Combination of SOM-RBF for drought code prediction using rainfall and air temperature data

Abstract

This study aims to predict Drought Code (DC) in Kabupaten Kubu Raya using a combination of SOM-RBF. The final weight value of SOM was used as a center on the RBF network. The input data variables are rainfall data and air temperature data for three days with three binary outputs to predict DC values. This study also observed the effect of the number of neurons, learning rates, and the number of iterations on the results of the SOM-RBF network training. The smallest MSE of training result from the SOM-RBF network was 0.159933 using 65 neurons in the hidden layer, learning rate 0.007, and epoch 45000. The detection accuracy of SOM-RBF was 91.34 % from 245 test data.

Application of Support Vector Machine on Drought Code Classification in North Sumatra Indonesia

“…DC is a numerical level of water content contained in the organic layer below the soil surface. DC is used as an indicator of the level of potential ease of occurrence of forest fires in terms of weather parameters [4]. The highest DC ratings occur more frequently in peatland fires.…”