| dc.description.abstract | In Indonesia, agriculture becomes an important sector for national development and national economy. The length of rainy season is one of the rainfall variables that affect agricultural production. The changing of the rainy season length can impact on crop failures. This research aims to develop a model for predicting the length of rainy season using Cascade Neural Network (CNN). Predictor data used in this research is sea surface temperature from region of NINO 1+2, NINO 3, NINO 4, dan NINO 3.4 from 1982 to 2011. Observational data used is the length of rainy season of Pacitan region in Arjosari, Kebon Agung, and Pringkuku weather stations from 1982/1983 to 2011/2012. This research obtained the best model from Pringkuku weather station with R2 of 0.72 and RMSE of 1.87 using a learning rate of 0.3, 10 hidden neurons and NINO 4 region. | en |
