ABSTRACT
Due to the obscure and lack of sufficient knowledge about physical processes in hydrological cycle, stochastic modeling is an important activity in the field of hydrology and water resources management. Drought has the stochastic behavior and the important role in water resources planning and management. Rainfall is one of the most important elements in water cycle and drought analysis. Therefore, rainfall forecasting is an important activity in water resources planning and management. This chapter is concerned with forecasting methods based on the use of time series analysis. The concepts of random variable have been used in the field of hydrology since the beginning of the twentieth century. The formal development of stochastic modeling began with the introduction and application of autoregressive models to seasonal and annual hydrologic time series. The process of time series modeling and forecasting can be divided as follows: selection of the model among the range of AR(p), ARMA(p, q), ARIMA(p, d, q), and SARIMA(p, d, q)(P, D, Q)s models, selection of the order of models by using the autocorrelation and partial autocorrelation functions, determination of the parameters of the models, and simulation and validation for data generation and forecasting. This chapter is divided into time series analysis and time series modeling. An example is finally given on rainfall data in Iran.
