This research focuses on the seasonal prediction of precipitation in Thailand. Seasonal scale prediction requires to consider mutual relationship between atmosphere, ocean and land. 9 climate indices are investigated in order to extract features of those relationship. 2 statistical model, Multi linear regression model(MLR) and Genetic programming model(GP) are applied for prediction.
As a result, GP succeeded to predict large fluctuations in some years. MLR, however, underestimated these fluctuations. GP still has to be improved for practical use for dam operation.