Yoo-Geun Ham and colleagues present a deep learning approach that is able to predict El Nino events. The model was trained using historical climate data from 1871 to 1973 and simulations of El Nino events, and tested with data from 1984 to 2017. The deep learning algorithm was able to predict El Nino events with greater accuracy than current climate forecasts and with a longer lead time of up to one and a half years. The authors were also able to use their forecasting model to predict whether the event originated in the central or eastern Pacific, and identified sea surface temperature changes that precede an El Nino event.
The authors propose that the forecasts provided by this approach could also be used for future climate projections and to help inform policy responses to the impacts of El Nino.
(reference: https://www.natureasia.com/en/research/highlight/13091 )
(more: https://www.nature.com/articles/s41586-019-1559-7/metrics )
This lab (Ocean & Climate Science Lab) conducts studies
- Climate forecasts using a deep learning technique
- Seasonal to decadal prediction by using a global coupled climate model
- The development of the initialization system including the data assimilation and the optimal perturbation method for sub-seasonal
- Sub-seasonal, interannual and decadal climate variability over the tropics (e.g. El nino, AMOC)
- Climate change/sensitivity after the global warming
To understand the physical mechanisms of the climate variability and the improvement of the seasonal predictability is the main aim of the research.