جستجوی مقالات مرتبط با کلیدواژه "regression models" در نشریات گروه "آب و خاک"

The runoff generation in a watershed is mainly influenced by the hydrological, geomorphological, and climatic conditions of the region. Regarding rainfall-runoff models, the problem becomes very complicated due to the non-linear response of the watershed to the rain event. Prediction of daily river flow is one of the most important hydrological issues, which is very important for flood management. River flow rates can be estimated by several methods, each of which has strengths and weaknesses. Regarding rainfall-runoff models, the problem becomes very complicated due to the non-linear reaction of a watershed to the rain event. In addition, due to the spatial changes of precipitation in an area, this complexity increases. In this research, the rainfall and runoff model is analyzed with the help of statistical methods and multivariate regression. The purpose of this study predict the inflow to Amirkabir Dam using multivariate regression methods and artificial intelligence (AI) methods, including the network model. It is an artificial neural network (ANN).

To investigate the relationship between rainfall and runoff and to estimate the water entering the dam due to the rainfall upstream of the watershed, the rainfall of all the stations of the watershed upstream was received. The 7-year statistics of Karaj river flow (2016-2022) were used. After checking the rainfall data of the upstream stations, the homogeneity of the data was checked and the stations that had a suitable correlation in terms of climate were selected. At this stage, stations with appropriate conditions were selected by using factor analysis between upstream precipitation and runoff and water entering the dam downstream of the watershed. Then, to more properly analyze the relationship between rainfall and runoff, two-day and three-day cumulative rainfall at the selected stations was calculated. Then, the relationship between rainfall and runoff to the dam was investigated using statistical methods of multivariable regression and artificial intelligence. To get more accurate results, different seasons of the year were divided and the relationship between rainfall and runoff entering the dam in different seasons was investigated. Error statistics were calculated for calibration and verification during the test and training period. Finally, the final analysis of the data and the prediction of the runoff entering the dam was estimated using the upstream rainfall.

Determining the effective stations in the runoff generation entering the dam as well as the delay time of their precipitation was achieved using multivariable regression and four stations of Nesa, Sira, Shahristanak, and Amirkabir Dam., the model of the volume of inflow to the dam, and precipitation in the catchment area of Amirkabir Dam. The coefficient of determination (R2) of the calibrated model was calculated as 76%, which is an acceptable coefficient in the relationship between precipitation and runoff. Based on the calibration and validation models of rainfall-runoff evaluation of rainfall forecasting models in July 2022, good rains are predicted for the watershed of Amir Kabir Dam. The rain system entered the country on July 28th and 29th and until July 31th it had relatively good coverage in the whole country, and on August 1st and 2nd this system weakened and only operates in limited parts of the country such as the Amir Kabir watershed. The results of evaluating the performance of the models with indicators such as coefficient of explanation (R2), mean absolute value of error (MAE), and root mean square error (RMSE) showed that the ANN model in both calibration (training) and validation (testing) stages ) has performed better than the multivariate regression model. The accuracy indices of the model for the ANN model training stage were equal to R2=0.77 and RMSE=0.27 m3 s-1, while these indices for the testing stage were equal to R2=0.87 and RMSE=0.46 m3 s-1. It indicates the better performance of the ANN model.

The research results of this article showed that due to the presence of 5 rain gauge stations in the catchment area of Amir Kabir Dam, all the stations can not have the same effect on the water entering the dam. Using the cluster cluster method, the effect of all the stations on the inflow to Amirkabir Dam was investigated and suitable rain gauge stations were selected. Also, the results showed that the relationship between the rainfall of the watershed and the runoff entering the Amirkabir dam is different in different seasons and it has the highest correlation in the winter season because it is less affected by other factors affecting the runoff of the basin, including water from melting snow or thunderstorms. One of the other results of this study was that the calibrated and validated model had a slightly higher yield in the three seasons of winter, spring, and autumn, and a slightly lower yield in the autumn season.

The lead-time and accuracy of the precipitation forecasts have a substantial influence on the flood forecast and warning systems. The application of Ensemble Precipitation Forecasts (EPFs) derived from numerical precipitation models has been developed due to their impact on increasing flood lead-time. This research aims to improve the skill of numerical precipitation models using post-processing techniques. In this regard, EPFs of three meteorological models, e.g., NCEP, UKMO, and KMA, were extracted for sex precipitation events leading to flood in the Dez river basin during 2013-2019. The statistical approaches and data-driven model were applied to post-process the EPFs. For this purpose, the raw forecast of every single model was corrected using linear and power regression models. Then, the corrected output of single models was combined using the proposed model of Group Method of Data Handling (GMDH). The results indicated that Power Regression Model (PRM) outperformed the linear models to correct raw forecasts. After correction of models' output, more accurate results were obtained by NCEP and UKMO models. Moreover, the Multi-Model Ensemble (MME) system constructed by the GMDH model (MME_GMDH) had a great effect on the skill of numerical precipitation models, so that the Nash–Sutcliffe and normalized error (NRMSE) efficiency criteria for MME_GMDH respectively were improved on average 23% and 11% in comparison with the PRM. A comparative assessment of the discrimination capability of MME with single ensemble models using ROC curve at the thresholds of 2.5 and 10 mm represented a higher discrimination ability by MME_GMDH for both thresholds. Post-processed EPFs exert as a reliable input to the hydrological models for extreme events forecast.

Climate variations are one of the most important factors affecting water resources. Severe floods and runoff increase the risk of the vulnerability of hydraulic structures. The failure of an embankment dam causes extensive financial, human, and environmental damages. Overtopping and internal erosion are the main causes of the embankment failure. More than 46% of the embankment failures around the world are attributed to overtopping. The breach process during this event is generally divided into two parts: the breach initiation stage; and the breach development stage. In the initial stage, the outflow discharge from the dam is not considerable and includes a small stream along the channel, while in the breach development stage, the outflow and erosion processes are significant. On the other hand, about 48% of failures and accidents affecting embankment dams are related to piping. In an embankment dam failure, accurate determination of flow, time, and breach characteristics along with the analysis of hydrograph components can play an important role in reducing the financial losses and fatality. Several equations have been established using literature data and field observations to calculate the peak outflow discharge (Qp) as a function of the height of water above the breach (Hw) and stored volume above the breach (Vw) (Costa 1985; Gupta and Singh 2012; Hooshyaripor et al. 2014; MacDonald and Langridge‐Monopolis 1984; Pierce et al. 2010). The failure time (tf) has been investigated by various researchers. The tf equations were obtained as a function of the average breach width (Bave) (USBR, 1988), Hw, or their combination (Von Thun & Gillette, 1990). Therefore, the height of breach (Hb) and Vw are also considered as important parameters (Froehlich, 2008). On the other hand, Hb is found to be an important factor affecting the hydraulic and breach characteristics (Dhiman & Patra, 2019; Wang et al., 2020). In this research, physical models with different geometrical and mechanical properties have been used to investigate the mechanisms of erosion and breach evolution. Therefore, several experimental models were constructed and tested in the laboratory flume at three heights of 0.3, 0.4, and 0.5 m. Therefore, five different soil combinations were used and studied. The breach hydrograph components were analyzed, and the breach characteristics were examined as well as the hydraulic characteristics. The BREACH mathematical model is one of the most common models used to evaluate the breach parameters and output hydrographs in embankment dam failures. This model is developed by the National Weather Service (NWS) and is based on the principles of hydraulics, hydrology, and geotechnics. In overtopping failures, the flow over the crest is calculated by the broad-crest weir formula. While the flow into the pipe is simulated by the orifice equation. The results of the model are compared with the observations of some historical failures, which indicates the higher accuracy among the existing mathematical models. In the present study, the output hydrograph components of the experimental models were also compared with the historical data obtained from the BREACH mathematical model. Gene Expression Programming (GEP) was employed as one of the artificial intelligence methods along with the nonlinear regression to obtain a suitable relationship between the input parameters of the models. In order to evaluate the efficiency of the models, three statistical indices, including the root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and coefficient of determination (R2) are used for performance assessment of the proposed equations in the present study. To develop new equations for the determination of Qp, there are several input variables, that were not introduced before. Therefore, multiple combinations of datasets including historical, experimental, and the hypothetical failure of real dams have been used in this study. Based on observations, the values of tf are highly correlated with hydraulic and breach characteristics. Therefore, new relations have been proposed based on those parameters. On the other hand, the newly introduced equations related to the Hb can lead to more accurate assessment of the breach process in the overtopping and piping failures. According to statistical analyses, the values of R2 for the proposed equations of Qp, obtained from GEP, as well as nonlinear regression, were 0.84 and 0.84, respectively, based on the breach parameters. The values of the recent coefficient for the development of tf relations obtained from the regressions were 0.87 and 0.88, respectively, according to the hydraulic and breach characteristics. By application of GEP for the determination of Hb in both overtopping and piping failure cases, the values of R2 were 0.99 and 0.99, respectively, as a function of the embankment and hydraulic characteristics. Soil gradations play an important role in increasing the erosion rate and reducing the tf. Therefore, breach formation in coarse-grained particles will take less time to evolve due to its lower shear stresses compared to fine-grained soils. Similarly, the Bave has a significant effect on the breach output hydrograph and its components. The Bave variations based on Hw defined in this study, could cover a wide range of embankment dam failures.

In Mazandaran Province the performance of different drainage systems is essential for Canola cultivation as a second crop in paddies. For this purpose an experiment was conducted in Sari agricultural Sciences and Natural Resources University as base, in 2017-2018 cropping season. In different canola growth stage intervals, eight sampling were established under randomized complete block design with three replications in subsurface drainage systems and surface (Control) in order to determinate leaf area (LA), leaf area index (LAI), numbers of leaves (SLN) and leaf dry weight (LDW). Then Statistical analysis was carried for study of drainage depth and space on the mentioned growth index and mathematical relationship between leaf area and its dry weight with the evaluation of linear and nonlinear regression models was determined in different drainage systems. Maximum of LA in all treatments occurred about 90 day after planting. Mathematical relations between LA and LDW were described by linear and power model is suitable as a correlation coefficient was 0.98. Among the mathematical functions, reverse polynomial functions with degrees 4 and 5, logarithmic equations and inverse logarithmic equations with degrees 3, 4, and 5 showed better results than other mathematical functions The relations obtained in this experiment can be used in simulation models of winter canola growth under water table control conditions.

Evapotranspiration is one of the most important parameters in the Planning and operation of reservoirs, designing of irrigation systems. The practical importance of accurate estimates of evaporation and the complexity of effect phenomenon, shows the use of new methods of data mining. In this study, the simulation of pan evaporation in Tabriz station using multiple regression models were investigated. Meteorological data, including maximum and minimum air temperature, dew point, maximum and minimum air relative humidity, number of sunshine hours and Daily wind speed during (1992-2012) were used in synoptic Tabriz stations. Various models of multiple linear regression and nonlinear one were derived for Tabriz station. The selected multiple linear regression model were tested by Ridge Regression method to be considered multi-collinearity among inputs in the model.Variance inflation factor, values for each variable were calculated. The results showed that all Variance inflation factor ,s had the value less than 10. In addition, the ratio for two- variable selected model was 3.34. Therefore, there was no multi-collinearity in the selected multiple linear regression model f (Tmin, n). Durbin-Watson statistic for the selected model was 1.45 that shows the reliability of the selected multiple linear regression model. RMSE and R2 values of the selected models (multiple linear regression and Non- Linear Regression) was calculated as 2.45 and 0.67 and 2.58 and 0.65, respectively. This results demonstrate the ability of regression techniques to estimate Pan evaporation in Tabriz station.

This paper presents the results of an experimental program developed to investigate the effect of an additive agent branded CBRPLUS on the mechanical behavior of a forest soil with high plasticity. Various experiments consisting of Atterberg limits, standard compaction, California bearing ratio (CBR), swelling potential and swelling pressure were conducted on natural soil and soil stabilized with various percentages of CBRPLUS. The results indicated that the addition of this material (at the rate of 0.05%), significantly changes the physical and mechanical properties of rehabilitated soil, including, reduction of the liquid limit (at least 6%), plasticity index (at least 9%), swelling potential (at least 27%), and swelling pressure (at least 45%), and also increasing the bearing capacity of soil (at least 53%); hence, the improvement of soil properties is a function of mass percentage of CBRPLUS. Furthermore multiple regression models were developed for CBR, swelling potential and swelling pressure as a function of additive agent percentage, plasticity index and maximum dry unit weight with accuracy and a high degree of agreement between experimental and predicted values. In addition a sensitivity analysis was also performed to investigate the effect of various parameters on CBR, swelling potential and swelling pressure values.

Evaporation is one of the main parameters for the optimum operation of reservoirs, design of irrigation systems and scientific management of water resources. Accurate estimation of the water evaporation level is crucial in any region especially in arid and semiarid regions. In this study, the feasibility of simulation of pan evaporation in Maraghe station using the multiple regression models were investigated. Meteorological data, including the maximum and minimum air temperatures, dew point temperature, the maximum and minimum relative humidities, the number of sunshine hours, the wind speed records during the 1992 to 2012 (using the daily time scale) of Maraghe synoptic station were used. Various models of multiple linear regression (MLR) were derived for simulating the evaporation in the mentioned station. The selected MLR model was tested for multi-collinearity of input repressors using the Ridge Regression. For this purpose, the Variance Inflation Factor (VIF), responsible for the multi-collinearity in regression analysis, was calculated for each of the input variables. The results showed that all of the obtained VIFs values were less than 10 and the multi-collinearity is not created. Furthermore, the ratio of eigenvalues of the correlation matrix, λmax\λmin, for the selected model was calculated as 6.2. The selected model consisted of the maximum relative humidity (RHmax), number of sunshine hours (n), and minimum air temperature (Tmin) as independent inputs, and the Pan evaporation as the dependent variable, f (RHmax, Tmin, n). Therefore, it can be concluded that there was no multi-collinearity in the selected MLR model. The RMSE and R2 values of the selected model (MLR) was calculated as 2.37 and 0.676 mm/day, respectively.

Direct measurement of soil hydraulic characteristics is costly and time-consuming. Also، the method is partly unreliable due to soil heterogeneity and laboratory errors. Instead، soil hydraulic characteristics can be predicted using readily available data such as soil texture and bulk density using pedotransfer functions (PTFs). Artificial neural networks (ANNs) and statistical regression are two methods which are used to develop PTFs. In this study، the multi-layer perceptron (MLP) neural network and backward and stepwise regression models were used to estimate saturated hydraulic conductivity using some soil characteristics including the percentage of particle size distribution، porosity، and bulk density. Data of 125 soil profiles were collected from the reports of basic soil science and land reclamation studies conducted by Khuzestan Water and Power Organization. The results showed that MLP neural network having Bayesian training algorithm with the greater coefficient of determination (R2=0. 65) and the lower error (RMSE =0. 04) had better performance than multiple linear regression model in predicting saturated hydraulic conductivity.

Application of empirical models is a must owing to complexity of process, different features, spatial and temporal variation of soil erosion and non-existence or lack of pertaining data. In this study, the efficiency of rainfall and runoff variables of 11 storms during winter 2006 and spring 2007 in explanation of storm-wise sediment yield in Chehelgazi watershed of Gheshlagh Dam basin in Kurdistan province was evaluated with the help of bivariate and multivariate regression models by using different transformed data. The models’ efficacy was then assessed by using coefficient of determination, error of estimation and verification. The results showed that bivariate regression models, using different transformed data with determination coefficient of beyond 66%, and respective error of estimation and verification of below 40 and 30%, had a better efficiency in estimation of storm-wise sediment yield than multivariate regression models. The results also verified that the rainfall variables could explain storm-wise sediment yield variations better than runoff relating factors with overall contribution of some 80%.

Sediment load-discharge data of hydrometric stations in the north of Great Khorasan province were studied. Twenty nine stations were selected and the mean annual sediment yield was computed using sediment rating curves. The total annual sediment yield for these catchments (61.5 to 16800 km2) varied between 4.8 to 19500 M ton/year and the specific sediment yield varied between 62 to about 4000 ton/year/km2. Due to large variations in the total and specific sediment yield, 29 selected catchments were divided in two groups: 17 large catchments (area>500 km2) and 12 smaller ones (area)