DATA.zip

INPUT : The input datasets for training and test of convolutional neural networks used in this study. We use a monthly output data from the Geophysical Fluid Dynamics Laboratory Coupled Model 2.1 control experiment of 1,000 years. The variables (sea surface temperature and sea surface height) are monthly detrended, are 3-month averaged, and are normalized by the area-averaged standard deviation. MAM season (4th per every year) is used for The resolution is 2.5 latitude × 2.5 longitude.<br>TARGET : The output variable for training and test of convolutional neural networks used in this study. We use a monthly output data from the Geophysical Fluid Dynamics Laboratory Coupled Model 2.1 control experiment of 1,000 years. The variables (sea surface temperature and sea surface height) are monthly detrended, are 3-month averaged, and are normalized over time. DJF (12th per every year) Nino3.4 (5S-5N, 170-120W) sea surface temperature anomalies are used.