Is it possible to predict el nino

At the regional level, seasonal outlooks need to assess the relative effects of both the ENSO state and other locally relevant climate drivers. Research conducted over recent decades has shed considerable light on the important role played by interactions between the atmosphere and ocean in the tropical belt of the Pacific Ocean in altering global weather and climate patterns.

These temperature changes are strongly linked to major climate fluctuations around the globe and, once initiated such events can last for 12 months or more. The forecasting of Pacific Ocean developments is undertaken in a number of ways.

Complex dynamical models project the evolution of the tropical Pacific Ocean from its currently observed state.

Statistical forecast models can also capture some of the precursors of such developments. Expert analysis of the current situation adds further value, especially in interpreting the implications of the evolving situation below the ocean surface.

All forecast methods try to incorporate the effects of ocean-atmosphere interactions within the climate system. The exchange and processing of the data are carried out under programmes coordinated by the WMO.

It is based on contributions from the leading centres around the world monitoring and predicting this phenomenon and expert consensus facilitated by WMO and IRI. Skip to main content. Many state-of-the-art forecasting models use mathematical equations to power their predictions. These models elegantly simulate the physical relationships between the ocean and the atmosphere, but they contain slight errors that compound over time, rendering long-term forecasting unmanageable.

On the other hand, models based solely on analyzing data, called statistical models, have traditionally lacked a sufficient number of measurements to make them robust. The latest study led by Ham from Chonnam National University in South Korea built a statistical model that skirts the problem of data scarcity. Ham and his colleagues fed their model data from both sophisticated climate models and an ocean reanalysis model that gave them global snapshots of ocean temperatures since the late 19th century.

Using these model outputs increased the number of available data from about measurements to nearly 3, per month. With a new trove of available data, the scientists used an artificial intelligence technique called deep learning to analyze it. Deep learning is often used in image recognition: The technique identifies noteworthy qualities in an image and systematically classifies it through a series of steps. The SST data during the early decades such as shown in Fig.

While data based on reanalysis are not expected to be as accurate as actually measured data at least in regions lacking the original measurements , they are usually approximately correct. A Brazilian reader suggested the location was most likely one of two places called "Queimadas" in eastern Brazil. The text and caption have been updated. Barnett , T. Science, , Cane, M. Dolan, and S.

Glantz, M. McPhaden, M. Timmermann, M. Widlansky, M. Balmaseda and T. Meinen, C. Climate , 13 , Quinn, W. University of California, San Diego. Wyrtki, K. Stroup, W. Patzert, R. Williams, and W. Science , , References Barnett , T.

Add new comment. Perfect explanation Permalink. Perfect explanation.