Univrsity Of Tehran Press Water and Irrigation Management 2251-6298 12 1 2022 03 21 Evaluation of structural approaches to state space compared to classical in predicting precipitation time series ( Dez catchment) Evaluation of structural approaches to state space compared to classical in predicting precipitation time series ( Dez catchment) 1 13 86598 10.22059/jwim.2022.336530.956 FA Mohammadreza Sharifi Assistant Professor, Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Amin Mohammadzadeh Shobegar Ph.D. Student in Water Resources, Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Fereydoon Radmanesh Associate Professor, Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Behzad Mansouri Associate Professor, Department of Statistics, Faculty of Mathematics and Computer Science, Shahid Chamran University of Ahvaz, Ahvaz, Iran. Journal Article 2021 12 30 In this paper, a study on the use of precipitation prediction techniques with time series data was presented. Time series are an effective tool for understanding the nature of hydrological phenomena that with sufficient knowledge of them, future changes can be modeled and predicted. Various statistical models have been considered with the aim of reducing error and increasing forecast accuracy. Due to its structural and flexibility, state space makes it possible to model each of the components of a variable, including surface, seasonal and random separately. Therefore, by identifying the system in the way of modeling the studied variable, it is possible to control and minimize the estimation error, more intelligently compared to classical models. In the present study, in order to evaluate the modeling capability of state space and compare it with classical models, monthly preciptation modeling was performed in three rain gauge stations in Dez catchment, with four structural models of state space including Kalman filter, ETS exponential smoothing model and Modified exponential smoothing models were BATS and TBATS and the classic model was ARIMA. The results showed that at Sepiddasht Sezar station based on RMSE and MAE criteria of TBATS model and in Tangpanj Bakhtiyari station based on RMSE and MAE criterion of Kalman filter model and in Telezang station according to RMSE and MAE criterion of TBATS model the best models were chosen. In this paper, a study on the use of precipitation prediction techniques with time series data was presented. Time series are an effective tool for understanding the nature of hydrological phenomena that with sufficient knowledge of them, future changes can be modeled and predicted. Various statistical models have been considered with the aim of reducing error and increasing forecast accuracy. Due to its structural and flexibility, state space makes it possible to model each of the components of a variable, including surface, seasonal and random separately. Therefore, by identifying the system in the way of modeling the studied variable, it is possible to control and minimize the estimation error, more intelligently compared to classical models. In the present study, in order to evaluate the modeling capability of state space and compare it with classical models, monthly preciptation modeling was performed in three rain gauge stations in Dez catchment, with four structural models of state space including Kalman filter, ETS exponential smoothing model and Modified exponential smoothing models were BATS and TBATS and the classic model was ARIMA. The results showed that at Sepiddasht Sezar station based on RMSE and MAE criteria of TBATS model and in Tangpanj Bakhtiyari station based on RMSE and MAE criterion of Kalman filter model and in Telezang station according to RMSE and MAE criterion of TBATS model the best models were chosen. https://jwim.ut.ac.ir/article_86598_3b02b131062b72a17cbe28cf42f3650d.pdf