Tropical cyclone intensity prediction using regression method and neural network

Using the multiple linear regression method and the standard back-propagati on neural network, tropical cyclone intensity prediction over the western N orth Pacific at 12, 24, 36, 48, 60, and 12 h intervals is attempted. The da ta contain a 31-year sample of western North Pacific tropical cyclones from 1960 to 1990 and eight climatology and persistence predictors are consider ed. The percent of variance explained by the neural network model is consis tently larger than that explained by the regression model at all time inter vals with an average difference of 12 %. The average intensity prediction e rrors from the neural network model are 10-16 % smaller, except at 12 h whe re the errors are nearly equal, than those from the regression model. This study clearly shows potential of the neural network in the prediction of tr opical cyclone intensity.