Drought is one of the important natural disasters that may happen in any climate conditions. Since drought is inevitable phenomenon, therefore familiar with that natural disaster is very important for reliable water management. Drought prediction system design is one of the efficient ways that it can minimize the drought damages. In this research for predicting the coming drought, genetic algorithm and conjoined model of neural network-wavelet is used for analyzing standardized precipitation index. The results show that genetic algorithm and conjoined model of neural network-wavelet is more satisfactory than genetic algorithm and neural network.