The present research was planned to evaluate the skill of linear stochastic models known as ARIMA and multiplicative Seasonal Autoregressive Integrated Moving Average (SARIMA) model in the quantitative forecasting of the Standard Runoff Index (SRI) in Karkheh Basin. To this end, SRI was computed in monthly and seasonal time scales in 10 hydrometric stations in 1974-75 to 2012-13 period of time and then the modeling of SRI time series was done to forecast the one to six months of lead-time and up to two seasons of lead-time. The SRI values related to 1974-75 to 1999-2000 were used to develop the model and the residual data (2000-2001 to 2012-13) were used in model validation. In the validation stage, the observed and the predicted values of SRI were compared using correlation coefficient, error criteria and statistical tests. Finally, models skills were determined in view point of forecasting of lead-time and the time scale of drought evaluation. Results showed that the model accuracy in forecasting two months and one season of lead-time was high. In terms of the forecasting of SRI values, the skill of SARIMA in monthly time scale (with a RMSE and a MAE of 0.61 and 0.45 respectively and a correlation coefficient average of 0.72) was better than its skill in seasonal time scale. The application of SARIMA in monthly time scale was therefore preferred to its application in seasonal time scale.

Accurate precipitation forecasts are much attractive due to their complexity. This study aimed to use the hybrid Seasonal Autoregressive Integrated Moving Average (SARIMA) model and machine learning techniques such as Artificial Neural Networks (ANN) and Support Vector Machines (SVM) to improve precipitation forecasts. Time variation analysis and time series decomposition were the two concepts applied to construct the hybrid models. The performance of the two concepts was evaluated with monthly precipitation time series of two stations in northern Iran. Time variation analysis of time series was conducted with the clustering analysis, which increased the accuracy of forecasting with 20.99% decrease in the geometric mean error ratio for the two stations. SVM model decreased the forecasted error compared to ANN in the internal process of time variation analysis. Average of Mean Relative Error (MRE) were MRESVM= 0.72, MREANN= 0.89, and Mean Absolute Error (MAE) in the two stations were MAESVM= 18.02 and MAEANN= 23.88. Therefore, SVM outperformed the ANN model. Comparison of the two hybrid models indicated that more accurate results belonged to the concept of time series decomposition (the decrease in root mean square error from time variation to time series decomposition concepts was 13.35%). Extracting the pattern of data with SARIMA-based hybrid model with time series decomposition improved the precipitation forecasting. Configurations related to nonlinear components of time series with time steps of residual had good performance (the average of agreement index was 0.9). The results suggest that the hybrid model can be a valuable and effective tool for decision processes, and time series decomposition to linear and nonlinear components has a better performance.

The analysis of spatio-temporal series is crucial but a challenge in different sciences. Accurate analyses of spatio-temporal series depend on how to measure their spatial and temporal relation simultaneously. In this article, one-sided dynamic principal components (ODPC) for spatio-temporal series are introduced and used to model the common structure of their relation. These principal components can be used in the data set, including many spatio-temporal series. In addition to spatial relations, trends, and seasonal trends, the dynamic principal components reflect other common temporal and spatial factors in spatio-temporal series. In order to evaluate the capability of one-sided dynamic principal components, they are used for clustering and forecasting in spatio-temporal series. Based on the precipitation time series in different stations of Golestan province, the efficiency of the principal components in the clustering of hydrometric stations is investigated. Moreover, forecasting for the SPI index, an essential indicator for detecting drought, is conducted based on the one-sided principal components.

Box-Jenkins prediction model is one of the most famous time series models and is important in predicting different geographic phenomena. In Box-Jenkins methodology, time series models are in fact autoregressive integrated moving average models that are known as ARIMA models in statistics. Various models such as simple and multivariate regression, autoregressive, moving average, seasonal models and even unknown models can be derived from ARIMA models. In this research, while expressing the precipitation forecasting method using the Box-Jenkins time series model practically and by fitting this model on the monthly precipitation data of Ghaemshahr synoptic station, which contains statistics of 50 years, the best model for forecasting precipitation in this station was selected, which was from the type of SARIMA (1.0.1) (0.1. 1) model.

Urmia Lake in Iran is the second largest saline lake in the world. Due to various socio-economical and ecological criteria, Urmia Lake has important role in the Northwestern part of the country but it has faced many problems in recent years. Because of droughts, overuse of surface water resources and dam constructions water level is reduced. One of the important factors that has influence in correct management, is having a suitable point of view for future events in that field. So simulation and forecasting of hydrological variables has many importance. In this research, time series, Artificial Neural Network and Neural Network-Wavelet methods for presentation the best method in monthly scale for simulation and forecasting Urmia Lake water level is compared. Comparing these three methods indicates that forecasting with Neural Network-Wavelet due to considering monthly, seasonal and annual changes in the time series analysis, has the best Performance.

In this study, a multitude of statistical tools were used to examine PM10 concentration trends and their seasonal behavior from 2015 to 2021 in Tehran. The results of the integrated analysis have led to a better understanding of current PM10 trends which may be useful for future management policies. The Kruskal – Wallis test indicated the significant impact of atmospheric phenomena on the seasonal fluctuations of PM10. The seasonal decomposition of PM10 time series was conducted for better analysis of trends and seasonal oscillations. The seasonal Mann-Kendall test illustrated the significant possibility of a monotonic seasonal trend of PM10 (p = 0.026) while showing its negative slope simultaneously (Sen = -1.496). The forecasting procedure of PM10 until 2024 comprised 15 time series models which were validated by means of 8 statistical criteria. The model validation results indicated that ARIMA (0,1,2) was the most satisfactory case for predicting the future trend of PM10. This model estimated the concentration of PM10 to reach approximately 79.04 (µg/m3) by the end of 2023 with a 95% confidence interval of 51.38 – 107.42 (µg/m3). Overall, it was concluded that the use of the aforementioned analytical tools may help decision-makers gain a better insight into future forecasts of ambient airborne particulate matter.

Long-term drought prediction is of considerable importance in water resources management. Time series models are appropriate tools to predict climatic events. In this study, the Reconnaissance Drought Index (RDI), which is based on precipitation and potential evapotranspiration, was applied to calculate droughts of Yazd synoptic station at time scales of one, three, and six months from 1961 to 2018. The period 2006-2018 was selected as the forecast period. Drought data of the forecast period were not considered to the applied models. Results showed that the pattern of drought data at 1, 3 and 6-month time scales in the Yazd synoptic station is seasonal. The SARIMA is a univariate time series model created by adding a seasonal component to the ARIMA model. The SARIMAX multivariate model is created by adding parameter covariate variable (exogenous variable) to SARIMA. In the present study, the efficiency of the seasonal univariate model (SARIMA) and seasonal multivariate model (SARIMAX) in predicting drought in arid regions were compared. To implement the SARIMAX model to predict droughts, precipitation and potential evapotranspiration were provided to the model as covariates, separately. The results of the coefficient of determination (R2) between observed RDI and predicted RDI values by SARIMA showed that the model offers higher performance on 3 and 6-month time scales with 0.66 and 0.71, respectively. The results of the SARIMAX model showed that in one-month time scale, the SARIMAX model based on potential evapotranspiration with 0.60, and for 3-month time scale, the SARIMAX model based on precipitation with 0.79 performed better. In 6-month time scale, the performance of the model for the both covariates were almost the same with the coefficient of determination of 0.79. Comparison of the results of the two models showed that the performance of the SARIMAX model is higher than the SARIMA model for drought predicting in arid regions.

The most important pillar of a scientific and applied research is the statement of the problem, when a problem can be scientific and practical that creates a challenge in relation to the solution of the problem and clearly defines the purpose of the work, as well as the challenges that have arisen in relation to the problem in question, the researcher uses Simulation models can overcome one of the challenges and work as a source of information for climate researchers to use for future research. In this research, the statement of the present problem is the statement of forecasting the average seasonal temperature. What element is temperature, the answer to these questions and reasons, let's hypothesize against it, after formulating the assumptions, prepare climatic data of temperature of the study area and the neighboring stations of the area, and also specify the study area To start the work, using modeling (simulation) and comparison and accuracy of forecasting, he used two models by comparing and measuring the accuracy of their errors, because Temperature is a physical quantity, some of the sun's radiant energy is absorbed by the earth's surface and becomes thermal energy.This energy is expressed in the form of temperature or degrees. Among the different climatic elements, temperature and precipitation are of special importance to predict this. The important key climatic element, our goal is to examine the seasonal average temperature changes in the seasons and determine the seasonal changes with 95% and 80% accuracy using artificial neural network - Arima time series model, RMSE index, and also the models together Let's compare which predicts temperature changes better. So that researchers can use and test these models in future researches to predict other climate parameters and also the impactful consequences of seasonal temperature changes and climate elements such as relative humidity - evaporation and transpiration - industry - transportation - bridges and other infrastructures. Proper planning and management should be done in this regard. In the 21st century, climate change is considered one of the biggest environmental threats to the world. Changes in Farin's climate are estimated to have more negative effects on human society and the natural environment than changes in the average climate (Mahmood and Babel, 2014: 56). Based on the fourth report of the International Commission on Climate Change, which was published under the title of Climate Change Assessment Reports, the global increase in temperature and the occurrence of climate change have been confirmed by using the measured data of the surface temperature of land and water in the world (IPC Si, 2014: 32). The first effect of climate change on atmospheric elements is especially temperature and precipitation, then due to the relationship between atmospheric elements and terrestrial ecosystems, water resources, vegetation, soil and also human life will be affected by this phenomenon; Therefore, investigating the trend of atmospheric variables such as temperature is of particular importance (Abkar et al., 2013: 14).Temperature Some of the radiant energy of the sun absorbed by the effects of the earth's surface turns into thermal energy. This energy is manifested in the form of temperature or degree. Among the different climatic elements, temperature and precipitation are of particular importance. Although the main cause of temperature is the energy obtained from the absorption of short solar radiation on the earth's surface.Using artificial neural network and Arima time seriesThe purpose of this research is to model forecasting changes in seasonal average temperature in the study area of Al-Shatar city using artificial neural network and Arima time series model and to determine the measurement accuracy of neural network models and Arima time series model in forecasting average temperature changes and also The above simulation models should be used to predict the research of future climate researchers and be realized.The main goals of this research are to model and identify seasonal average temperature changes and the relationship of this key element with other climatic parameters of Al-Shatar city. In terms of seasonal average temperature changes and prioritizing areas with temperature variability.This part of the research has monitored and simulated the regression error of Lorestan stations (Alshatar-Broujerd-Aligodarz-Noorabad-Khorramabad-Poldakhter) in the time period (1998-2018) of the stations of Lorestan province with the temporal-spatial analysis of the RMSE index. The obtained results show that the indicators of the cold period of the year in the current situation in different areas (stations of Lorestan province) have had different trends, but the average temperature of the cold seasons of autumn and winter is an increasing trend, which results in the melting of the glaciers and snowfall. Rain is coming and this process is predicted for the next eleven (11) years. In general, the results obtained in this section have shown that the heat waves in the future will be more intense, sharper and more lasting than the current situation, and the highest temperature fluctuations in the autumn season, which is 81. Using RMSE = .003 and ME = .86, it is the artificial neural network that has the best efficiency and performance in Elshatar city station and predicts the average temperature better than the Arima time series model, therefore the artificial neural network model and Arima time series Both have 95% and 80% measurement accuracy. It is better to use these models and other machines in future research to predict the minimum and maximum temperature and other climatic elements. Because they have the best performance and efficiency in forecasting the elements, forecasting the average seasonal temperature can help to plan and manage, control evaporation and transpiration and other resources of the country and Al-Shatar city. It is summer and the least accuracy is in autumn and winter. Considering that the prevailing rain-producing air masses in Al-Shatar city leave the most seasonal changes in autumn and winter, it can be concluded that the most temperature fluctuations occur in the cold seasons of the year and the least fluctuations in The summer season occurs due to the deactivation of the rain-producing western wind, whose value is 33/. Is

The Penman FAO is one of the appropriate methods for the estimation of evapotranspiration at Bajgah experimental station, Shiraz University. Modeling and forecasting of weekly and monthly time series of evapotranspiration with Penman FAO method using seasonal auto-regressive integrated moving average (SARIMA) models as the linear stochastic models for this station were studied. The time series data of weekly and monthly average of evapotranspiration for the period 1366-1386 were separately considered as the input file of SARIMA models. On the basis of the corrected Akaike's information criterion (AIC) and significant coefficients, and models were selected for weekly and monthly time scales, respectively. The auto-correlation function plots of the residuals for these models have indicated that the residuals are uncorrelated. The weekly and monthly values of evapotranspiration from Khordad 1386 to Ordibehsht 1378 as the test data was forecasted using the fitted models. The results have indicated that the square of correlation coefficient between the observed and predicted values for weekly and monthly time scale is 0.92 and 0.99, respectively. The root mean square error for weekly and monthly time scale is respectively, 0.48 and 0.16 mm.

Statistical modeling has been used for seasonal rainfall forecasting based on synoptical patterns of the atmospheric upper levels in Khorasan province - northeast of Iran. The data of 37 rainfall stations were obtained from Iranian Meteorological Organization and the first stage was filling the gaps estimating and missing data using statistical methods. At the second stage, the RUN-TEST homogeneity procedure were done to find out if the rainfall data are randomly collected. Mean local time series of rainfall have been calculated by Arc GIS software. In order to forecast the seasonal rainfall in the period of Dec ember to May, the relations between rainfall and atmospheric upper level parameters at the difference time intervals were used as inputs of statistical model. Results show that the statistical modeling can successfully predict amount of the rainfall. Root mean square error obtained by stepwise and backward models were 50.4 and 47.3 millimeter respectively.