| چکیده انگلیسی مقاله |
Introduction Today, drought is one of the most important natural hazards that has direct and indirect consequences in different parts of the planet (barqi et al., 2018: 141). Nevertheless, drought is one of the environmental events and an integral part of climate fluctuations. This phenomenon is one of the main characteristics and recurrence of different climates (Hejazizadeh and Javizadeh, 2019: 251 ) The purpose of this study was to analyze the temperature and precipitation data first, then, using ANFIS and RBF model model, a model-comparative model was developed and the new S.M.S drought index was designed. Finally, in order to better visibility of the drought situation for the future, in areas affected by drought in southern regions of Iran were predicted. Material and method In this study, after the 29-year data on temperature and precipitation data for 28 stations in the drought areas of Iran, the data were first analyzed, then normalized and the stations with abnormal data were normalized. After normalizing the temperature and precipitation data, using two new and powerful applied models for modeling and forecasting in climateology, namely ANFIS and RBF neural network models, were modeled. Then, the two models were compared for accurate prediction for the future, and after training three SPI, MCZI, and SET data, they predicted a new drought index called SMS, for the coming years, and Finally, using the TOPSIS multivariate decision making model, the areas most involved with the drought risk phenomenon were prioritized and ArcGIS software delimited the output data. Results Drought is a natural hazard, which is evident gradually over the long years due to climate change in its affected areas. Which effects itself on different parts of the living environment of living organisms. One of these areas in Southwest Asia is Iran, which in recent years has shown drought in its regions, especially the southern regions of high intensity. According to the comparisons of ANFIS and RBF neural network models, the two models were able to predict the drought. The results obtained from the training of the ANFIS neural network model were, at best, RMSE values equal to 9.64 and R2 values equal to 0.0681. But the results obtained from the training of the RBF neural network model were, at best, RMSE equal to 1.15 and the R2 value was 0.9961By comparing these two models, it was finally concluded that the performance of the RBF neural network model was better. According to the modeling and the results obtained from the comparison of the models, the accuracy and reliability of the RBF neural network model was confirmed for prediction. The prediction of the RBF neural network model was used. Modeling and predicting droughts in 28 synoptic stations in southern regions of Iran were compared using SMS fuzzy new index and ANFIS, RBF models. The methods used in this study, in most studies, Monitoring, Modeling and Comparison. Among these, studies have been done in Iran: Zeinali and Safarian-zengir (2017) by studying drought monitoring in the Lake Urmia basin using Fuzzy index; Babayan et al. (2018), the monthly forecast of drought in the southwestern basin of the country Using the CFSv.2 model, they confirmed the model's acceptable accuracy. However, with all the comparisons of different models and indices in these researches, the new SMS fuzzy index and two ANFIS and RBF models used in this study, namely, modeling and predicting the natural hazards of drought In the southern regions of Iran, it has an acceptable performance. Conclusion The purpose of this study was to model and investigate the possibility of drought prediction in the southern half of Iran. To do this, the fuzzyization of the SMS index, based on the three SPI, MCZI, SET, comparisons and the results of two new simulation models in Climatology, the ANFIS and RBF neural network models, as well as the TOPSIS multivariate decision making model. The results showed that the S.M.S index reflected the three SPI, MCZI, and SET indices. Comparing two models of ANFIS and RBF neural networks, the RBF model is more accurate than the ANFIS model. As a result, for prediction of drought, RBF model was used for future years. The results showed that the S.M.S index reflected the three SPI, MCZI, and SET indices. Comparing two models of ANFIS and RBF neural networks, the RBF model is more accurate than the ANFIS model. As a result, for prediction of drought, RBF model was used for future years. The accuracy of the RBF model at best was RMSE equal to 1.15 and the R2 value was 0.99 The results of the fuzzification of the SMS index showed that the central and western parts of the study areas such as Kerman, Yasuj and Abadan, with the SMS drought percentage (0.99, 0.97 and 0.89), respectively, were higher Exposed to the drought. |