جستجوی مقالات مرتبط با کلیدواژه « support vector machine » در نشریات گروه « آب و خاک »

Soil properties play a crucial role as they determine the soil's suitability for different types of plant growth, ecosystems, and biota functioning. They have a significant impact on nutrient cycling, carbon sequestration, and soil management. Digital Soil Mapping (DSM) is a process aimed at delineating soil properties. Soil sampling for DSM serves as  a fundamental  step in improving prediction accuracy and is crucial for incorporating variability in terms of environmental covariates. Conditioned Latin Hypercube (CLH) sampling is a technique utilized to generate a sample of points from a multivariate distribution conditioned on one or more covariates. Numerous researchers (Ramirez-Lopez et al., 2014; Adhikari et al., 2017; Zhang et al., 2022) have endorsed this approach in their studies, following its inception by Minasny and McBratney in 2006. However, there has been limited research to date on the impact of the Latin hypercube method's random sample selection process on the accuracy of resulting maps. Hence, the central question remains: Is the Latin hypercube sampling method, which is currently widely adopted, always a dependable approach in this field?

The study area covers longitudes 50°35'47'' to 51°29'' east and latitudes 31°36''31'' to 32°15'48'' north in Borujen city, Chaharmahal, and Bakhtiari Province. The region, with an average elevation of 2338 meters above sea level, receives an annual rainfall of 250 millimeters and maintains an average temperature of 11.5 degrees centigrade. In this investigation, inherited data from soil studies were utilized, consisting of 250 samples distributed across the study area. In this research, the studied characteristics included percentage of equivalent calcium carbonate, clay, and soil organic carbon at a depth of 0 to 30 cm. Land component variables were extracted using the Alus Palsar digital elevation model with a spatial resolution of 12.5 meters. In the initial stage, digital maps of equivalent calcium carbonate, clay, and soil organic carbon were generated using the support vector machine method. The modeling process proceeded until a highly accurate model was achieved, with the root mean square error percentage (RMSE%) being less than 40. The Latin hypercube approach was utilized for sample design, with 500 repetitions in this study. After selecting sampling points for each run using the Latin hypercube method, these points were mapped onto a detailed map, and the corresponding feature values were retrieved. The final map was created based on the extracted points. Subsequently, the latin hypercube approach was employed to generate soil property maps for each selected dataset. Validation was conducted using criteria such as the coefficient of explanation, root mean square error, and root mean square error in multiple iterations to ensure the accuracy of the generated maps.

The results distinctly illustrates the varied selection of sampling positions with each implementation of the Latin hypercube method. It is important to note that there may be some overlaps in different implementations. Consequently, the primary question arises: Is a one-time execution of the Latin hypercube sufficient for selecting study points? The findings indicate that the support vector machine model achieves satisfactory accuracy for all the examined characteristics. In the studied area, the environmental factors such as slope and elevation were identified as a significant predictors for estimating percentage of equivalent calcium carbonate.

In the present study, the accuracy of the latin hypercube method was assessed for selecting sampling location for digital soil mapping endeavors in Chaharmahal and Bakhtiari Province. Given the impracticality of collecting numerous field samples to evaluate the soil sampling method, this research aimed to employ simulation methods based on highly accurate maps for this purpose. The results indicate that the different outputs of the Latin hypercube method influence the accuracy of modeling, although this effect is also influenced by the specific feature under investigation and the extent of its variability within the study area.  Considering that the Latin hypercube method is based on the principle that samples are randomly selected in each class of environmental parameters, it is suggested that future studies using this method should account for this principle. Adequate consideration should be given, and the selection of sampling locations should rely on multiple implementations of the Bhattacharya distance method to ensure robustness and reliability.

One of the ways to prevent creating negative pressure and cavitation in spillways is to introduce air into the flow over the spillways. Understanding the distribution of air concentration variations along the spillway is of significant importance for estimating the aeration level. This study explores the application of GPR and SVM molels in predicting air concentration. To achieve this, a dataset of 2268 laboratory experiments obtained from hydraulic models of chute spillways was utilized in the modeling process. Various input models were defined based on different combinations of measured parameters. The results demonstrate the high capability of both methods in estimating the required air concentration over the spillway. In predicting air concentration in the chute spillway under artificial aeration conditions, flow discharge (QW), longitudinal distance ratio from the end of the deflector to the channel width (L/W), and depth ratio (perpendicular to the spillway) to channel width (Y/W) significantly influenced the outcomes. Statistical indices, including R, DC, and RMSE for this case were 0.9214, 0.8451, and 1.008, respectively, in the GPR, and 0.9333, 0.8662, and 0.937 in the SVM. For scenarios without artificial aeration, the model with input parameters QW, L/W, Y/W, and ΔP (pressure difference between atmospheric pressure and the pressure under the jet) achieved the best performance in the GPR method with values of R=0.9222, DC=0.8644, and RMSE=0.914. In the SVM, the same model with values of 0.87, 0.7543, and 0.123 for R, DC, and RMSE, respectively, was selected as the superior model.

In order to control and minimize the damaging impacts of floods, flood modeling or simulation is a fundamental solution. Identifying effective models for this purpose is crucial in watershed management. This study evaluates the accuracy of support vector machine models combined with the support vector machine (SVM), Grasshopper algorithm (SVM-GOA) and least square support vector machine (LS-SVM) in simulating the flood peak discharge of Poldokhtar station in the Karkheh basin. For this study, 74 flood events from 2009 to 2016 at the Poldokhtar station and data from 13 daily rainfall stations in the upstream area for the same period were utilized. Subsequently, 52 events were allocated for training, and 22 for validation. The comparison of results was conducted using three statistical indicators: Correlation coefficient (R2), Root mean square error (RMSE), Nash efficiency (Ns), and Standard error (SE). Additionally, uncertainty analysis was performed using two indexes: ARIL and POC. The results indicate the relative superiority of the LS-SVM model with SE=0.407, RMSE=110.16, NS= 0.91 and R2=0.92 compared to the SVM model with SE=0.5, RMSE=137.70, NS= 0.87 and R2=0.88 and SVM-GOA model with SE=0.519, RMSE=144.53, NS= 0.83  and R2=0.9. The study's overall conclusion is that the LS-SVM model is more accurate, faster, and easier to implement compared to the SVM and SVM-GOA models. As a result, it can be confidently preferred over the SVM and SVM-GOA models due to its significant advantages. The research emphasizes the critical importance of precise flood modeling and simulation in watershed management for mitigating the destructive impact of floods.

Due to the location of Iran in arid and semi-arid regions and according to the quantitative and qualitative limitations of water resources, optimal management and volumetric delivery of water is important in irrigation and drainage networks. In this regard, it is necessary to estimate the water requirement of crops accurately and provide adequate water to farmers. Remote sensing technology provides facilities that can be used to obtain different layers of information at the lowest cost in the fastest time. Accordingly, many researchers have used remote sensing data to monitor vegetation cover, provide land use maps, estimate crop evapotranspiration and have declared this technology as appropriate tool for such studies. Based on the previous studies, it is observed that low researches has been conducted to investigate the crop evapotranspiration considering the crop water requirement. Therefore, the most important objectives of this study are: provide the cropping pattern and land use maps using Sentinel 2 satellite images, determination of the water requirement for the delivery points of irrigation network, determination of the actual evapotranspiration of the crop cover using SEBAL algorithm and Landsat 8’s images and finally evaluation of the water supply and management in the Mahabad irrigation and drainage network. In order to determine the cropping pattern of the Mahabad irrigation and drainage network, Sentinel 2 images have been used related to the 2018-2019 crop year. The images were examined in terms of the region of syudy and the percentage of cloudiness and after selecting the appropriate images, pre-processing operations including radiometric and atmospheric corrections were applied on them. Then, the NDVI index was calculated based on selected images. On the other hand, after determination of the classification classes, the phenological cycle of crops were examined for each class and spectral pattern of crops was determined during the growing season. Training samples were selected for supervised classification using the existing maps, Google Earth images, creating images with false color composites and considering the growth pattern and some of them were also considered for validation of the classified map. Then, the cropping pattern map was obtained by using the SVM classification algorithm. After generating the crop classification map, the water requirement of the different classes was determined based on the Penman-Montith evapotranspiration method, applying plant coefficients and irrigation application efficiency at the volumetric water delivery points. Finally, the actual evapotranspiration rate of the study area calculated based on the SEBAL algorithm and compared with the net water requirement map. Based on the results, kappa coefficient and overall accuracy of the classified map were determined to be 0.953 and 91%, respectively. The area of the planted agricultural farms was equal to 10594 hectares and 1576 hectares of farms were without planting. The area of orchard farms was equal to 6786 hectares and the area of sugar beet, wheat, alfalfa and corn lands were obtained to 998, 1839, 693 and 278 hectares, respectively. Thus, the net irrigation water requirement was equal to 71 million cubic meters and the gross irrigation water requirement was calculated equal to 161.36 million cubic meters, considering the irrigation efficiency of 44%. On the other hand, the evaluation of the SEBAL evapotranspiration maps during the growing season indicated that the total amount of evapotranspiration was equal to 79.78 million cubic meters, and this amount was 14% higher than the net irrigation water requirement. Finally, according to the crop classification map and based on the comparison of the net irrigation water requirement and evapotranspiration maps, the water consumption in the Mahabad irrigation and drainage network was evaluated. It turned out that in the upstream farms of the network or close to the Mahabad River, the Water consumption was more than net water requirement and downstream areas were faced to deficit irrigation due to lack of sufficient water.Finally, based on the results of this study, it was observed that by using the capabilities of satellite images and remote sensing, it is possible to monitor and evaluate the condition of agricultural farms on a large scale with acceptable accuracy. Also it is possible to improve the management of water supply and water use efficiency in irrigation and drainage networks by creating up-to-date land use maps, determining net and gross irrigation water requirment and comparing with actual evapotranspiration maps.

River flow forecasting has been one of the important challenges of water resources management in recent decades, so many researchers have proposed different methods to improve the performance of forecasting models. In the last decade, artificial intelligence methods have been most widely used in the simulation of various processes, including hydrological processes, due to their flexibility and high accuracy in modeling. However, the results of these methods have always been associated with uncertainty due to several factors such as structure, algorithm, input data, and the type of method chosen for data calibration. One of the methods that can somewhat solve this problem is the uncertainty analysis of the predictions made by these models.

In this study, the uncertainty of the results of artificial neural network (ANN) and support vector machine (SVM) models in predicting the monthly flow of the river has been evaluated. In this research, the time series of the monthly flow of the Ghezelozan River using the data of the Bianlu-Yasaul Stream gauging station in 39 years from 1976 to 2014 was used, where 75% and 25% of the data was used for training and testing the models, respectively. In these models, to estimate the monthly flow of the Ghezelozan River, six different input combinations including the flow of one, two, and three months before and the number of months of the flow were used. Then, the accuracy and performance of the models were compared using the coefficient of determination (R) and root mean square of errors (RMSE). Finally, the uncertainty of the results of ANN and SVM models in predicting the monthly flow of the river was evaluated by the Monte-Carlo method using d-factor and 95PPU values.

The evaluation of the performance of the ANN model shows that the best performance is related to the combination where the flow of the previous two months and the number of the month of the flow are the inputs of the model so that R and RMSE indexes were obtained as 0.757 and 9.45, respectively. In the SVM model for the monthly river flow series, the best performance is related to the combination where the flow of one, two, and three months ago and the number of months of the flow were the inputs of the model, and the R and RMSE indexes for this input pattern were 0.729 and 10.946, respectively. After studying the uncertainty of the models, the results showed that the ANN model has more uncertainty in the output values compared to the SVM model, and this is while the d-factor of the ANN model, both in the training and test phase, it was more than the SVM model. The comparison of the uncertainty analysis of the results of the ANN and SVM models showed that the SVM model with d-factor and 95PPU values equal to 0.155 and 17.241, respectively, compared to the ANN model with d-factor and 95PPU values equal to 0.993 and 85.470, respectively, has less uncertainty in the output values. So the number of observation data placed in the 95% confidence range (95PPU) of the ANN model compared to the SVM model has increased significantly in both the training and testing phases. Also, the results showed that both models have more uncertainty in the months with a large volume of water, which can be due to the complexity of the process and the involvement of uncertain factors in these months, as well as the effect of factors that are not considered in the structure of predictive models.

The results of ANN and SVM models in predicting the monthly flow of the Ghezelozan River showed that although the ANN model with R-value equal to 0.757 and RMSE value equal to 9.45 has a good performance compared to the SVM model with R-value equal to 0.729 and RMSE value equal to 10.946 in predicting the river flow, the results of this model are associated with high uncertainty. The comparison of the uncertainty analysis of the results of ANN and SVM models by Monte-Carlo method showed that the SVM model with d-factor and 95PPU values equal to 0.155 and 17.241, respectively, compared to the ANN model with d-factor and 95PPU values equal to 0.993 and 85.470, respectively, has less uncertainty in predicting the monthly flow of the Ghezelozan River and it is better than ANN model. According to the results of this research, taking into account the fact that advanced artificial intelligence models also have uncertainty, it is necessary to apply these methods in the fields of risk management and future planning to obtain the best performance.

A landslide is one of the mass movements on the top surface of the earth. Landslides have resulted in notable injury and damage to human life and destroyed infrastructure and property. Landslides represented approximately Nine percent of the natural disasters worldwide during the 1990s. According to studies, this trend is expected to continue due to increased human development. Many studies have been done to determine the factors affecting mass movement. In large part of Iran including the mountain areas, tectonic activity and seismic high with diverse geological and weather conditions led to many countries prone to landslide. Landslides cause wide damage to natural resources, human settlements, infrastructure, mud floods, and filling reservoirs. Landslides cause extensive property damage and occasionally result in loss of life. Besides, should not be ignored the social and environmental impacts resulting from the occurrence of this phenomenon, such as immigration and unemployment. One of the strategies for reducing losses due to a range of movements is the identification and management of unstable slope areas. To identify unstable regions pay to landslide hazard mapping. The main purpose of this research is to assess the effective parameter on landslide occurrence and to compare different machine learning models including SVM, GP regression, and RF for landslide susceptibility zoning.

The study area is a part of the Haraz Watershed, Mazandaran Province, Iran, occurrence many landslides are damaged after each heavy rain. So, it was selected as a suitable Watershed to evaluate the landslide susceptibility mapping (LSM). The vegetation covers and land mainly consists of rangeland. The geology of the study area consists mainly of Quaternary and Shemshak formations. The first step for the assessment of landslide susceptibility is gathering the necessary data and preparing information. These data were determined based on several factors. Considering the literature review, the local conditions, and previous studies. In this study, nine parameters such as slope angle, slope aspect, elevation, geology, land use, the distance of fault, the distance of the road, the distance of the river, and precipitation were identified as key factors for the prediction of landslide susceptibility. To assess the effectiveness of GP-PUK, GP-RBF, SVM-PUK, SVP-RBF, AND RF to estimate the landslide susceptibility map (LSM), data used in the present study were taken from field data. In this study, the dataset contains 148 observations of landslide occurrence and landslide non-occurrence points. The landslide data have been randomly separated into training (70% of landslides; 103) and testing (30% of the landslides; 45). To judge the performance of the soft computing techniques, statistical evaluation parameters were used. In this research, three statistical evaluation parameters were used. These parameters are the correlation coefficient (C.C.), root mean square error (RMSE), and Nash–Sutcliffe model efficiency (NSE).

According to the results of the comparison of methods, RF was the best model and the accuracy of the RF model was more suitable for the estimation of the landslide occurrence. So, in this study, RF was used for the landslide susceptibility map. Single-factor ANOVA test suggests that there is an insignificant difference between observed and predicted values of landslide occurrence and landslide non-occurrence using GP_PUK, GP_RBF, SVM_PUK, SVM_RBF and Random Forest approaches. According to the results of the comparison of methods, RF was the best model and the accuracy of the RF model was more suitable for the estimation of the landslide occurrence. The map of landslide susceptibility map was divided into five classes from none susceptible to very high susceptibility. According to the final Landslide susceptibility map, the area belonging to the “non-susceptible” class covers 35.86 km2, “low susceptibility” class 36.19 km2, “moderate susceptibility” class 15.06 km2, “high susceptibility” class 10.95 km2 and “very high susceptibility” class 14.46 km2 of Haraz Watershed. Sensitivity analysis was performed to find the most significant input parameter in the prediction of landslide occurrence and landslide non-occurrence. The result shows that aspect has a major role in predicting landslide occurrence and landslide non-occurrence in comparison to other input parameters, respectively.

Due to all results, some zones are potentially dangerous for any future habitation and development. Thus, there is an immediate need to implement mitigation measures in the very high-hazard and high-hazard zones, or such zones need to be avoided for habitation or any future developmental activities. The results of this research can be used by the local authority to manage properly, and systematically and plan development within their areas.

Rivers are always faced with erosion and sediment transport. Sediment transport in rivers is one of the most complex topics in river engineering and is always the focus of experts and water engineers. This phenomenon is one of the important hydrodynamic processes that affect many hydraulic systems and water facilities and is considered one of the basic problems in the exploiting surface water resources globally. Estimating the sediment load of rivers is one of the important and practical issues in the studies and design of water engineering projects, such as the design and development of irrigation and drainage networks, water extraction from rivers, etc. Sediment concentration can be calculated by direct or indirect methods, which are usually expensive and time-consuming direct methods. Various factors affect this phenomenon, which makes their analysis difficult. Therefore, they cannot model the sedimentation phenomenon with acceptable accuracy. Hydraulic models cannot always be trusted due to the need for a lot of data, unavailability of the required data, and the inaccuracy of the data due to human error for simulating sediments. Nowadays, fuzzy and neural intelligent conductor systems, due to their ability to solve complex and nonlinear phenomena, have found many applications in various water engineering problems, including sedimentation. The purpose of this research is to evaluate and compare adaptive neural fuzzy models (ANFIS), support vector machine (SVM), gene expression programming (GEP), and group model of data handling (GMDH) in estimating the sediment load of Tirah River, Markazi Province.

In this research, first, the long-term daily statistics of temperature, rainfall, average flow rate, and sediment concentration of Hasan Abad hydrometric and sediment measuring station located on the main branch of the Tirah River were collected. Then, the data sufficiency test for analysis, checking the correlation between parameters of river discharge, precipitation, temperature with sediment discharge, and determining the long-term average of suspended sediment in the studied stations were performed. In the next step, a suitable combination of input variables was selected. The design of the input parameter pattern can be based on the relationship between flow and sediment flow parameters, rainfall, temperature, flow, and sediment flow. Of course, considering that the mentioned parameters have a historical course, therefore, the design of the input patterns of soft computing models should be done based on time delays (like what is discussed in the analysis and forecasting of time series). Determining the most appropriate time delay of the input parameters in the modeling of discharge, sediment, temperature, and rainfall, then the appropriate design of the structure of the used soft calculation models was done. In the next step, the estimation of sediment discharge using an SVM, GEP, and ANFIS group method of GMDH data control and comparison of three data mining methods, and also with the sediment rating curve and observational data. About 70 % of the research data was used as training and between 20 to 30 % for validation and testing.

Based on the statistical indicators of optimal model selection, the best performance of the SVR model has been obtained for model number one. In this model, the R2 and RMSE obtained from the model are 0.96 and 0.0047, respectively. Besides, the R2 and the RMSE error of the models in predicting suspended sediment values in the test stage are 0.95 and 0.014, respectively for the ANFIS model, and 0.50 and 4.97, respectively for the GEP model. The best performance of the ANFIS model has been obtained for model number one. In this model, the R2 and the RMSE obtained from the model are 0.95 and 0.014. The R2 and RMSE of the models in predicting suspended sediment values in the test stage are 0.96, 0.0047 for the SVR model, and 0.50, 4.97 for the GEP model, respectively. The best performance of the GEP model has been obtained for pattern number nine. In this model, the R2 and RMSE obtained from the model are 0.99 and 0.010, respectively. The R2 and the RMSE of the models in predicting the amount of suspended sediment in the test stage are respectively equal to 0.70, 0.015 for the ANFIS model and 0.78, 0.0185 tons respectively for the SVR model.

It can be seen that the performance of the GEP model was better compared to other models. SVR and ANFIS models are ranked second and third. In the next step, the best-selected pattern of ANFIS, SVM, and GEP models was used as the input of the GMDH model. First, input pattern one, which was selected as the best pattern for ANFIS and SVM models, was introduced as the input of the GMDH model. In the training and test, the values of R2 statistical indices are 0.94 and 0.99, respectively, the RMSE error value is 0.0079 and 0.0038, respectively, the MSE value is 0.000062 and 0.000015, respectively, and the MAPE values are respectively 0.007 and 0.003. In the next step, input pattern nine, which was selected as the best pattern for the GEP model, is introduced as GMDH input. In the training and test steps, the value of R2 is equal to 0.95 and 0.98 respectively, the RMSE error value is equal to 0.0077 and 0.0045 respectively, and the MSE value is equal to 0.0006 and 0.00002 respectively, and MAPE value is equal to 363 and 502. The results showed the acceptable performance of the GMDH model with the highest R2 equal to 0.99 and 0.98 and the lowest RMSE equal to 0.0038 and 0.0045, respectively.

The importance of potassium in agricultural products has increased the demand for potassium fertilizers. Potassium grade in aquifers ensures its extraction. The purpose of this research is to use RF and SVM algorithms in order to prioritize the effective parameters on the potassium grade of saline water groundwater in playa Khoor and Biabank in Isfahan province. For this purpose, 55 parameters were measured in 12 drilling holes.The parameters measured as independent variables include the percentage of saturated moisture, the apparent specific gravity and the porosity of the core at 15 different depths, the area  polygon, the depth of the underground water, the depth of the salt layer, the potassium of the surface layer, the density of the brine and the amount of Elements of calcium, magnesium, sodium, chlorine and grade potassium were included in the model as dependent variables. In the RF model, the (PFI) and (RFE) were used for prioritization. In the different kernels of the SVM algorithm, in order to prevent the collinearity of the independent parameters, all the combinations of the independent variables, considering the variance inflation factor less than 8 and the highest coefficient of determination and the lowest MSE error, were examined and selected as the best combination. The effective parameters in predicting the grade potassium of the brine in the RF algorithm and the linear function of the SVM algorithm are sp, ap, duw, slp, SAR and n, sp, duw, and SAR respectively, which led to the best results. The coefficient of determination for both models is 0.99 and 0.97, respectively, which indicates the good accuracy of both algorithms.

Water plays a crucial role in ensuring the sustainable development of any region. Given that our country consists primarily of arid and semi-arid regions, where the majority of rivers are also found, along with the critical state of groundwater extraction and the growing importance of surface water, It is crucial to have a deep understanding of the future condition of water resources within the country's watersheds (Fathollahi et al., 2015). By utilizing intelligent models, it becomes feasible to represent the inherent relationships between data that cannot be solved by conventional mathematical methods. Support vector machine (SVM) and Random Forest algorithms are two types of machine learning methods that utilize essential algorithms for making repeated and accurate predictions (Kisi & Parmarm, 2016). The most recent study conducted by Zarei et al. (2022) evaluated the risk of flooding using data mining models of SVM and RF (case study: Frizi watershed). By analyzing the results, it was found that both the SVM algorithm and the new random forest algorithm showed higher accuracy in predicting flooding risks, both in terms of the educational data and algorithmic performance. The purpose of this study is to simulate the precipitation-runoff process in the hydrometric stations at the end of the Maragheh plain (Khormazard station on the Mahpari chai river and Bonab station on the Sufichai river) in East Azerbaijan province using support vector machine and random forest modeling algorithms. This study has been conducted over a period of 43 years, making it one of the few research cases in this area.

The Maragheh Sufi chai basin is situated in the eastern region of Lake Urmia, within the East Azarbaijan province. It covers an area of 611.89 square kilometers and is located between longitudes 45° and 40´ to 46° and 25´and latitudes from 37° and 15´ to 37° and 55´ north. The average height of the basin is 1767 meters above sea level (Sharmod et al., 2015). Based on the substantial changes observed in the runoff trend in the data since 1994 (without any noticeable change in the precipitation trend), the available data was divided into two distinct periods. The first period spans from 1976 to 1994, and the second period covers the years 1995 to 2019. To simulate rainfall-runoff, first the average rainfall of Maragheh plain was calculated by polygonal method. Subsequently, this data was combined with the discharge output from Bonab and Khormazard stations, with a one-day time lag. These inputs were then utilized in two models, SVM (kernel function) and RF. For this purpose, 70% of the data was used for the training stage and 30% of the data was used for the validation stage. Then, the rainfall and runoff training sets from one day before were chosen as the predictor variables, while the runoff training set was designated as the target variable. Several combinations of runoff and rainfall inputs were evaluated for the purpose of modeling. The inputs consist of the monthly Q and P values that were recorded previously (Pt, Qt-1), while the output represents the current runoff data (Qt), with the subscript t indicating the time step. As a result, two input combinations were constructed from Q and P data (as seen in Table 3) and SVM and RF models were used for rainfall-runoff modeling to determine the optimal input combination.
Calculating average rainfall through the Thiessen Polygons method Thiessen polygons, which are Voronoi cells, are used to define rainfall polygons that correspond to the surface area (Ai). These polygons are used to weight the rainfall measured by each rain gauge (ri). Consequently, the area-weighted rainfall is equivalent to:
(1)
Random Forest Algorithm
Random forest is a modern type of tree-based methods that includes a multitude of classification and regression trees. This algorithm is one of the most widely used machine learning algorithms due to its simplicity and usability for both classification and regression tasks.
Support Vector Machine (SVM) algorithm
Support vector machines works like other artificial intelligence methods based on data mining algorithm. The most important functions of the support vector machine model are classification and linearization or data regression.
       Evaluation Criteria
To evaluate the models and compare their effectiveness, this research employs metrics such as the root mean square error (RMSE), correlation coefficient (r), explanation coefficient (R2) and Nash-Sutcliffe efficiency coefficient (NS) are used. Below are the relationships among these criteria:
(2)
(3)                                                     
(4)
(5)

 Figure 6 displays the time series data for rainfall and runoff during the two study periods, before and after 1994.The analysis of the figures showed that for Bonab station, during the two study periods, the value of Kendall's statistic for precipitation variable was 0.044 and 0.028, respectively. For Khormazard station, this statistic value for the first and second period was 0.030, and 0.028, respectively. However, these values are not significant at the 95% level. This indicates that the annual rainfall for the two studied stations during these years is not statistically significant. Therefore, it is concluded that the annual rainfall in these stations between the years 1976 to 2019 did not show any significant trend. The variations observed during this period were deemed normal, suggesting that the time series of rainfall displayed fluctuating patterns. However, it should be noted that there were instances of both increasing and decreasing trends in certain years Examining the time series reveals varying trends Initially, the outflow from Bonab station (both a and b) displayed fluctuating patterns, followed by periods of both decreasing and increasing trends. However, in recent years, there has an increase in outflow from this station. The Mann-Kendall test statistic for the two study periods for this station is 0.325 and 0.512, respectively. These values are significantly different at the 95% level, indicating that the increasing trend of discharge for both time periods was statistically significant. The reason for this trend at the Bonab station, compared to other entrance stations to Lake Urmia, is the lower demand for water in the Sofichai basin for agricultural and industrial purposes, in contrast to other rivers. To explore the root cause of this issue, studies should be conducted to examine both underground and surface water sources, as well as the utilization of water in the agricultural and industrial sectors of this region. On the contrary, the trend observed at Khormazard station (c and d) is different. Unlike Bonab station, the discharge from Khormazard station exhibited a complete downward trend. The Mann-Kendall test statistic for the discharge variable during our two research periods were -0.269 and -0.412, respectively. At the 95% level, the decreasing trend of discharge in this station was found to be significant. On the other hand, it is apparent that the volume of discharge in this hydrometric station has decreased drastically since 1976 (d). Apart from 2007, when there was a sudden increase in discharge volume, the water inflow into lake Urmia has remained at its lowest level throughout the years. To analyze the Bonab and Khormazard stations during two distinct periods, rainfall and runoff statistics (average, minimum, maximum) for the first period (1976-1994) and the second period (1995-2019) are presented in Tables 4 and 5. Based on the data presented in both tables, the Bonab station displays the highest average rainfall and runoff values in the total data column, while the Khormazard station has the lowest average rainfall and runoff values.
As mentioned, in order to model rainfall-runoff data using SVM and RF models, a portion of the data was used for training purposes, while another portion was used for validation. Tables 5 and 6 present the values of the calculated statistical indicators associated with the results obtained from the training and validation sections for both SVM and RF models. According to the results of Tables 6 and 7, it is clear that in both study periods, the SVM model outperformed the RF model at the Bonab station. The SVM model demonstrated superior accuracy in simulating both flow rate and monthly rainfall. Conversely, at the Kharmazard station during these periods, the RF model displayed better performance compared to the SVM model. The modeling results in the test set for both stations revealed that the mutual correlation values for the first and second study periods at the Bonab station were 0.85 and 0.84, respectively. For the Kharmazard station, these values were 0.79 and 0.75, respectively.

The results indicate that for both periods at the Bonab station, the SVM model exhibited higher efficiency compared to the RF model. Conversely, at the Khormazard station, the RF model outperformed the SVM model for both periods. Mutual correlation values for the test sets were 0.85 and 0.84 for the first and second study periods at the Bonab station, respectively, for the SVM model test set. For the Khormazard station, these values were 0.79 and 0.75, respectively, for the RF model test set. Other notable findings of this research include the analysis of the time series data for rainfall and runoff over 43 years. Graphs obtained for both stations, along with the Mann-Kendall statistic for precipitation and flow parameters, revealed no discernible trend in precipitation during the two study periods. Instead, precipitation in these areas displayed fluctuating patterns However, the analysis of the time series and statistical values for the discharge of Sofichai and Mahpari chai rivers at the Bonab and Khormazard stations showed different results. In the Bonab station, the discharge exhibited fluctuations, with an increase observed in the second period. Conversely, at the Khormazard station, the discharge trend was downward in both study periods. The volume of Mahpari chai River outflow notably decreased in recent years, as evidenced by the Mann-Kendall statistic showing a decreasing trend.

Predicting groundwater potential is crucial for systematic development and planning of water resources. The main objective of this study is to develop machine learning models including Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM) for predicting potential groundwater areas in the Birjand plain. Therefore, for the implementation of this study, geohydrological data related to 37 groundwater wells (including the number and location of wells and groundwater levels) and 17 hydrological, topographical, geological, and environmental criteria were used. Feature selection was performed using Support Vector Machine's least squares method to determine effective criteria for improving the performance of machine learning algorithms. Ultimately, predictive maps of groundwater potential were prepared using DT, RF, and SVM models, and the performance of these models was evaluated using the Area under the Curve (AUC) and other statistical indicators. The results showed that the DT model (AUC=0.89) has very high predictive capability for groundwater potential in the study area, and elevation was identified as the most important factor in predicting groundwater potential in this area. The findings of this study can serve as a guide for decision-making and appropriate planning in the optimal use of groundwater resources.

Estimating crop evapotranspiration (ETc) in arid and semi-arid areas can be difficult due to the dynamic nature of this process across both time and space. In addition, obtaining on-site measurements for this variable can be very time-consuming and costly. This study aimed to develop a framework that accurately estimates the sugarcane crop evapotranspiration on a spatio-temporal scale. This was achieved using four machine learning (ML) algorithms (MLR, CART, SVR, and GBRT) combined with remote sensing (RS) data and meteorological variables. Also, to reduce the dependence on several meteorological parameters in conventional ETc equations, the performance of eight different experimental temperature-based methods and four modified Hargreaves & Samani equations was evaluated compared to the standard FAO-Penman-Monteith method. For this purpose, weather data were collected from Hakim Farabi Sugarcane Agro-Industrial meteorological station for three years (2018-2021). Nine combinations of input variables (RS data and meteorological variables) were designed based on the IGR method and then evaluated by the ML algorithms. The results showed that the highest accuracy of ML algorithms based on R2, RMSE, and MAE statistics was obtained in CART (0.99, 0.41, and 0.18) and GBRT algorithms (0.99, 0.65, and 0.26), respectively. Regarding temperature-based methods, Ivanov’s equation had the best performance with an R2 of 0.91, while Baier and Robertson’s equation had the weakest performance with an R2 of 0.78 when estimating ETc. Overall, the combination of RS and ML algorithms effectively produced more precise and reliable ETc values on both temporal and spatial scales.

Non-linear weirs meanwhile economic advantages, have more passing flow capacity than linear weirs. These weirs have higher discharge efficiency with less free height upstream compared to linear weirs by increasing the length of the crown at a certain width. Intelligent algorithms have found a valuable place among researchers due to their great ability to discover complex and hidden relationships between effective independent parameters and dependent parameters, as well as saving money and time. In this research, the performance of support vector machine (SVM) and gene expression programming algorithm (GEP) in predicting the discharge coefficient of arched non-linear weirs was investigated using 243 laboratory data series for the first scenario and 247 laboratory data series for the second scenario. The geometric and hydraulic parameters were used in this research including the water load (HT), weir height (P), total water load ratio (HT/p), arc cycle angle (Ɵ), cycle wall angle (α), and discharge coefficient (Cd). The results of artificial intelligence showed that the combination of parameters (Cd, H_T/p, α, Ɵ) respectively in GEP and SVM algorithms in the training phase related to the first scenario (Labyrinth weir with cycle wall angle 6 degrees) were respectively equal to (R2=0.9811), (RMSE=0.02120), (DC=0.9807), and (R2=0.9896), (RMSE=0.0189), (DC=0.9871) in the second scenario (Labyrinth weir with a cycle wall angle of 12 degrees) it was equal to (R2=0.9770), (RMSE=0.0193), (RMSE=0.9768), and (R2 = 0.9908), (RMSE = 0.0128), (DC = 0.9905), which compared to other combinations has led to the most optimal output that shows the very favorable accuracy of both algorithms in predicting the coefficient the Weir discharge is arched non-linear. The results of the sensitivity analysis indicated that the effective parameter in determining the discharge coefficient of the arched non-linear Weir in GEP and in SVM is the total water load ratio parameter (HT/p). Comparing the results of this research with other researchers revealed that the evaluation indices for GEP and SVM algorithms of this research had better estimates than other researchers.

The effective use of water for irrigation requires that flow discharge and flow volume be measured carefully. Venturi flumes are widely-used structures for monitoring flow discharges in canal networks (Venturi tubes used in pipelines). Venturi was the first that observed the effect of a local contraction in a conduit on flow velocity distribution. The Venturi flumes have a local constriction. These devices may be built in different shapes and generally are very accurate when operated under free outflow conditions. Longitudinal section of the Venturi flumes has a constant bottom slope, or the bottom has a local sill or hump. The Venturi flume with an arc-shaped inlet is referred to as Khafagi flume. Montana flume is also a flume without diverging downstream wall. The polygonal-shaped flumes are simpler in construction than curve-shaped flumes and are less expensive due to plan shaped elements. The Parshall flume is characterized by a specific shape with variousdegrees of convergence and divergence. Since development of the Parshall flume in 1926, many studies have been made to simplify, reduce construction costs, increase performance and accuracy of the flumes. A review of the literature of the subject shows that the study of hydraulics in flow measurement flumes is mainly based on laboratory research, and although numerical modeling is of interest, due to the complexity of the geometry of the section and the Contraction of the triangular shape, their accuracy is not reported to be acceptable. On the other hand, researchers have tried to develop and use soft computing models to estimate flow characteristics in such sections due to the hydraulic complexity of these types of flumes, which according to published reports, their accuracy has been suitable in all types of sections. Therefore, in this research, the development of data group classification model, support vector machine (SVM) model and random forest algorithm were developed to estimate the Discharge in flumes with triangular contraction.

By investigating the hydraulics of flow in flumes, researchers have found that the Discharge depends on the width of the contraction at the location of the structure, the horizontal and vertical slopes of the triangular walls, and the relative depth of the flow. Therefore, in the present study, for the development of GMDH, SVM and RF models, five dimensionless input parameters were considered. GMDH algorithm has been widely used in solving various hydraulic engineering problems. One of the most important applications of this method is the estimation of erosion around the bridge base, downstream of the cup-shaped launcher, and the discharge coefficient of flow measurement structures such as overflows. The SVM model is divided into two main groups a) Support Vector Classification model and b) Support Vector Regression model or SVR for short. The support vector machine classification model is used to solve data classification problems that are placed in different classes, and the support vector machine regression model is used to solve forecasting problems.

First, the collected data are divided into two categories, training and testing. It should be noted that the number of collected data is 592, and in this research, 80% of the data was assigned to training and the remaining 20% to testing. The training data is used for calibration and the test data is used for validation. Due to the fact that the collected data do not have a time series nature, they were randomly assigned to each of the training and testing groups. First, the results of the random forest model are presented. The reason for the priority of presenting the results of the random forest model compared to other modes used in this research is the identification of the most important effective parameters in the development process of the random forest model in the modeling and estimation of Discharge.

First, the collected data are divided into two categories, training and testing. It should be noted that the number of collected data is 592, and in this research, 80% of the data was assigned to training and the remaining 20% to testing. The training data is used for calibration and the test data is used for validation. Due to the fact that the collected data do not have a time series nature, they were randomly assigned to each of the training and testing groups. First, the results of the random forest model are presented. The reason for the priority of presenting the results of the random forest model compared to other modes used in this research is the identification of the most important effective parameters in the development process of the random forest model in the modeling and estimation of Discharge.

Land-use changes especially agricultural lands have a significant impact on  the microclimate of a region,natural resrource managrment and land-atmoshptre interactions .Remote sensing is a reliable and precise techniques in generating land-use maps. The aim of this study, is producing to a land use map by and detection of land cover pattern changes including urban,industrial agricultural and fallow land in Zarand region, Kerman province,south of Iran, during 1987 to 2020. In order to classify land use in four above mentioned types, three methods of maximum likelihood, artificial neural network, and support vector machine were used. The support vector machine was found to be the best performing method. In general, the generated land-use maps in the studied years showed an increase of 64,17 and 2 hectares in the agricultural, urban and industrial land uses, respectively. The observed increase in industrial and agricultural lands are quite important in possible changes of cropping pattern and agroclimatic condtion of the region and needs further investigatin in long term environmental management planing.

It is common to use different data mining methods in drought prediction. However, the selection of the best model is mainly based on the accuracy of the simulation, while most of the studies do not mention the features of the models. In this paper, the performance of the most common data mining models, including Multilayer Perceptron Artificial Neural Network (ANN-MLP), Radial Base Function Neural Network (ANN-RBF), Regression Decision Tree (CART), Model Tree (M5P), and Support Vector Machine (SVM) is evaluated in order to predict monthly one year ahead rainfall at Bandar Abbas synoptic station and then the characteristics of each of them are described. Calibration and validation of the models were done using raw data and a three-year moving average of climatic parameters from 1347 to 1396. The performance of the models has been evaluated using different statistical indices and comparative diagrams. The results showed that the SVM and M5P models have good prediction performance with RMSE of 7.93 and 8.31 mm, the MAE of 3.66 and 4.69 mm, and the CC of 0.83 and 0.82, respectively. Also, with the exception of the CART, the change in the data mining tool makes an eight to 11 percent difference in the accuracy of the estimates. Therefore, the most appropriate model should be selected based on other characteristics of the methods besides their accuracy. In addition, using the three-year moving average of the input parameters has increased the correlation coefficient by about 78 percent and reduced the RMSE by about 63 percent. The analysis of the long-term drought situation showed that with the increase in the period of the standard precipitation index, the separation of wet and dry years becomes more specific.

 In order to simulate the yield and water productivity of cucumber plant (Cucumis sativus L.), an experiment was conducted in the form of a completely randomized block design with three irrigation levels of 100, 85 and 75% of the water requirement in two growing seasons during 2017 and 2018 and using perceptron neural networks (MLP) and support vector machine (SVM) methods were used and finally, to select the appropriate and optimal model, the indices of explanatory coefficient, mean squared error and normalized mean squared error were used. The amount of irrigation water, number of leaves on the plant, temperature, evaporation rate and relative humidity were selected as input data and 60%, 20% and 20% of the total data were allocated for training, validation and testing of the model, respectively. The results showed that the MLP neural network with the inputs of irrigation water and number of leaves was more accurate in simulating fruit yield and water productivity in cucumber plants with an explanation coefficient of 0.92 and 0.86, respectively. The results of the sensitivity analysis indicated that the irrigation water input parameters are the most important effective parameters on the water consumption efficiency model and cucumber fruit yield with sensitivity coefficients of 0.9 and 0.86, respectively.

The gradual increase in the world’s population requires continues increase in agricultural production. Climate change is one of the challenges of our society and frequent droughts affect large areas of the world, which requires more accurate management of water resources, both globally and in local catchments. Accurate estimation of components of the hydrological cycle is essential for proper irrigation scheduling. Most of the precipitation received by the earth is returned to the earth’s atmosphere by the process of evapotranspiration. On the other hand, because every process that takes place in the plant is dependent on water and one of the most common uses of water in the plant is evapotranspiration, so reducing amount of the water will have adverse effects on photosynthesis, crop production, product quality, etc. The complex and nonlinear relationship between the factors affecting the process of evapotranspiration, has caused researchers today to use new methods to accurately identify and predict this parameter. Reference evapotranspiration is a concept that uses the crop coefficient to obtain the actual water requirement. According to the FAO proposal, the FAO- Penman- Monteith equation was introduced as a benchmark method for calculating reference evapotranspiration values when measurements of this parameter are not available and there is no access to lysimetric data. One of the major advantages of this model is its physical basis and global validity, but this equation needs a large number of meteorological parameters that are often not available, instead empirical equations with low meteorological variables or modern methods such as artificial intelligence and machine learning methods can be used.

In this study, meteorological data related to two stations of Astara located in the humid region and Sirjan located in the arid region of Iran in the period of 2000-2020 were studied to predict the crop evapotranspiration values. As mentioned, the FAO- Penman- Monteith method has used as a standard method for calibration and evaluation of the other functional equations and machine learning methods. In this study, four types of empirical equations including Hargreaves –Samani, Makkink, Turk and Dalton were evaluated against the FAO- Penman- Monteith model. Also, modelling was performed using Support Vector Regression, Random forest and M5P Tree model. In this study, 70% of data were considered for training and 30% for testing. Finally, statistical parameters including root mean squared error (RMSE), correlation coefficient (R), scatter index (SI), Nash-Sutcliffe coefficient (NS) and Wilmot index (WI) were used to determine the performance of each mentioned methods in estimating reference evapotranspiration values.

Using different meteorological parameters in accurate prediction of evapotranspiration using 4 combined scenarios, calibration calculations were performed on 70% of data and validation calculations were performed on 30% of testing data implementing Weka software. The obtained results showed that the SVR3 and M5P3 models in Astara station with all meteorological parameters and having R= 0.993, RMSE= 0.201 and also, the SVR3 model in Sirjan station with R= 0.982, RMSE= 0.410 compared to the studied empirical methods provided better results in estimating the reference evapotranspiration and scenario 3 with all meteorological parameters was introduced as the top scenario. Among the empirical methods, Hargreaves- Samani was superior to some models only in Astara station. At Sirjan station, none of the empirical models performed better than the machine methods.

Accurate estimation of reference evapotranspiration in water resource management is essential. In this study, meteorological data from Astara and Sirjan stations were used to evaluate the ability of machine learning methods including SVR, RF and M5P to estimate the values of reference evapotranspiration and compared the results with empirical methods. The results showed that the high accuracy of the SVR3 model in both stations and in the next position M5P3 model for humid area. Empirical methods except Hargreaves- Samani had poor performance compared to data- driven models. Finally, the use of SVR and M5P methods in irrigation scheduling is recommended.

Introduction:

Reference evapotranspiration (ET0), a complex hydrological variable affecting crop water requirements and irrigation scheduling, is defined by a number of climatic factors that have an impact on water and energy balances. On the basis of accurate climatic data, conventional methods for calculating ET0 include a variety of empirical approaches. But there are a lots of locations where different climatic information might not be available for ET0 estimation.

The objective of this study is to evaluate different data mining methods to estimate ET0 with limited meteorological data. This study aims to answer the question: can reference evapotranspiration be estimated without reducing accuracy, regardless of the availability of all variables? In this research, the accuracy of data mining methods in estimating ET0 with respect to the plant water demand system (FAO Penman-Monteith standard method) was evaluated

 Data such as sunshine hour, air temperature, wind speed, and relative humidity from thirteen climatology stations in the Zanjan province over a ten-year period (2010-2021) were collected. The ET0 was calculated using the FAO56 Penman-Mantith method on a daily time scale (as refrence method) and the estimated values obtained by data mining methods (Artificial Neural Network (ANNs), Random Forest (RF) and Support Vector Machine (SVM)) were evaluated. The data from each station were divided into two sets: training (two-thirds of the data) and testing (one-third of the data) in order to calibrate and validate the proposed methods. Finally, based on NRMSE, RMSE, MBE, and EF criteria, the generalizability of the aforementioned methods for estimating ET0 was examined.

 According to the results, ANNs performed better than SVM and RF methods. The mean values of, RMSE, EF and NRMSE criteria for the ANNs method in the training and testing steps were 0.49, 0.94 and 0.14, respectively. The mean values of these criteria for RF method in the training step were 0.49, 0.94 and 0.14 and in the testing step was 0.52, 0.94 and 0.15, respectively. The mean values of these criteria for the SVM method for both (training and testing) steps were 0.52, 0.94 and 0.15, respectively.The average air temperature is the most significant and effective parameter to estimate ET0, according to more than 92 percent (12 stations) of the results obtained from two ANNs and RF methods. The sunshine hours is the second-most crucial and useful input in estimating ET0, according to more than 84 percent (11 stations) of the results. As a result, using four meteorological variables such as average air temperature, average relative humidity, wind speed, and sunshine hours as input, excellent performance can be achieved. The NRMSE values obtained from ET0 estimation did not exhibit regular variations with the average values of parameters (temperature, humidity, wind speed, sunshine hours, slope percentage).

It was found that the average air temperature was the most crucial and useful parameter as a result of the sensitivity analysis of the ANNs method and the Predictor Importance of the RF method. According to the current study, Pari and Zanjan stations outperformed than the other stations in Zanjan province, probably due to their plainer conditions. The results of the current study will help to estimate ET0 for semi-arid climates where ET0 is critical for agricultural water resource management.

In the present study, the flow rate in flues containing lateral semi-cylinders (SMBF) was simulated and estimated under free and submerged conditions using back vector machine models (SVM), spin multivariate adaptive regression (MARS), and multilayer artificial neural network (MLPNN) model. In free flow mode, the dimensionless parameters extracted from the dimensional analysis include the ratio of upstream flow to throat width and contraction ratio (throat width to channel width), and in the submerged state, in addition to these two parameters, the depth-to-throat width, and bottom-depth parameters upstream depth were used as input and the two-dimensional form of flow rate was used as the output of the models. The results showed that in free flow mode in the validation stage, the MARS model with statistical indices of R2 = 0.985, RMSE = 0.008, MAPE = 0.87%, and the SVM model with statistical indices of  R2 = 0.971, RMSE = 0.0012, MAPE =1.376%, and MLPNN model with statistical indices of R2 = 0.973,  RMSE = 0.011, MAPE = 1.304% have modeled and predicted the flow rate. In the submerged state, the statistical indices of the developed MARS model were R2 = 0.978, RMSE = 0.018, MAPE = 3.6%, and the statistical indices of the SVM model were R2 = 0.988, RMSE = 0.014, 2%. MAPE = 4, and the statistical indicators of the MLPNN model were R2 = 0.966, RMSE = 0.022, and MAPE = 5.7%. In the development of SVM and MLPNN models, radial kernel and hyperbolic tangent functions were used, respectively.

Estimating the sediment load of rivers is one of the important and practical issues in the studies and design of water engineering projects, such as the design and development of irrigation and drainage networks, water extraction from rivers, etc. Sediment concentration can be calculated by direct or indirect methods, which are usually expensive and time-consuming direct methods. Various factors affect this phenomenon, which makes their analysis difficult. Statistical and regression models are the most common methods of analysis, which often provide erroneous results due to the linear solution of these phenomena. Therefore, they cannot model the sedimentation phenomenon with acceptable accuracy. Hydraulic models cannot always be trusted due to the need for a lot of data and sometimes the unavailability of the required data and the inaccuracy of the data due to human error for simulating sediments. Nowadays, intelligent fuzzy and neural conductor systems, due to their ability to solve complex and nonlinear phenomena, have found many applications in various water engineering problems, including sedimentation. The purpose of this research is to evaluate and compare adaptive neural fuzzy models (ANFIS), machine Support vector (SVM) and GEP gene expression programming in estimating the sediment load of selected rivers in Central Province. For this purpose, the performance of three types of support vector machine (SVM), adaptive neural system (ANFIS) and GEP gene expression programming in the simulation of sediment load of rivers was studied.

In this research, first, the long-term daily statistics of temperature, rainfall, average flow rate and sediment concentration of Hasan Abad hydrometric and sediment measuring station located on the main branch of the Tirah River were collected. Then, data sufficiency test for analysis, checking the correlation between parameters of river discharge, precipitation, temperature with sediment discharge, and determining the long-term average of suspended sediment in the studied stations were performed. In the next step, a suitable combination of input variables was selected. The design of input parameter pattern can be based on the relationship between flow and sediment flow parameters, rainfall, temperature, flow flow and sediment flow. Determining the most appropriate time delay of input parameters in flow and sediment modeling. Estimation of sediment discharge using support vector machine (Svm), gene expression programming (GEP) and fuzzy-adaptive neural system (Anfis), comparing three data mining methods with each other as well as with gauge curve and observational data. The appropriate design of the structure of soft calculation models is used, in this research the number of data required for training (usually more than 70 percent), research data as training and also determining the required data (usually between 20 and 30 percent) is used for validation and testing.

In this research, The best performance of the GEP model has been obtained for pattern number 13. In this model, the R2 explanatory coefficient and the RMSE error obtained from the model are 0.97 and 0.033, respectively. The coefficient of explanation R2 and the RMSE error of the models in predicting suspended sediment values in the test phase were obtained as 0.53, 3.18 for the ANFIS model, and 0.70, 15.16 for the SVR model, respectively. Comparing the results of ANFIS and GEP models with the SVR model indicates the superiority of the GEP model in predicting the amount of suspended sediment according to Verdi model number 13. According to the obtained results, it can be seen that the performance of GEP model was better compared to other models. SVR and ANFIS models are ranked second and third. According to the obtained results, it can be said that the GEP model as a powerful and high-speed model can be used to model the suspended sediment in the Qomroud catchment area of Bagherabad station.

The results show the acceptable performance of the models compared to the gauge curve. Also, the results showed the superiority of the GEP model with the highest coefficient of determination R2 with a value of 0.99 and the lowest root mean square error RMSE in terms of tons per day with a value of 0.010. In this regard, the efficiency of the SVR model was somewhat better than the ANFIS model. The obtained results showed that all three investigated data mining methods provide far better results than the sediment gauge curve.