JWSS - Journal of Water and Soil Science

Drought as a natural hazard is a gradual phenomenon, slowly affecting an area; it may last for many years and can have devastating effects on the natural environment and in human lives. Although drought forecasting plays an important role in the planning and management of water resource systems, the random nature of contributing factors contributing to the occurrence of and severity of droughts causes some difficulties in determination of the time when a drought begins or ends. The present research was planned to evaluate the capability of linear stochastic models, known as multiplicative Seasonal Autoregressive Integrated Moving Average (SARIMA) model, in the quantitative forecasting of drought in Isfahan province based on the Standardized Precipitation Index (SPI). To this end, the best SARIMA models were chosen for modelling the monthly rainfall data from 1990 to 2017 for every 10 synoptic stations in Isfahan province to forecast their monthly rainfall up to five years. The monthly time scale SPI values based on these predictions were used to assess the drought severity of different stations for the 2018- 2022 time period. The station results indicated a weak drought at the 2019- 2022 period for Isfahan, Kashan and Naeen, a severe drought in 2019 for Ardestan and Golpaygan, and a weak one in 2019 for the East of Isfahan, KabootarAbad and Shahreza stations. All other stations, except Golpayegan, Isfahan, Kashan and Naeen, faced a severe drought in 2018.

In this study, we used the ARIMA time series model, the fuzzy-neural inference network, multi-layer perceptron artificial neural network, and ARIMA-ANN, ARIMA-ANFIS hybrid models for the modeling and prediction of the daily electrical conductivity parameter of daily teleZang hydrometric station over the statistical period of 49 years. For this purpose, the daily data for the 1996-2004 period were used for model training and data for the 1996-2006 period were applied for testing. In order to verify the validity of the fitted ARIMA models, the residual autocorrelation and partial autocorrelation functions and Port Manteau statistics were used. PMI algorithm were   then used to model and predict electrical conductivity for selecting the effective input parameter of the neural fuzzy inference network and the artificial neural network. The daily parameters of magnesium (with two days delay) and sodium (with one day delay), heat (with one day delay), flow rate (with two months delay), and acidity (with one day delay) were obtained with the lowest values of Akaike and highest values of hempel statistics as the input of the neural fuzzy inference network and the artificial neural network for modelling daily electric conductivity predictions; then predictions were made. Also, models evaluation criteria confirmed the superiority of the ARIMA-ANFIS hybrid model with the trapezoidal membership function and with two membership numbers, as compared to other models with a coefficient of determination of 0.86 and the root mean square of 29 dS / m. Also, the Arima model had the weakest performance. So, it could be applied to modeling and forecasting the daily quality parameter of the tele Zang hydrometer station.