JOURNAL OF WATER AND SOIL RESOURCES CONSERVATION
Year:2021 | Volume:10 | Issue:2|Papers Count:10

Accurate investigation related to the structure of time series plays an important role in increasing the accuracy of ARIMA forecasting. The aim of this research is to investigate the effect of modeling decomposition of linear and non linear parts of time series on ARIMA model results. The decomposition of wheat and maize yield time series (in Kermanshah and Esfahan provinces) in the linear part was related to ARIMA and in the non linear part was conducted with support vector regression (hybrid model). The kind of configuration of non linear part of hybrid model is more important for example in the maize time series of Kermanshah, the values of RMSE for configuration with residual was 1. 52 and for time series configuration was 15. 03. The decreasing of RMSE, MAE and UII for wheat time series of Esfahan with hybrid model was 45. 94%, 52. 29% and 46%, respectively which is indicative of hybrid model improvement. The value of GMER in all four time series was greater than one which indicates the overestimation of hybrid model. Comparison the average of each criteria with two models and crops in each province indicated the effect of climate on modeling process because the average of criteria in Esfahan province decreased rather to Kermanshah (RMSE decreasing= 24. 72%, UII decreasing=12. 24%). Therefore, decomposition of time series to linear and non linear parts of time series can increase the accuracy of ARIMA model results.

Soil moisture content (SMC) as a small part of water balance, nearly considered in all hydrological process and soil and atmosphere tradeoff. Therefor its prediction is useful in planning, designing and decision making. For this, purposeweekly SMC in 40 weeks was measured by Time Domain Refl ectometry in 3 different location of wheat and rangeland in Loess deposits (West of Gorgan with 27 ha area) at 20cm intervals down to the 80cm depth. SMC in all considered depths and locations had trend for study period and the best model was selected regards to Akaike information criterion (AIC). The best prediction model in rangeland belongs to 60cm depth (R= 0. 96). For all considered depths except 40cm in one location in wheat, Integrated Moving Averages (1, 1) was selected as the best model. For the other location in the same land cover, the best prediction model devoted to 20cm depth (R= 0. 86). Integrated Moving Averages (1, 1) for all study locations had the highest priority. Considering tillage practices in crop land and following plough pan in 40cm depth, Autoregressive Integrated moving Average (1, 1) selected as the best model for prediction.

Standard precipitation index (SPI) is the most widely drought monitoring index. However, this index only uses the gamma distribution function for fitting precipitation data and does not consider seasonal variations. The purpose of this study was to evaluate the efficiency of SPI in drought monitoring of arid and semi-arid regions of Iran and fix the related problems with this Index. Then the SPI was compared with its modified state (SPImod) over (1956– 2010). The results showed that the generalized extreme value distribution function in more than 57% of the cases was the most appropriate probability distribution function of rainfall data. But the default distribution (Gamma) was selected only in 11% of months. Comparison of Kappa index showed that with increasing time window, the agreement between SPImod and SPI indexes increases. The amount of one-month Kappa for studied stations was Tehran (0. 31), Mashhad (0. 33), Bushehr (0. 32) and Khorram-Abad (0. 26), while for nine-month the Kappa increased. Such that in Tehran (0. 49) and in Mashhad, Bushehr and Khorramabad, respectively, with values (0. 47), (0. 56) and (0. 45). Also, the results showed that the frequency and displacement of drought classes would be very variable in comparison to these two indices. As the displacement of normal, severe drought and severe, with a total of 259, 147 and 111 events in the time window-three and displacement of moderate drought, normal and moderate wet year, with a total of 68, 54 And 28 events in time window-nine were noticeable.

Accurate estimation of sediment transport in rivers due to erosion is an important factor for the management of hydrological and ecological projects. Artificial neural networks are of great importance for many reasons, such as the ability to detect patterns, the good relationship between input and output, and the need for less input data to predict suspended sedimentation. Accordingly, the present study attempts to model the estimation of suspended sediment content in the Pasikhan River using the artificial neural network of the M5 decision tree. The amount of sediment in rivers is subject to many parameters of river geometry, hydraulic flow and sediment properties. For this reason, in this study, it has been tried to reduce the number of effective parameters by first dimensioning the effective parameters on sediment transport capacity. The results showed that the initial decision tree, the M5 tree, does not require pruning and is suitable for use. Three parameters of determination coefficient (R2), mean relative error (ME) and mean squared error (RMSE) were used to evaluate the accuracy of the prediction model. The obtained values for these three parameters were 0. 851, 1037. 64 and 941. 32, respectively, indicating the suitability of these three parameters. Comparison of suspended sediment yield from decision tree model with Pasikhan River measurement data showed that the coefficient of determination was 0. 8953 which is a very good value. The results showed that this model is effective in predicting suspended sediment content in the Pasikhan River.

Artificial neural networks (ANN) are one of the data mining methods applied by many researchers in different fields of studies such as rainfall runoff modeling. To improve the performance of these networks, deep learning neural networks were developed to increase modeling accuracy. This study evaluated deep learning networks to improve the performance of artificial neural networks in Galikesh watershed and to predict flow discharge for 1, 3, 6 and 12-month time scale based on 1-to 5-month time scale lags made in rainfall and temperature data. Based on 70% and 30% of the data used for training and test respectively the results demonstrated that in all time steps, the deep learning neural network improved the performance of artificial neural network and on average RMSE decreased in both training and test from 0. 68 to 0. 65 and 0. 84 to 0. 73 respectively. Moreover, R-square was increased on average from 0. 57 to 0. 62 and 0. 51 to 0. 67 respectively in training and test. We can also denote the effect of temperature on the increase of accuracy of rainfall-runoff modeling.

Conservation of soil and water resources in arid and semi-arid countries is a serious concern for salinity. The present study was carried out in a completely randomized block design to investigate soil salt accumulation in tape irrigation. Treatments included: “ surface plaque tape” , “ semi-subsurface plaque tape in 10 cm depth of soil” , “ surface tape” , “ semi-subsurface tape in 10 cm depth of soil” and “ surface tape with mulch” . Salinity of irrigation water was 2 ds/m with Forage Maize cultivation. The results of salinity analysis indicate that salt distribution in 15-20 cm depth soil and in 10-15 cm space from dripper had highest value. Also in confidence level of 95%, in all of treatment in 0, 15 and 30 cm space of dripper and 0-20 cm depth of soil level there were different in salt but in another depth (20-40 and 40-60 cm) there weren’ t any different also, in use of drip tape irrigation system in soil texture silt-loam discrete kind of tape and location of installation, mainly salt distribution happen between 0-15 cm space of dripper and 0-20 cm depth of soil level and we have to do leaching. In this research, surface tape with mulch treatment had the highest yield and lowest water use between studied treatments. This treatment reduced the amount of salt accumulation by 10. 39% on average compared to other treatments.

In this study, rainfall and runoff data recorded of selected stations of Aras Boundary Basin were used to analyze rainfall and runoff fluctuations and they are projected for horizons, 2050. The Pettitt test was used to detect the breakpoint in rainfall and runoff time series. Trends in rainfall and runoff were also calculated using the original and modified Mann-Kendall test. The trend line slope was also obtained by Sen's estimator method. To project the future, general circulation models (GCMs) under two greenhouse gas emission scenarios i. e. RCP4. 5 (low emission) and RCP8. 5 (high emissions) were used. The Eureqa Formulize tool was used to simulate the rainfallrunoff process. Results showed that most of the abrupt changes have occurred in the second half of the 1990s. 83% of seasonal time series breakpoints were related to runoff. Also, 67% of the abrupt changes have occurred in the winter and spring seasons. The highest increase in annual rainfall (according to RCP4. 5 scenario) at Nir station is expected to be 9% and the highest decrease in annual rainfall (according to RCP8. 5 scenario) at Khoy station is predicted at 11%. It is also worth mentioning that in the seasonal time scale will have the highest rainfall reduction in summer. The Eureqa Formulize performed very well at all stations with NRMSE of less than 0. 5%. The results indicated that the lowest slope of the base period runoff trend line (in seasonal time scale) was-1. 3 million m 3 in summer at Badalan station. There will be no significant change in the annual flow in the future period.

Grouping of catchments based on their climatic factors and physiographic characteristics is a prerequisite for regional analysis of runoff and its use for estimating discharge of catchments without discharge measurement station. In this study, catchments located in Ardabil province were separated into homogeneous hydrological zones using discharge, mean annual precipitation and physiographic characteristics of catchments and hierarchical clustering method. Due to the large number of parameters, by using principal component analysis, the first four components with 83. 6% of total variance were selected as inputs for cluster analysis. Then, the optimal number of clusters was determined by using hierarchical method and drawing the tree diagram, and finally the final clustering was done by K-means method. Subsequently, the sub-catchments that followed a hydrological process were identified using the Dalrymple uniformity test. The results of the uniformity test showed that by excluding stations outside the confidence limits of each cluster, catchments that were similar in terms of annual discharge and other physiographic and meteorological parameters were clustered. Therefore, the number of sub catchments located in clusters 1, 2, 3 and 4 were 8, 4, 9 and 9 catchments, respectively, which can be used in regional analysis to estimate runoff and floods in catchments without discharge measurement data.

Splash erosion is as the first stage from process of water erosion that it cause for effect raindrop on soil surface. The amount of soil splash can change with changing the characteristics of soil physical. Therefore, the conservation from the surface soil cause the reducing the effect of raindrop energy on surface soil and so the sediment amount from the process of splash erosion decrease. Therefore, the present study was conducted to efficiency evaluation of perlite with levels of 25, 50 and 75 percent at rainfall intensity of 80 mm h-1 on splash erosion at collected soils of forest, rangeland and agricultural land uses. The experiments were carried at laboratory conditions and scale of splash cups and then the rates of splash erosion measured at different rates of perlite and collected soil from various land uses. The results showed that the application of different rates of perlite at collected soils from different land uses caused the reducing the total splash and net splash at compared with control treatment. Also the results showed that separation effect of collected soil from different land uses and different rates of perlite on total and net splash was significant at level of 99 percent and also the interaction effect of different rates of perlite and collected soil from land uses on total splash was significant at 99 percent. Also, the collected soil from land uses of rangeland and agriculture, perlite with amount of 25 percent had the maximum effect on controlling splash erosion. This amount caused the reducing total splash with rates of 55. 27 and 57. 48 percent, the net splash with rates of 55. 11 and 91. 03 percent, the up slope with rates of 62. 78 and 36. 85 percent and down slope splash with rates of 55. 23 and 66. 72 percent. The difference of perlite effect with used rates at collected soil from different land uses verified the use importance of appropriate from conditioners at the management of soil and water resources.