Related Experiment Videos
Tropical basin interactions reduce spring predictability barrier of ENSO in a deep learning model
Lu Zhou1, Rong-Hua Zhang1,2
1State Key Laboratory of Climate System Prediction and Risk Management/Key Laboratory of Meteorological Disaster, Ministry of Education/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters/School of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, China.
Science Advances
|May 20, 2026
Summary
The El Niño-Southern Oscillation (ENSO) experiences a spring predictability barrier (SPB). A new deep learning model, GL-Geoformer, effectively reduces this barrier by incorporating tropical basin interactions, improving ENSO forecasts.
Area of Science:
- Climate Science
- Oceanography
- Artificial Intelligence
Background:
- The El Niño-Southern Oscillation (ENSO) shows reduced predictability during boreal spring, known as the spring predictability barrier (SPB).
- Tropical basin interactions are recognized for potentially improving ENSO predictability, but their role in mitigating SPB within deep learning (DL) frameworks is underexplored.
Purpose of the Study:
- To introduce GL-Geoformer, a novel deep learning model designed for global tropical ocean-atmosphere prediction.
- To investigate the impact of tropical basin interactions on reducing the SPB in ENSO prediction using DL.
- To quantify the contributions of Indian Ocean Dipole and Atlantic Niño to ENSO predictability.
Main Methods:
- Development of GL-Geoformer, a DL model capturing spatiotemporal evolutions of wind and 3D temperature anomalies across tropical basins.
- Utilizing pacemaker experiments to isolate and quantify the nonlinear contributions of specific ocean-atmosphere interactions.
- Data-driven modeling to represent complex tropical basin interactions.
Main Results:
- Incorporating tropical basin interactions significantly reduces the SPB.
- GL-Geoformer achieves skillful ENSO predictions up to 16 months in advance when initialized in spring.
- Subsurface heat transport and Walker circulation are identified as key mechanisms through which Indian Ocean Dipole and Atlantic Niño influence ENSO predictability.
Conclusions:
- Tropical basin interactions are crucial for mitigating the SPB and enhancing ENSO predictability.
- The GL-Geoformer model provides a data-driven framework for understanding and reducing SPB.
- This research deepens the understanding of ENSO predictability by leveraging DL and inter-basin dynamics.
Related Concept Videos
01:12Precipitation Processes
The experimental conditions in a gravimetric analysis should be optimized to maximize the particle size and purity of the obtained precipitate. Ideally, the concentration of the precipitating reagent should be low with effective stirring to maintain low relative supersaturation for the growth of large crystals. In homogeneous precipitation, the precipitant is slowly generated by a chemical reaction in the solution to avoid local reagent excesses. For example, urea decomposes gradually to...
01:17Precipitation and Co-precipitation
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...
01:19Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...
01:50Global Climate Change
Throughout its ~4.5 billion year history, the Earth has experienced periods of warming and cooling. However, the current drastic increase in global temperatures is well outside of the Earth’s cyclic norms, and evidence for human-caused global climate change is compelling. Paleoclimatology, the study of ancient climate conditions, provides ample evidence for human-caused global climate change by comparing recent conditions with those in the past.
01:16What is Climate?
Climate refers to the prevailing weather conditions in a specific area over an extended period. As the saying goes, “Climate is what you expect. Weather is what you get.” Climate is influenced by geographic factors, such as latitude, terrain, and proximity to bodies of water.
01:03Prediction Intervals
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
The...
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
The...