Mohammad Ansari Ghojghar; Sosan Salajegheh; Paria Pourmohammad
Abstract
This study aims to model dust storms in Khuzestan province using hybrid Jenkins-Catalyst SARIMA-ACOR and SARIMA-PSO models. For this purpose, hourly dust data and codes from the World Meteorological Organization (WMO) were used from seven synoptic stations across Khuzestan over a 40-year period. To enhance ...
Read More
This study aims to model dust storms in Khuzestan province using hybrid Jenkins-Catalyst SARIMA-ACOR and SARIMA-PSO models. For this purpose, hourly dust data and codes from the World Meteorological Organization (WMO) were used from seven synoptic stations across Khuzestan over a 40-year period. To enhance accuracy and minimize potential errors, this research employs the integration of optimization algorithms, namely Ant Colony Optimization (ACOR) and Particle Swarm Optimization (PSO), with the Box-Jenkins SARIMA model. The optimization algorithms are used for model training, parameter selection, pattern recognition, clustering, reinforcement learning, image processing, intelligent system design, and optimizing generative models. To determine the best-fitting model, the goodness-of-fit criteria, including R, RMSE, MAE, and NS, were applied. The results indicate that the hybrid SARIMA-ACOR model outperforms both the SARIMA-PSO hybrid model and the standalone SARIMA model. Among the seasonal combinations tested, combinations one and two demonstrated the highest performance and accuracy. The SARIMA-ACOR hybrid model showed superior performance in predicting the FDSD index, with Root Mean Square Error (RMSE = 0.219–0.198), Correlation Coefficient (R = 0.891–0.859), Mean Absolute Error (MAE = 0.142–0.123), and Nash-Sutcliffe Efficiency (NS = 0.881–0.862) compared to the other models.
Ommolbanin Bazrafshan; Ali Salajegheh; Ahmad Fatehi; Abolghasem Mahdavi; Javad Bazrafshan; Somayeh Hejabi
Abstract
Drought is random and nonlinear phenomenon and using linear stochastic models, nonlinear artificial neural network and hybrid models is advantaged for drought forecasting. This paper presents the performances of autoregressive integrated moving average (ARIMA), Direct multi-step neural network (DMSNN), ...
Read More
Drought is random and nonlinear phenomenon and using linear stochastic models, nonlinear artificial neural network and hybrid models is advantaged for drought forecasting. This paper presents the performances of autoregressive integrated moving average (ARIMA), Direct multi-step neural network (DMSNN), Recursive multi-step neural network (RMSNN), Hybrid stochastic neural network of directive approach (HSNNDM) and Hybrid stochastic neural network of recursive approach(HSNNRM) with time scale monthly and seasonally for hydrology drought forecasting and SDI selected as predictor in the Karkheh river basin. The results shown performances of HNNDA was found to forecast hydrological drought with greater accuracy for SDI forecasting, so performances model in monthly scale was greater accuracy to seasonality scale.
