West Antarctic ice-shelf), climate feedback loops (e.g., clouds, permafrost thawing), future policy decisions, and human actions. Most existing climate modeling approaches use the same set of weights globally, during either regression or deep…

  5. Related Another approach to the problem
    Feature Importance in a Deep Learning Climate Emulator
    Wei Xu, Xihaier Luo, Yihui Ren et al. · 2021 · Machine Learning · preprint, not peer reviewed · cited 19 times · Not summarized yet

    The study uses feature-importance methods to identify SST inputs shaping climate-emulator forecasts, whereas this paper uses CNOP to identify influential current errors in ENSO forecasts.

    Abstract

    We present a study using a class of post-hoc local explanation methods i.e., feature importance methods for "understanding" a deep learning (DL) emulator of climate. Specifically, we consider a multiple-input-single-output emulator that uses a DenseNet encoder-decoder architecture and is trained to predict interannual variations of sea surface temperature (SST) at 1, 6, and 9 month lead times using the preceding 36 months of (appropriately filtered) SST data. First, feature importance methods are employed for individual predictions to spatio-temporally identify input features that are important for model prediction at chosen geographical regions and chosen prediction lead times. In a second …

  6. Related Broader context
    Data-driven and machine-learning based prediction of wave propagation behavior in dam-break flood
    Changli Li, Zheng Han, Yange Li et al. · 2022 · Fluid Dynamics · cited 2 times · Not summarized yet

    The study applies machine learning to predict dam-break flood waves, while this paper uses an ocean AI model to investigate extreme El Niño forecast errors.

    Abstract

    The computational prediction of wave propagation in dam-break floods is a long-standing problem in hydrodynamics and hydrology. Until now, conventional numerical models based on Saint-Venant equations are the dominant approaches. Here we show that a machine learning model that is well-trained on a minimal amount of data, can help predict the long-term dynamic behavior of a one-dimensional dam-break flood with satisfactory accuracy. For this purpose, we solve the Saint-Venant equations for a one-dimensional dam-break flood scenario using the Lax-Wendroff numerical scheme and train the reservoir computing echo state network (RC-ESN) with the dataset by the simulation results consisting of time…

  7. Related Broader context
    An Interpretable Model of Climate Change Using Correlative Learning
    Charles Anderson, Jason Stock · 2022 · Atmospheric and Oceanic Physics · preprint, not peer reviewed · cited 1 time · AI summary available

    The study interprets neural-network patterns associated with global climate change, while this paper identifies ocean-current perturbations that drive errors in extreme El Niño forecasts.

    Abstract

    Determining changes in global temperature and precipitation that may indicate climate change is complicated by annual variations. One approach for finding potential climate change indicators is to train a model that predicts the year from annual means of global temperatures and precipitations. Such data is available from the CMIP6 ensemble of simulations. Here a two-hidden-layer neural network trained on this data successfully predicts the year. Differences among temperature and precipitation patterns for which the model predicts specific years reveal changes through time. To find these optimal patterns, a new way of interpreting what the neural network has learned is explored. Alopex, a sto…

  8. Related Shared data, tool or method
    Nonlinear ensemble filtering with diffusion models: Application to the surface quasi-geostrophic dynamics
    Feng Bao, Hristo G. Chipilski, Siming Liang et al. · 2024 · Mathematical Physics · cited 32 times · AI summary available

    The study develops a diffusion-model ensemble filter for data assimilation in surface quasi-geostrophic dynamics, a generic assimilation method relevant to this paper's focus on ocean initialization errors.

    Abstract

    The intersection between classical data assimilation methods and novel machine learning techniques has attracted significant interest in recent years. Here we explore another promising solution in which diffusion models are used to formulate a robust nonlinear ensemble filter for sequential data assimilation. Unlike standard machine learning methods, the proposed \textit{Ensemble Score Filter (EnSF)} is completely training-free and can efficiently generate a set of analysis ensemble members. In this study, we apply the EnSF to a surface quasi-geostrophic model and compare its performance against the popular Local Ensemble Transform Kalman Filter (LETKF), which makes Gaussian assumptions on t…

How are these papers found?

We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.

Updated on 16 November 2026.

The illustrated guide to the papers around a paper