Madden–Julian Oscillation Prediction Research Articles

Decrease in MJO Predictability Following Indo–Pacific Warm Pool Expansion

AbstractThe characteristics of the Madden–Julian oscillation (MJO) have changed and are projected to continue changing with the expansion of the Indo–Pacific warm pool, which is the Earth's largest region of warm sea surface temperatures (SSTs). However, the likelihood of a change in MJO predictability following warm pool expansion remains unaddressed. Therefore, this study investigated the effect of warm pool expansion on MJO variability and predictability using the highly idealized aquaplanet configuration of Community Earth System Model 2 (CESM2). By expanding the warm pool in the Indo–Pacific, MJO‐like waves become more regionally confined, short‐lived convective events with weaker magnitude and less robust eastward propagating signals, possibly due to stronger zonal SST gradients and wider meridional widths of the warm pool. Perfect‐model ensemble forecast experiments revealed that the MJO predictability decreased by approximately 5 days, the forecast error proliferated, and the signal rapidly reduced following warm pool expansion.

Deep learning reveals moisture as the primary predictability source of MJO

The Madden-Julian Oscillation (MJO) is the dominant mode of tropical intraseasonal variability that interacts with many other Earth system phenomena. The prediction skill of the MJO in many operational models is lower than its potential predictability, partly due to our limited understanding of its predictability source. Here, we investigate the source of MJO predictability by combining machine learning (ML) with a 1200-year-long Community Earth System Model version 2 (CESM2) simulation. A Convolutional Neural Network (CNN) for MJO prediction is first trained using the CESM2 simulation and then fine-tuned using observations via transfer learning. The source of MJO predictability in the CNN is examined via eXplainable Artificial Intelligence (XAI) methods that quantify the relative importance of the input variables. Our CNN exhibits an enhanced prediction skill over previous ML models, achieving a skill level of about 25 days. This level of performance is slightly superior or comparable to most operational models participating in the S2S project, although a few dynamical models surpass it. The XAI methods highlight precipitable water anomalies over the Indo-Pacific warm pool as the primary precursors of the subsequent MJO development for 1–3 weeks forecast lead times. Our results suggest that realistic representation of moisture dynamics is crucial for accurate MJO prediction.

The Indo‐Pacific Maritime Continent Barrier Effect on MJO Ensemble Prediction

AbstractThe barrier effect of the Indo‐Pacific Maritime Continent (MC) on the Austral summertime Madden‐Julian Oscillation (MJO) is explored using retrospective forecasts from subseasonal‐to‐seasonal (S2S) prediction models. The general MJO prediction skills in the S2S models are evaluated and the top‐performing models are identified. We select two sets of observed MJO events ‐ continuously propagating across the MC into the western Pacific (WP) and blocked by the MC. The continuously propagating MJO events are better predicted than the blocked MJO events for their systematic eastward propagating behavior, especially in the ocean‐atmosphere coupled models. Although the best four models and their ensemble consistently produce greater prediction skills of the continuously propagating MJOs, the all‐model ensemble is not better than the top‐performing models. Our analysis suggests that a realistic representation of air‐sea interaction over the WP is crucial for better MJO prediction.

Potential Predictability of the Madden‐Julian Oscillation in a Superparameterized Model

AbstractThe Madden‐Julian Oscillation (MJO) is a promising target for improving sub‐seasonal weather forecasts. Current forecast models struggle to simulate the MJO due to imperfect convective parameterizations and mean state biases, degrading their forecast skill. Previous studies have estimated a potential MJO predictability 5–15 days higher than current forecast skill, but these estimates also use models with parameterized convection. We perform a perfect‐model predictability experiment using a superparameterized global model in which the convective parameterization is replaced by a cloud resolving model. We add a second “silent” cloud resolving component to the control simulation that independently calculates convective‐scale processes using the same large‐scale forcings. The second set of convective states are used to initialize forecasts, representing uncertainty on the convective scale. We find a potential predictability of the MJO of 35–40 days in boreal winter using a single‐member ensemble forecast.

Impacts of tidal mixing on diurnal and intraseasonal air-sea interactions in the Maritime Continent

The Maritime Continent (MC) is a region with enhanced tidal mixing and ocean cooling, which influences regional-scale sea surface temperatures (SSTs). We examine the coupled impacts of tidal mixing on near-surface stratification, SST, and deep convection on diurnal and intraseasonal time-scales, using ensembles of high-resolution, coupled ocean-atmosphere regional model simulations, with and without tidal forcing. Results show that the area-averaged SST in the eastern MC is reduced by 0.20 °C due to tidal forcing, with cooling exceeding 1 °C in the nearshore zones of shallow and complex bathymetry. The reduced SSTs decrease surface heat fluxes, leading to tropospheric drying and reduced precipitation, which are most pronounced in the nearshore zones. The results show that the magnitude of tidally-induced SST cooling is phase-dependent during the passage of the Madden Julian Oscillation (MJO). Strong westerly winds enhance entrainment cooling through wind-driven mixing and upwelling during the active phase. Conversely, the upper-ocean stratification is enhanced during the suppressed phase, and SSTs are less sensitive to subsurface cooling. Such spatio-temporal variability in the SST response to tides is accompanied by consistent changes to deep convection and atmospheric circulation. On the diurnal time-scale, nearshore cooling weakens the early-morning convection when the land-based convection propagates offshore and interacts with the cooler SST. On intraseasonal time-scales, the coupling between SST and precipitation is strengthened because of the asymmetric impacts of tide-induced mixing on SST and MJO-induced winds. The robust SST and precipitation responses demonstrated in this study suggest the need for an accurate representation of tidal forcing and vertical mixing processes in local MJO prediction models for the MC.

The Role of Subtropical Rossby Waves in Amplifying the Divergent Circulation of the Madden–Julian Oscillation

Abstract The composite structure of the Madden–Julian oscillation (MJO) has long been known to feature pronounced Rossby gyres in the subtropical upper troposphere, whose existence can be interpreted as the forced response to convective heating anomalies in the presence of a subtropical westerly jet. The question of interest here is whether these forced gyre circulations have any subsequent effects on divergence patterns in the tropics and the Kelvin-mode component of the MJO. A nonlinear spherical shallow water model is used to investigate how the introduction of different background jet profiles affects the model’s steady-state response to an imposed MJO-like stationary thermal forcing. Results show that a stronger jet leads to a stronger Kelvin-mode response in the tropics up to a critical jet speed, along with stronger divergence anomalies in the vicinity of the forcing. To understand this behavior, additional calculations are performed in which a localized vorticity forcing is imposed in the extratropics, without any thermal forcing in the tropics. The response is once again seen to include pronounced equatorial Kelvin waves, provided the jet is of sufficient amplitude. A detailed analysis of the vorticity budget reveals that the zonal-mean zonal wind shear plays a key role in amplifying the Kelvin-mode divergent winds near the equator, with the effects of nonlinearities being of negligible importance. These results help to explain why the MJO tends to be strongest during boreal winter when the Indo-Pacific jet is typically at its strongest. Significance Statement The MJO is a planetary-scale convectively coupled equatorial disturbance that serves as a primary source of atmospheric predictability on intraseasonal time scales (30–90 days). Due to its dominance and spontaneous recurrence, the MJO has a significant global impact, influencing hurricanes in the tropics, storm tracks, and atmosphere blocking events in the midlatitudes, and even weather systems near the poles. Despite steady improvements in subseasonal-to-seasonal (S2S) forecast models, the MJO prediction skill has still not reached its maximum potential. The root of this challenge is partly due to our lack of understanding of how the MJO interacts with the background mean flow. In this work, we use a simple one-layer atmospheric model with idealized heating and vorticity sources to understand the impact of the subtropical jet on the MJO amplitude and its horizontal structure.

Exploring dominant processes for multi-month predictability of western Pacific precipitation using deep learning

Over the past half-century, there has been an increasing trend in the magnitude and duration of the Madden-Julian Oscillation (MJO) attributable to the significant warming trend in the Western Pacific (WP). The MJO, bridging weather and climate, influences global and regional climate through atmospheric teleconnections, and climate models can predict it for up to 4–5 weeks. In this study, we use deep learning (DL) methods to investigate the predictability of the MJO-related western Pacific precipitation on a multi-month time scale (5–9 weeks). We examine numerous potential predictors across the tropics, selected based on major MJO theories and mechanisms, to identify key factors for long-term MJO prediction. Our results show that DL-based useful potential predictability of the WP precipitation can be extended up to 6–7 weeks, with a correlation coefficient skill ranging from 0.60 to 0.65. Observational and heat map analysis suggest that cooling anomalies in the central Pacific play a crucial role in enhancing westerly anomalies over the Indian Ocean and warming in the WP, thereby strengthening the Walker circulation in the equatorial Pacific. In addition, the predictability of WP precipitation is higher in La Nina years than in El Nino or normal years, suggesting that mean cooling in the central Pacific may contribute to increased predictability of the MJO-related WP precipitation on the multi-month time scale. Additional model experiments using observed sea surface temperature (SST) anomalies over the central Pacific confirmed that these anomalies contribute to enhanced MJO-related convective anomalies over the WP. The study highlights that DL is a valuable tool not only for improving MJO-related WP prediction but also for efficiently exploring potential mechanisms linked to long-term predictability.

The Idealized Aquaplanet Maritime Continent Barrier Effect on the MJO Predictability

Abstract Studies have indicated exaggerated Maritime Continent (MC) barrier effect in simulations of the Madden–Julian oscillation (MJO), a dominant source of subseasonal predictability in the tropics. This issue has plagued the modeling and operational forecasting communities for decades, while the sensitivity of MC barrier on MJO predictability has not been addressed quantitatively. In this study, perfect-model ensemble forecasts are conducted with an aquaplanet configuration of the Community Earth System Model version 2 (CESM2) in which both basic state and tropical modes of variability are reasonably simulated with a warm pool–like SST distribution. When water-covered terrain mimicking MC landmasses is added to the warm pool–like SST framework, the eastward propagation of the MJO is disturbed by the prescribed MC aqua-mountain. The MJO predictability estimate with the perfect-model experiment is about 6 weeks but reduces to about 4 weeks when the MJO is impeded by the MC aqua-mountain. Given that the recent operational forecasts show an average of 3–4 weeks of MJO prediction skill, we can conclude that improving the MJO propagation crossing the MC could improve the MJO skill to 5–6 weeks, close to the potential predictability found in this study (6 weeks). Therefore, more effort toward understanding and improving the MJO propagation is needed to enhance the MJO and MJO-related forecasts to improve the subseasonal-to-seasonal prediction.

Response of the Madden–Julian Oscillation and Tropical Atmosphere to Changes in Oceanic Mixed Layer Depth over the Indian Ocean

Abstract The Madden–Julian oscillation (MJO) is a component of tropical variability that influences high-impact events such as hurricane activity and Asian monsoons on intraseasonal (2–8 weeks) time scales. However, the atmosphere–ocean dynamics responsible for the MJO are highly debated. To gain insight into MJO–Indian Ocean dynamics, we conduct climate model experiments where the ocean is replaced by a motionless slab whose thickness, called the mixed layer depth (MLD), varies in space but not in time. Changes in the MLD and ocean heat convergence over the Indian Ocean have no discernible impact on MJO propagation, predictability, or variability within the Community Earth System Model (CESM) version 1.2.1. This suggests that ocean dynamics may not be critical to the MJO over the Indian Ocean in this dynamical model (CAM5 coupled to motionless slab). To diagnose changes in intraseasonal variability beyond the MJO, a discriminant analysis technique is used to optimize differences in variability between experiments. This analysis reveals that differences caused by changing Indian Ocean MLD were restricted mostly to local surface fluxes and could be explained by simple energy balance physics. Despite modeling adjustments intended to preserve the climate, the control slab has a warmer climate than the fully coupled model. The resulting changes in the mean climate are consistent with changes theoretically expected from global warming, particularly the “wet-gets-wetter” mechanism. Significance Statement The Madden–Julian oscillation (MJO) is a tropical eastward-moving pulse of convection that can influence a wide variety of global phenomena. Currently, models do not capture many key aspects of the MJO such as speed and spatial structure. The uppermost ocean layer that communicates with the atmosphere is widely believed to play a large role in the evolution of the MJO. To test the importance of ocean dynamics on simulated MJO, a slab-model configuration is used to allow the atmosphere and ocean to communicate through surface fluxes of heat and moisture while suppressing interactive ocean currents. Changes to the upper ocean did not impact the MJO in our model setup.

Skill improvement of the yearly updated reforecasts in ECMWF S2S prediction from 2016 to 2022

Hazardous weather events are often accompanied by subseasonal processes, but the forecast skills of subseasonal prediction are still limited. To assess the skill improvement of the constantly updated model version in ECMWF subseasonal-seasonal (S2S) prediction from 2016 to 2022, the performance of yearly updated reforecasts was evaluated against ERA5 reanalysis data using the temporal anomaly correlation coefficient (TCC) as a metric. The newly updated reforecasts exhibit stable superiority at the weather scale of the first two weeks, regardless of whether the 2-m temperature or precipitation forecast is being considered. At the subseasonal time scale starting from the third week, some slight improvements in prediction skills are only found in several tropical regions. Generally, the week-3 TCC values averaged over global land grids still reflect an advancement in prediction skills for updated reforecasts. For the Madden–Julian Oscillation (MJO), reforecasts can reproduce the characteristics of eastward propagation, but there are deviations in the intensity and propagation range of convection anomalies for reforecasts of all seven years. Based on an evaluation of MJO prediction skill using the bivariate anomaly correlation coefficient and bivariate root-mean-square error, some differences are apparent in the MJO prediction skills among the updated reforecasts, but the improvements do not increase monotonically year by year. Despite the inherent limitation of S2S prediction, positive progress has already been achieved via the constantly updated S2S prediction in ECMWF, which reinforces the confidence in further collaboratively improving S2S prediction in the future.摘要在2016年至2022年间, ECMWF次季节预测系统不断升级并逐年完成新的回报试验. 本文考察该预测系统逐年升级带来的预测技巧提升潜力. 从2米气温和降水来看, 在起报之后的前两周内天气尺度上预测技巧表现出逐年稳定提升的趋势; 在从第三周开始的次季节时间尺度上, 预测技巧的提升仅限于热带部分区域. MJO预测技巧并不随着模式升级而逐年单调提升. 尽管目前S2S预测技巧存在局限性, 但目前已有的进展增强了在未来深入合作以提高S2S预测技术的信心.

Improved MJO Forecasts Using the Experimental Global‐Nested GFDL SHiELD Model

AbstractSitting at the crossroads of weather and climate, the Madden‐Julian Oscillation (MJO) is considered a primary source of subseasonal predictability. Despite its importance, numerical models struggle with MJO prediction as its convection moves through the complex Maritime Continent (MC) environment. Motivated by the ongoing effort to improve MJO prediction, we use the System for High‐resolution prediction on Earth‐to‐Local Domains (SHiELD) model to run two sets of forecasts, one with and one without a nested grid over the MC. By efficiently leveraging high‐resolution grid spacing, the nested grid reduces amplitude and phase errors and extends the model's predictive skill by about 10 days. These enhancements are tied to improvements in predicted zonal wind from the Indian Ocean to the Pacific, facilitated by westerly wind bias reduction in the nested grid. Results from this study suggest that minimizing circulation biases over the MC can lead to substantial advancements in skillful MJO prediction.

The Indo-Pacific Maritime Continent Barrier Effect on MJO Prediction

Abstract The Madden–Julian oscillation (MJO) is often observed to weaken or sometimes completely decay as its convective anomaly moves from the Indian Ocean over to the Maritime Continent (MC), which is known as the MC barrier effect on the MJO. This barrier effect is often exaggerated in numerical models. Using 23 years of the retrospective intraseasonal forecast from two coupled model systems with useful MJO prediction skills, we show that the predictive skill of the real-time multivariate MJO (RMM) index for the continuously propagating MJO events across the MC region is higher than for the blocked MJO events. The greater prediction skill is not related to the higher initial RMM amplitude for the continuous MJO events. Rather the higher skill arises from the more persistent behavior of the propagating MJO events as the convective anomaly moves through the MC region into the western Pacific. The potential predictability is similar for both types of MJO events, suggesting the forecast models hardly differentiate the two types of MJO events in prediction; they only maintain higher RMM magnitudes of the continuously propagating events. The global reanalysis dataset indicates that the blocked events are often associated with persistent higher surface pressures over colder sea surface temperatures in the central Pacific, suggesting the large-scale environment plays a role in promoting or inhibiting the MJO propagation across the MC region. Caveats in the models to reproduce the observed MJO events are also discussed.

Assessing the Impact of Ocean In Situ Observations on MJO Propagation Across the Maritime Continent in ECMWF Subseasonal Forecasts

AbstractDespite the well‐recognized initial value nature of the subseasonal forecasts, the role of subsurface ocean initialization in subseasonal forecasts remains underexplored. Using observing system experiments, this study investigates the impact of ocean in situ data assimilation on the propagation of Madden–Julian Oscillation (MJO) events across the Maritime Continent in the European Centre for Medium‐Range Weather Forecasts (ECMWF) subseasonal forecast system. Two sets of twin experiments are analyzed, which only differ on the use or not of in situ ocean observations in the initial conditions. Besides using the Real‐time Multivariate MJO Index (RMMI) to evaluate the forecast performance, we also develop a new MJO tracking method based on outgoing longwave radiation anomalies (OLRa) for forecast evaluation. We find that the ocean initialization with in situ data assimilation, though having an impact on the forecasted ocean mean state, does not improve the relatively low MJO forecast skill across the Maritime Continent. Moist static energy budget analysis further suggests that a significant underestimation in the meridional moisture advection in the model forecast may hinder the potential role played by the ocean state differences associated with data assimilation. Bias of the intraseasonal meridional winds in the model is a more important factor for such underestimation than the mean state moisture biases. This finding suggests that atmospheric model biases dominate the forecast error growth, and the atmospheric circulation bias is one of the major sources of the MJO prediction error and should be a target for improving the ECMWF subseasonal forecast model.

Excitation of the Madden‐Julian Oscillation in Response to Transient Ocean Warming in SPCAM

AbstractRecent studies have suggested that the Madden‐Julian oscillation (MJO) could be generated as part of atmospheric adjustment to localized equatorial heating in models properly resolving moist convection. Here we use the Super‐parameterized Community Atmosphere Model (SPCAM) to study atmospheric response to transient sea surface warming in the equatorial Indian Ocean, which leads to the excitation of an MJO event, robust across different experiments, in addition to the expected equatorial Rossby and Kelvin waves. A moist static energy (MSE) budget analysis suggests that longwave and surface turbulent latent heat flux anomalies are predominantly responsible for the MJO excitation; however, these terms oppose its eastward propagation. In contrast, advection of MSE generally weakens the MJO amplitude, but contributes to its eastward propagation. These results highlight the role of the MJO in the moist atmospheric adjustment to localized tropical heating, with implications for the MJO mechanisms and prediction.

Interpretable Deep Learning for Probabilistic MJO Prediction

AbstractThe Madden‐Julian oscillation (MJO) is the dominant source of sub‐seasonal variability in the tropics. It consists of an Eastward moving region of enhanced convection coupled to changes in zonal winds. It is not possible to predict the precise evolution of the MJO, so sub‐seasonal forecasts are generally probabilistic. We present a deep convolutional neural network (CNN) that produces skilful state‐dependent probabilistic MJO forecasts. Importantly, the CNN's forecast uncertainty varies depending on the instantaneous predictability of the MJO. The CNN accounts for intrinsic chaotic uncertainty by predicting the standard deviation about the mean, and model uncertainty using Monte‐Carlo dropout. Interpretation of the CNN mean forecasts highlights known MJO mechanisms, providing confidence in the model. Interpretation of forecast uncertainty indicates mechanisms governing MJO predictability. In particular, we find an initially stronger MJO signal is associated with more uncertainty, and that MJO predictability is affected by the state of the Walker Circulation.

Improving the prediction of the Madden–Julian Oscillation of the ECMWF model by post-processing

Abstract. The Madden–Julian Oscillation (MJO) is a major source of predictability on the sub-seasonal (10 to 90 d) timescale. An improved forecast of the MJO may have important socioeconomic impacts due to the influence of MJO on both tropical and extratropical weather extremes. Although in the last decades state-of-the-art climate models have proved their capability for forecasting the MJO exceeding the 5-week prediction skill, there is still room for improving the prediction. In this study we use multiple linear regression (MLR) and a machine learning (ML) algorithm as post-processing methods to improve the forecast of the model that currently holds the best MJO forecasting performance, the European Centre for Medium-Range Weather Forecasts (ECMWF) model. We find that both MLR and ML improve the MJO prediction and that ML outperforms MLR. The largest improvement is in the prediction of the MJO geographical location and intensity.

Pathways to Better Prediction of the MJO: 1. Effects of Model Resolution and Moist Physics on Atmospheric Boundary Layer and Precipitation

AbstractDespite recent advancements in numerical models, prediction of the Madden‐Julian Oscillation (MJO) remains a major challenge in numerical weather prediction and climate modeling. This study explores pathways for improving MJO prediction through systematic investigation of the effects of model resolution and moist physics on simulations of the MJO in Part 1, followed by effects of atmosphere‐ocean coupling in Part 2. The Unified Wave Interface—Coupled Model (UWIN‐CM) experiments with different cumulus parameterizations (CP) and explicit microphysics with convection‐permitting resolution are used to study the MJO convective initiation and eastward propagation. Observations of the atmosphere and ocean from the Dynamics of the MJO (DYNAMO) field campaign in 2011 are used to evaluate coupled model simulations. At lower resolution (12 km), the simulation with the Tiedtke CP produced an eastward propagating MJO event, while the simulation with the Kain‐Fritsch CP did not. The main difference between the two low‐resolution simulations is in the vertical structure of the atmospheric boundary layer which impacts the large‐scale MJO circulation and precipitation. The Kain‐Fritsch CP produced a persistent cloudy boundary layer that decoupled the tropospheric circulation from the surface and failed to produce the MJO. At higher resolution (4 km), convection‐permitting simulations are robust in capturing the observed eastward propagation of MJO precipitation and surface westerly winds. Increasing resolution improves the boundary layer structure and convective systems, which results in more realistic vertical structures of wind and moisture throughout the troposphere, as well as an improved eastward propagation of the MJO.

Using Simple, Explainable Neural Networks to Predict the Madden‐Julian Oscillation

AbstractFew studies have utilized machine learning techniques to predict or understand the Madden‐Julian oscillation (MJO), a key source of subseasonal variability and predictability. Here, we present a simple framework for real‐time MJO prediction using shallow artificial neural networks (ANNs). We construct two ANN architectures, one deterministic and one probabilistic, that predict a real‐time MJO index using maps of tropical variables. These ANNs make skillful MJO predictions out to ∼18 days in October‐March and ∼11 days in April‐September, outperforming conventional linear models and efficiently capturing aspects of MJO predictability found in more complex, dynamical models. The flexibility and explainability of simple ANN frameworks are highlighted through varying model input and applying ANN explainability techniques that reveal sources and regions important for ANN prediction skill. The accessibility, performance, and efficiency of this simple machine learning framework is more broadly applicable to predict and understand other Earth system phenomena.

How Long Can the MJO be Predicted During the Combined Phases of ENSO and QBO?

AbstractThe predictability limit of the Madden‐Julian Oscillation (MJO) in the El Niño and La Niña boreal winters (November‐February) is investigated using observational data and historical run outputs of CMIP models. The MJO predictability is computed by the nonlinear local Lyapunov exponents approach for various MJO indices obtained from bandpass‐filtered (30–80 days) outgoing longwave radiation, 850‐hPa zonal wind, and 200‐hPa zonal wind data. The result shows that the MJO predictability during La Niña winters is enhanced by up to 8 days compared to El Niño winters. Enhanced convection of the MJO phases 2–4 with persistence propagation during La Niña winters leads to higher predictability, as compared with those for El Niño winters. The highest (lowest) predictability of the MJO shows 39 (31) days during La Niña/EQBO (El Niño/EQBO) winters. The longer persistence of the MJO during La Niña/EQBO winters leads to higher predictability.

S2S Prediction in GFDL SPEAR: MJO Diversity and Teleconnections

Abstract A subseasonal-to-seasonal (S2S) prediction system was recently developed using the GFDL Seamless System for Prediction and Earth System Research (SPEAR) global coupled model. Based on 20-yr hindcast results (2000–19), the boreal wintertime (November–April) Madden–Julian oscillation (MJO) prediction skill is revealed to reach 30 days measured before the anomaly correlation coefficient of the real-time multivariate (RMM) index drops to 0.5. However, when the MJO is partitioned into four distinct propagation patterns, the prediction range extends to 38, 31, and 31 days for the fast-propagating, slow-propagating, and jumping MJO patterns, respectively, but falls to 23 days for the standing MJO. A further improvement of MJO prediction requires attention to the standing MJO given its large gap with its potential predictability (38 days). The slow-propagating MJO detours southward when traversing the Maritime Continent (MC), and confronts the MC prediction barrier in the model, while the fast-propagating MJO moves across the central MC without this prediction barrier. The MJO diversity is modulated by stratospheric quasi-biennial oscillation (QBO): the standing (slow-propagating) MJO coincides with significant westerly (easterly) phases of QBO, partially explaining the contrasting MJO prediction skill between these two QBO phases. The SPEAR model shows its capability, beyond the propagation, in predicting their initiation for different types of MJO along with discrete precursory convection anomalies. The SPEAR model skillfully predicts the observed distinct teleconnections over the North Pacific and North America related to the standing, jumping, and fast-propagating MJO, but not the slow-propagating MJO. These findings highlight the complexities and challenges of incorporating MJO prediction into the operational prediction of meteorological variables.