Showing 64 results for Regression
M. Erfanian, H. Farajollahi, M. Souri, A. Shirzadi,
Volume 20, Issue 75 (5-2016)
Abstract
The aim of this study is to prepare the groundwater spring potential map using Weight of Evidence, logistic regression, and frequency ratio methods and comparing their efficiency in Chehlgazi watershed, province of Kurdistan. At first, 17 effective factors in springs occurrence including geology, distance to fault, fault density, elevation, relative permeability of lithological units, slope steepness, slope aspect, plan curvature, profile curvature, precipitation, distance to Stream, drainage Stream density, Sediment Transport Capacity Index (STCI), Stream Power Index, topographic wetness index (TWI) and land use/land cover (LU/LC) were selected. The validation processes of methods were conducted by relative performance characteristic curve (ROC). The area under an ROC curve (AUC) for the weight of evidence, logistic regression and frequency ratio was 85/8%, 79% and 89%, respectively. The results showed that all methods are suitable estimator for mapping the groundwater spring potential in the study area. But the frequency ratio method with the most amounts is the best method to produce and map the groundwater spring potential. Also, validation of the mappings based on the percentage of pilot springs, training springs and all springs showed that the logistic regression, WoE and frequency ratio, with 45, 56 and 45 percent of spring occurrence on the high potential classes respectively, had the highest validation.
F. Abbaszadeh Afshar, ِ S. Ayoubi, A. Jafari,
Volume 21, Issue 1 (6-2017)
Abstract
Mapping the spatial distribution of soil taxonomic classes is important for useful and effective use of soil and management decisions. Digital soil mapping (DSM) may have advantages over conventional soil mapping approaches as it may better capture observed spatial variability and reduce the need to aggregate soil types. A key component of any DSM activity is the method used to define the relationship between soil observations and environmental covariates. This study aims to compare multiple logistic regression models and covariate sets for predicting soil taxonomic classes in Bam district, Kerman province. The environmental covariates derived from digital elevation models, Landsat imagery, geomorphology map and soil unit map that were divided into two different sets: (1) variables derived from digital elevation models, remote sensing and geomorphology map, (2) variables derived from digital elevation model, remote sensing, geomorphology map and the soil map. Stratified sampling schemes were defined in 100000 hectares, and 126 soil profiles were excavated and described. The results of accuracy model showed that data set 2 increased accuracy of model including overall accuracy, kappa index, user accuracy and reliability of the producer. The results showed that the multiple logistic regression model can promote traditional soil mapping and it can be used to large group of other scientific fields.
M. Isazadeh, P. Mohammadi, Y. Dinpazhoh,
Volume 21, Issue 4 (2-2018)
Abstract
Statistical analysis and forecast discharge data play an important role in management and development of water systems. The most fundamental issues of statistical analysis and forecast discharge in Iran are lack of data in long term period and lack of stream flow data in gauging stations. Considering the issues mentioned in this study, we tried to estimate the daily data flow (runoff) of Santeh gauging station in Kordestan province using the nearby hydrometric and meteorological stations data. This estimation occurred based on the sixteen different input combinations, including data of daily flow of hydrometric stations Safakhaneh and Polanian and daily runoff in Santeh precipitation gauging station. In this research, the daily flow estimation of the Santeh station in each of the months of the year was evaluated for sixteen different combinations and artificial neural network models and multiple linear regressions. The performance of each model was evaluated with the indicators RMSE, CC, NS and t-student statistic. The results showed good performance of both models but the performance of the artificial neural network model was better than the regression model in estimation of the daily runoff in the most months of the year. Mean error of artificial neural network and multiple linear regression models was respectively estimated as 6.31 and 8.07 m3/s in the months of the year. It should be noted that the artificial neural network, for each sixteen combination used, had better result than the regression model.
Z. Mollaee, J. Zahiri, S. Jalili, M. R. Ansari, A. Taghizadeh,
Volume 22, Issue 2 (9-2018)
Abstract
Spectral Reflectance of suspended sediment concentration (SSC) remotely sensed by satellite images is an alternative and economically efficient method to measure SSC in inland waters such as rivers and lakes, coastal waters, and oceans. This paper retrieved SSC from satellite remote sensing imagery using radial basis function networks (RBF). In-situ measurement of SSC, water flow data, as well as MODIS band 1 and band ratio of band 2 to 1 were the inputs of the RBF. A multi-regression method was also used to make a relationship between the in-situ data and the water reflectance data retrieved from MODIS bands. The results showed that RBF had the best SSC prediction error (RMSE=0.19), as compared to the multi-regression and sediment rating curve methods, with the RMSE of 0.29 and 0.21, respectively.
B. Farid Giglou, R. Ghazavi,
Volume 22, Issue 3 (11-2018)
Abstract
In this research, a regression model was introduced to study the mechanisms of the formation of gullies in the Quri Chay watershed, northern Ardebil province (Moghan Plain); this was done through investigating the effective factors of geo-environment and soil characteristics on the gully erosion. For this purpose, 17 gullies were randomly assigned through field surveys. Mapping and recording the morphometric of the selected gullies were performed by GPS positioning after seven rainfall events. The catchment-upper area of each gully was determined and its related physical parameters were calculated in order to investigate the effect of the physical characteristics of the catchment. Soil sampling was also done at the head of each gully at two different depths (30-30 and 60-30 cm) in order to determine the physical and chemical characteristics of the soil. According to measurement of the morphometric characteristics of the gully and soil characteristics through multivariate analysis of the data, a suitable regression model was developed for the longitudinal development of erosion after determining and calculating environmental factors related to the upper catchment of the gullies. The results of the correlation matrix between the longitudinal extension of the gully and the factors investigated indicated that the factors related to the physical characteristics of the beside watershed (area, perimeter, main stream length and average width of the catchment, main stream slope), gully morphometric characteristics (mean of gully cross section, the gully expansion area, and the gully average width) and soil characteristics (geometric mean of the aggregates diameter, lime, organic matter percentage) affected the formation and expansion of gully erosion in the Quri chay catchment. The results of regression analysis showed that the longitudinal expansion of the gully was mostly influenced by the area around each gully and the percentage of organic matter, which resulted in pressure on the rangeland and the loss of vegetation, which increased runoff and accelerated the lengthwise expansion of the gully. Also, the increase in the area of the beside catchment the gullies is known as one of the factors influencing the length of the gully, due to the high volume of runoff entering the head cut section; so it is necessary to manage runoff in the gully with the large beside catchment.
K. Nosrati, M. Heydari, M. Hoseinzadeh, S. Emadoddin,
Volume 22, Issue 3 (11-2018)
Abstract
Ziarat drainage basin, in the southern part of Gorgan city, is exposed to mass movement, especially landslide occurrence, due to geologic, geomorphologic, and anthropogenic reasons. The objectives of this study were to predict landslide susceptibility and to analyze the effective factors using rare events logistic regression. In view of this, the map layers of the variables including geology, land use, slope, slope aspect, distance of road, distance of fault and distance of river were prepared using topographic and geologic maps and aerial photo interpretation. In addition, the map layers of the soil variables including the percent of clay, silt, sand, and saturation water as well as plasticity limit index were determined based on the laboratory analysis of 32 soil samples collected from landslide sites and 32 soil samples obtained from non-occurrence landslide sites. The controlling factors of landslide were determined using rare events logistic regression analysis; then based on their coefficients, the landslide risk zoning map was prepared and validated. The landslide risk zoning map was classified in five different hazard classes ranging from very low risk to very high risk; the very high risk class with 16.8 km2 was assigned as the having the highest percent of the catchment area. The results of the model validation showed that the rare events logistic regression model with the receiver operating characteristic (ROC) of 0.69 could be a suitable prediction model for the study area. The results of this study could be, therefore, useful for corrective actions and watershed management landslide high-risk zones.
H. Asakereh, A. Shahbaee Kotenaee, M. Foroumadi,
Volume 23, Issue 1 (6-2019)
Abstract
In the vast majority parts of the Earth, a prospect now visible is the mostly synthetic thinking and fabrication by the human hand. Collision and impact of humans on the natural environment in the short and long-term courses for obvious geographical features have changed a variety of spaces. One of the consequences of human impact on the natural environment during the current period is the phenomenon of climate change. One of the climatic parameters that plays an important role in agriculture, energy, urban, tourism and road transport is the minimum temperature. In this study, an attempt was made using the minimum temperature data from 5 meteorological stations in the West Mazandaran province, as well as HADCM3 model data, to show how to change this parameter in the future periods based on simulation by the SDSM model. Accordingly, after selection of the suitable climate variables and model calibration, the accuracy of the created model in the base period was evaluated; after ensuring the sufficient accuracy of the model according to A2 and B2 scenario, data minimum temperature in 2100 was simulated. Based on the simulation results showed that the values of minimum temperature in the region over the coming years would increase. This parameter was such that the average seasonal periods 2016 to 2039, 2040 to 2069 and 2070 to 2099, as compared to the baseline period would increase, on average, by 1.8, 3.5 and 6 percent. The largest increases in the minimum temperature in the western and southern parts of the region could occur. It was also found that unlike other months of the year, the minimum temperature in January would be a decreasing trend.
S. Ghorbani, R. Moddress,
Volume 23, Issue 3 (12-2019)
Abstract
The purpose of this study was to model the relationship between the frequency of dust storms and climatic variables in desert areas of Iran. For this purpose, climatic data of temperature (maximum and minimum), rainfall, wind speed (maximum and minimum), and their relationship with the number of days with dust recorded in 25 meteorological stations (statistical period since their inception until 2014) in summer using Pearson correlation coefficient and linear regression method multivariate was analyzed in SPSS software. Also, due to regional analysis, correlation coefficient between climatic variables and frequency of drought storms in desert areas of Iran, the mapping of these coefficients was prepared by method of Inverse distance weighting (IDW) in Arc GIS software. The results showed that the stations in the south and southwest of the study area have the highest dust incidence in the summer season. So that Zabul station with (3892 days) has the most frequent occurrence of dust storms. In most stations, there was a significant relationship between the frequency of dust storms and the variables of average wind speed and maximum wind speed. The highest correlation coefficient of the mean wind speed was related to the station of the Chabahar Konarak with correlation coefficient of 0.710 and Iranshahr station with a correlation coefficient of 0.65, showed the highest correlation with maximum wind speed. The maximum temperature variable at Qom station with a correlation coefficient of 0.398 shows a significant and positive relationship. Iranshahr station has a correlation coefficient of -0.620 with a mean temperature and Minab station has a correlation coefficient of -0.446 with maximum temperature. The results of temperature correlation with the frequency of dust storms indicate that ground low pressure is effective in creating the phenomena in the warm course of the year. Most stations have inverse correlation with precipitation. The highest correlation coefficients between precipitation and dust events were observed at -0.208 and -0.185 at east of Isfahan and Torbat Heidariyeh stations, respectively. Multivariate regression modelling between dust and climatic variables in summer also shows that the most important parameter in dust events are average wind speed, maximum wind speed and average temperature. Regression models show that, at the best condition, climate variables explain only 70% of the variation of dust frequency.
Z. Ebrahimikhusfi,
Volume 24, Issue 1 (5-2020)
Abstract
The purpose of this study was to analyze the temporal variations of dust phenomenon and its relationship with the climatic elements in Yazd city, located near one of the critical centers of dust production in the center of Iran. For this purpose, the Dust Storm Index was first calculated. After the standardization of precipitation, temperature, maximum wind speed, average wind speed, relative humidity and, dust storm index, the co-linearity effect between variables was calculated by using inflation variance factor. Then, several regression models were prepared based on the optimal Ridge parameter. The performance of the models was evaluated based on the determination coefficient, F value and Root Mean Square Error. Finally, by using the most accurate model, the impact of climate parameters on the dust events changes was determined. The results showed that the incidence of dust events in the spring was more than the rest of the year. Based on the optimal model (Model 12), it was found that the main factor influencing the dust storm index variations in different seasons was the surface winds speed. It was also shown that 39%, 25%, 46% and 31% of dust storm index changes in winter, spring, summer, and autumn were due to the interaction of the five climatic parameters studied in this study.
Z. Maghsodi, M. Rostaminia, M. Faramarzi, A Keshavarzi, A. Rahmani, S. R. Mousavi,
Volume 24, Issue 2 (7-2020)
Abstract
Digital soil mapping plays an important role in upgrading the knowledge of soil survey in line with the advances in the spatial data of infrastructure development. The main aim of this study was to provide a digital map of the soil family classes using the random forest (RF) models and boosting regression tree (BRT) in a semi-arid region of Ilam province. Environmental covariates were extracted from a digital elevation model with 30 m spatial resolution, using the SAGAGIS7.3 software. In this study area, 46 soil profiles were dug and sampled; after physico-chemical analysis, the soils were classified based on key to soil taxonomy (2014). In the studied area, three orders were recognized: Mollisols, Inceptisols, and Entisols. Based on the results of the environmental covariate data mining with variance inflation factor (VIF), some parameters including DEM, standard height and terrain ruggedness index were the most important variables. The best spatial prediction of soil classes belonged to Fine, carbonatic, thermic, Typic Haploxerolls. Also, the results showed that RF and BRT models had an overall accuracy and of 0.80, 0.64 and Kappa index 0.70, 0.55, respectively. Therefore, the RF method could serve as a reliable and accurate method to provide a reasonable prediction with a low sampling density.
S. Motalebani, M. Zibaei, A. Sheikhzeinoddin,
Volume 24, Issue 3 (11-2020)
Abstract
The interaction of population growth, technological improvement and climate change have impacted severely on agricultural and environmental sustainability. In Iran, conventional tillage practice has resulted in soil erosion and loss of soil organic matter. In this regard, Conservation Agriculture (CA) forms part of this alternative paradigm to agricultural production systems approaches and can be regarded as a means to enhancing food productivity, reducing poverty, and mitigating the consequences of climate change in rural households. The objectives of this study were to examine the determinants and impacts of CA technology on wheat yield, poverty gap and water use. To this end, an endogenous switching regression (ESR) model was employed to estimate the impacts of CA technology on continuous variables such as wheat yield, poverty gap and water use. A sample of 260 farmers from Zarghan district was selected for interview collection of necessary farm level data. The results indicated that in the select equation of ESR model, ten coefficients (out of 12) are significant at the 5% level or higher. Knowledge of soil quality, access to credit, access to information, education, farm size, ownership of machinery, participation in agricultural extension activities and farmer’ perception have positive and significant effects on the probability of adopting CA. In contrast, variables such as the distance to shopping center and number of land parcels have negative and significant influence on adoption. Also, the results of ESR model and counterfactual analysis showed that wheat yield would increase by 1.05 tons and poverty gap and water use would decrease by 20% and 910 cubic meters per hectare respectively if farmers adopt CA technology.
S. Zandifar, Z. Ebrahimikhusfi, M. Khosroshahi, M. Naeimi,
Volume 24, Issue 3 (11-2020)
Abstract
The occurrence of wind erosion and the spread of dust particles can be regarded as one of the most important and threatening environmental factors. Climate change and the frequency of droughts have played an important role in exacerbating or weakening these events. The primary objective of the present study was to investigate the trend of changes in four important climatic elements (precipitation, temperature, wind speed and relative humidity) and dust storm index (DSI) in Qazvin city using the Mann-Kendall pre-whitened test and to determine the relationship between them based on the multiple linear regression method. Assessment of the meteorological drought status based on two standardized precipitation index and standardized precipitation, as well as the evapotranspiration index and analysis of their effect on activity level of dust events, was the other objective of this study in the study area. For this purpose, after preparing and processing the climatic data and calculating the dust storm index, the trend of changes and the relationship between climatic parameters and dust events were investigated. The results showed that the changes of trend in the annual precipitation and relative humidity in Qazvin city were increasing, while the trend of annual changes in the wind speed and the mean air temperature was a decreasing one. Investigation of the monthly changes in the dust events also showed that there was a sharp decrease in the occurrence of wind erosion and the spread of domestic dust particles only in July. On a seasonal scale, with the exception of winter that has been reported without trends, in other seasons, the intensity of these events was significantly reduced. The effect of the meteorological drought on wind erosion was estimated to be 11% at the confidence level of 99%. In general, these findings indicate a decreasing trend of land degradation and desertification caused by wind erosion in Qazvin.
M. Alinezhadi, S. F. Mousavi, Kh. Hosseini,
Volume 25, Issue 1 (5-2021)
Abstract
Nowadays, the prediction of river discharge is one of the important issues in hydrology and water resources; the results of daily river discharge pattern could be used in the management of water resources and hydraulic structures and flood prediction. In this research, Gene Expression Programming (GEP), parametric Linear Regression (LR), parametric Nonlinear Regression (NLR) and non-parametric K- Nearest Neighbor (K-NN) were used to predict the average daily discharge of Karun River in Mollasani hydrometric station for the statistical period of 1967-2017. Different combinations of the recorded data were used as the input pattern to predict the mean daily river discharge. The obtained esults indicated that GEP, with R2= 0.827, RMSE= 59.45 and MAE= 26.64, had a better performance, as compared to LR, NLR and K-NN methods, at the validation stage for daily Karun River discharge prediction with 5-day lag, at the Mollasani station. Also, the performance of the models in the maximum discharge prediction showed that all models underestimated the flow discharge in most cases.
A. Arab, K. Esmaili,
Volume 25, Issue 1 (5-2021)
Abstract
The study of floods has always been important for researchers due to the great loss of life and property. Investigation of flood bed can provide appropriate solutions to reduce this phenomenon to managers and researchers. In this research, the compound channel (with flood plain on one side of the main channel) Been paid, Therefore, two experimental models of compound channel in laboratory flume were examined by considering dimensional analysis. With the goal Investigation of lateral slope of flood wall in laboratory model In the first model, transverse slope 0 And in the second model, a value equal to 50% Was considered. Also in order to investigate the effect of longitudinal slope of river bed sediments Longitudinal slope in three steps 0.00 2, 0.004 and 0.006 Was changed. Examining the ADV speedometer data, the results showed that with increasing the longitudinal and transverse slope (slope of the flood wall) of the channel, the maximum longitudinal velocity changes to the floor of the channel. In order to investigate the effect of average sediment diameter on the scouring process during experiments Mm was used. The results showed that increasing the longitudinal and transverse slope had a great effect on increasing the volume of washed sediments 3 and 0.9 of sandy sediments with a diameter Along the canal and with the increase of these longitudinal and transverse slopes in the channel, more sediment transport volume occurs. In the following, using Investigation of dimensionless numbers obtained from dimensional analysis, dimensionless weight landing number was introduced to evaluate this value value of other hydraulic parameters and Was introduced. A relationship based on nonlinear regression with correlation coefficient Acceptable was introduced at around 0.88.
H. Kazemizadeh, M. Saneie, H. Haji Kandi,
Volume 25, Issue 2 (9-2021)
Abstract
To prevent demolishing bridge piles due to developing the scour hole under the foundation of these piles some solution has been proposed in the literature. One of the important approaches could be installing different geometric of roughness at the downstream and upstream piles sections. This causes the downward flows which are performing the main role in developing scour holes to be marginally decreased. The present study explores the effect of geometric roughness and also, continuity and un-continuity of roughness length on maximum scour holes around bridge pile. Results indicate that due to increasing the length of roughness the developed scour holes were formed by less scour hole depths. Furthermore, continuity of roughness increases the scour hole depths; however, un-continuity causes the height of scour holes to be developed by fewer values. Also, the comparison shows that the length of installed roughness in maximum value is decreasing the scour hole depth constitute 34 percent. Based on the non-linear regression technique an equation has been proposed to predict the maximum scour hole due to different conditions. Comparison between experimental and proposed values shows that the accuracy of the proposed equation has an acceptable error which has been calculated less than 11 percent.
A. Ghorbani, M. Moameri, F. Dadjou, L. Andalibi,
Volume 25, Issue 2 (9-2021)
Abstract
The purpose of this study was to model biomass with soil parameters in Hir-Neur rangelands of Ardabil Province. Initially, considering the vegetation types and different classes of environmental factors, at the maximum vegetative growth stage, using one square meter plot, biomass was estimated by clipping and weighing method. For each transect, a soil sample was taken and transferred to the soil laboratory and the various parameters were measured by conventional methods. The relationship between soil factors and the rangeland biomass was analyzed and simulated using linear multiple regression. Among the measured soil factors, the Silt, EC, Ca, Ksoluble, OC, POC, pH, Mg, TNV, clay, P, and volumetric moisture had the highest effect and percentage of biomass forecast (p<0.01). The accuracy of the simulated maps was analyzed using RMSE criteria and for grasses, forbs, shrubs, and total biomass were equal to 0.81, 0.65, 0.34, and 0.46, respectively. The results of this study, not only point out the importance of soil factors on the biomass but also as a baseline data for managing rangelands, supply-demand, and carbon balance can be used in the current section.
S. S. Ariapak, A. Jalalian, N. Honarjoo,
Volume 25, Issue 2 (9-2021)
Abstract
In this study, spatial-temporal variation of dust deposition rate in the western and eastern half of Tehran and its climatic parameters affecting were studied. At 34 points in the city, dust samples were collected by glass traps from the roof, for twelve months, and the climatic data were obtained and analyzed from relevant organizations. The highest deposition rate is in the western half of the city and its total amount has varied from 54.52 to 121.21 g/m2/y. In both halves of the city, summer has the highest dust deposition rate and its central areas have the highest amount. There were significant positive correlations between dust deposition rate with temperature and medium wind speed, and there were significant negative correlations between dust deposition rate with rainfall and relative humidity in all months, which justifies the high dust deposition rate in the dry seasons of the year. The results of stepwise regression showed that rainfall was the most important factor affecting the dust deposition rate in both halves of the city. The city of Tehran has a special geographical location the presence of mountains like a barrier has prevented dust from leaving the city and the air inlet corridor of Tehran has faced problems due to the expansion of building construction and high-rise building. Other factors affecting the rate of dust deposition in this city, in addition to the distance from the main source of dust production, atmospheric parameters can be mentioned the existence of barren lands around the city, vegetation cover, construction operations, and traffic.
K. Shirani,
Volume 25, Issue 2 (9-2021)
Abstract
Delineation of gully erosion susceptible areas by using statistical models, as well as optimum usage of existing data and information with the least time and cost and more precision, is important. The main objective of this study is to determine the areas accuracy to gully erosion and susceptibility mapping by using data mining of the bivariate Dempster-Shafer, linear multivariate statistical methods and their integration in Semirom watershed, southern Isfahan province. First, the geographical location of a total of 156 randomly gullies were mapped using preliminary reports, satellite imagery interpretation and field survey. In the next step, 14 conditioning parameters of the gullies in the study area were selected including the topographic, geomorphometric, environmental, and hydrologic parameters using the regional environmental characteristics and the multicollinearity test for modeling. Then, the Dempster-Shafer statistical, linear regression, and ensembled methods were developed using 70% of the identified gullies and 14 effective parameters as dependent and independent variables, respectively. The remaining 30% of the gully distribution dataset were used for validation. The results of the multivariate regression model showed that land use, slope and distance to drainage network parameters have the most significant relation to gully occurrence. The gully erosion susceptibility maps were prepared by individual and ensemble methods and they were divided to 5 classes of very low to very high rate. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to validate gully erosion susceptibly maps. The verification results showed that the AUC of ensemble method (0.948) is higher than Dempster-Shafer (0.924) and Multivariate regression (0.864) methods. Also, the the seed core area index (SCAI) value of the ensembled model from very low to very high susceptible classes have a decreasing trend that indicating a proper separation of susceptible classes by this model.
N. Salamati, H. Dehghanisanij, L. Behbahani,
Volume 26, Issue 2 (9-2022)
Abstract
Increasing crop production per unit volume of water consumption requires recognizing the most dependent variable in drip irrigation to the volume of water consumption and also identifying the most important variables independent of water productivity in surface and subsurface drip irrigation for optimal use of available water resources. The present research was carried out in Behbahan Agricultural Research Station during four cropping seasons (2013-2017) on a Kabkab date variety. Experimental treatments include the amount of water in the subsurface drip irrigation method based on two levels of 75% and 100% water requirement and in surface drip irrigation based on 100% water demand. Data were analyzed using a randomized complete block design with three replications. The results of the analysis of variance of the mean of different irrigation treatments in quantitative traits showed that the effect of irrigation was significant at the level of 1% in terms of cluster weight index, fruit weight, and fruit flesh to kernel weight ratio. The results of regression analysis of variance showed that in the dependent variable of cluster weight, the consumption water volume explained 19.1% (R2 = 0.191) of the fluctuations of the dependent variable (cluster weight). Among all the studied variables, the volume of water consumption explained the most significant changes in date cluster drying. Fruit moisture with t (2.096) and equivalent beta coefficient (0.046) had a significant positive effect on water productivity at the level of 5%. The results of the Pearson correlation coefficient showed that the effect of yield on changes in water productivity was much greater than the volume of water consumed so the yield caused significant changes in water productivity. While the effect of water consumption on water productivity was not significant.
B. Shahinejad, A. Parsaei, A. Haghizadeh, A. Arshia, Z. Shamsi,
Volume 26, Issue 3 (12-2022)
Abstract
In this research, soft computational models including multiple adaptive spline regression model (MARS) and data group classification model (GMDH) were used to estimate the geometric dimensions of stable alluvial channels including channel surface width (w), flow depth (h), and longitudinal slope (S) and the results of the developed models were compared with the multilayer neural network (MLP) model. To develop the models, the flow rate parameters (Q), the average particle size in the floor and body (d50) as well as the shear stress (t) as input and the parameters of water surface width (w), flow depth (h), and longitudinal slope (S) were used as output parameters. Soft computing models were developed in two scenarios based on raw parameters and dimensionless form independent and dependent parameters. The results showed that the statistical characteristics in estimating w, the best performance is related to the MARS model, whose statistical indicators of accuracy in the training stage are R2 = 0.902, RMSE=1.666 and in the test phase is R2 = 0.844, RMSE=2.317. In estimating the channel depth, the performance of both GMDH and MARS models is approximately equal, both of which were developed based on the dimensionless form of flow rate as the input variable. The statistical indicators of both models in the training stage are R2 » 0.90, RMSE » 8.15 and in the test phase is R2 » 0.90, RMSE = 7.40. The best performance of the developed models in estimating the longitudinal slope of the channel was related to both MARS and GMDH models, although, in part, the accuracy of the GMDH model with statistical indicators R2 = 0.942, RMSE = 0.0011 in the training phase and R2 = 0.925, RMSE = 0.0014 in the experimental stage is more than the MARS model.
