cross validation

The aim of the current research is to determine the cutoff score of the Tolimo test for doctoral candidates applying for study opportunities abroad by applying multiple regression in the Hurwicz method, which is a decision-making approach. The statistical population of this research includes the candidates of one course of Tolimo exam, which were 461 people. The research method of this study is based on a quantitative approach, and in terms of its purpose, it is part of applied research, and in terms of analysis, it is part of secondary analysis studies, and the scores of all 461 candidates in each of the grammar, reading comprehension, listening, and writing sections are used to determine the cutoff score. becomes Based on the results of the study and considering the small amount of classification error, if the total score is used, the average value of the Hurwicz index is the cutoff score of 481, and if the linear regression model is significant, using the results of the Hurwicz index in multiple regression, the cutoff score is 491. It can be used as a cutoff score. The proposed method significantly improves the accuracy of determining the cutoff score compared to Angoff and Bookmark methods. According to the findings obtained from cross-validation and error values, the cutoff score obtained from the combined strategy leads to more accurate results with zero classification error. 

Soil is considered to be dynamic and complex both spatially and temporally and thus, many physical, chemical and biological properties should be determined before assessing its quality. To reach this purpose, a large sample must be collected for laboratory tests which is both time-consuming and costly and requires lots of attention and precision. Compared to other components of soil, sand is closely related with the quality of soil and crop growth. Therefore, environmental modeling and digital soil mapping projects should pay special attention to this part of soil texture. However, large-scale detection, mapping and monitoring of sand content using common traditional sampling and usual laboratory analytical procedures are both time-consuming and costly due to the vast spatial variability of sand. Compared to laboratory-based and field spectroscopy, spaceborne and airborne remote sensing have a lower level of accuracy due to atmospheric effects, compositional and structural effects, lower spatial and spectral resolution, geometric distortions and spectral mixing. Hence, an appropriate technology is required to overcome these imperfections and study spatially variable factors. Lab Diffuse reflectance Spectroscopy (LDRS) which utilizes fundamental vibration, overtones and a combination of functional groups has been introduced as a promising tool for soil investigation. The present research uses proximal soil sensing technology to study sand content.

128 samples were collected from a soil depth of 20cm in accordance with stratified randomized sampling method and supplementary data (geology, pedology, land use, etc.). The samples were then divided into two subsets: calibration subset with 96 and validation subset with 32 samples. Afterward, definitive calibration model was developed and reviewed with two & four latent variables in accordance with R, R2, RMSE, RPD and RPIQ indices using multivariate regression analysis-PLSR method, LOOCV cross-validation technique and preprocessing algorithms such as spectral averaging (spectral reduction method), smoothing and 1st derivative (Savitzky-Golay algorithm).
 

Results & Discussion:

The estimating model indicated that out of the seven latent variables, the first two and four variables can provide the best estimate of the volume of sand in 96 calibration samples and the 32 validation subset. Since more than 60% of the variance of sand variable and 95% of the variance of spectral variables can be concentrated in these selected factors, the predicting model was calibrated based on the first four LVs and the full LOOCV procedure. The best model was calibrated with these features: Rc=0.76, R2C=0.57, RMSEc= 9.77 and SEc of about 9.82. The correlation coefficients (R) between sand contents and the effective spectral bands were calculated and equaled UV-390nm= 0.46, Vis-510 to 540nm about 0.53, 680 to 690 about 0.55, NIR- 950 to 970 about 0.67 and 1100nm= 0.70, SWIR- 1410 nm=0.76, 1860 to 1900 about 0.76, 2180 to 2220 about 0.77 indicating that the selected spectral bands (spectral ranges) with the maximum R contents were the most effective independent predictors in the present modeling process. Furthermore, the most influential spectral domains in the modeling process were determined as follows: UV-390 nm, Vis-440-540 nm, NIR- 740-990 nm, SWIR- 1430-1890, 1930, 2190-2240, 2330-2440 nm which was in agreement with previous studies. The quality of the calibrated sand predicting model was evaluated with Hotelling, Adjusted leverage and residual variances tests. The model was validated based on 32 independent samples. General characteristics of the validation process for LV=4 were Rp= 0.82, R2p= 0.67, RMSEp= 8.83, SEp= 8.92 and bias= -0.93 and Rp= 0.83, R2p= 0.68, RMSEp= 8.68, SEp= 8.72 and bias= -1.26 for LV=2.

Results indicate that the final model was capable of predicting sand contents and thus for two factors (LV=2): RPDc= 1.51, RPIQc= 2.44, RPDp= 1.78 and RPIQp= 2.45 were obtained while for four factors (LV=4): RPDc= 1.54, RPIQc= 2.48, RPDp= 1.75 and RPIQp= 2.41 were reached. A RPIQ of more than 2 shows that the model is capable of estimating soil sand content in Mazandaran province using data collected through diffuse reflectance spectroscopy. Since a new generation of hyperspectral remote sensors with high spectral resolution is now available, results of the present study can be the starting point for more accurate mapping of sand particles in soil texture using RS platforms. However, proximal spectroscopy must be more thoroughly investigated. Determining and detecting the key wavelengths in the modeling process can enhance the upscaling operation and the new airborne/satellite hyperspectral sensors and thus result in more precise mapping of the soil texture. Finally, the VNIR-DRS technology was proved to be potentially capable of estimating soil sand content in Mazandaran province. The present model and key spectral domains identified in the present study can make a basis for future studies investigating the sand content in very large-scale samples using airborne/satellite hyperspectral data. This shows the importance of LDRS and its role in identifying optical wavelengths which will be used in space-borne data (upscaling process).

Due to high salinity of surface waters in Tabriz plain, which is one of the major concerns about irrigation and sustainable agriculture in the area, farmers exploit groundwater as supplement for surface water to irrigate their fields. This study aimed to apply Algebraic and Geo-statistical models for mapping groundwater depth through Tabriz plain over a period of 13 years (1380 to 1392) using data collected from 42 piezometric wells. Used models include Inverse Distance Weighted (IDW) and Radial Basis Functions (RBF), as representative of algebraic methods and Kriging as representative of Geo-statistical methods. Selection of appropriate method and validation of models were done by means of cross validation, mean bias error (MBE), root mean square error (RMSE) and coefficient of determination (R2). Results indicated that Kriging is more precise than other methods for zoning mapping the depth of groundwater, and the output map corresponds highly with land use, drainage networks, geology and through the study area. So, the method is considered to as the best model to zoning mapping the groundwater depth through Tabriz plain. Also, comparison of groundwater depth zoning maps over examined periods is indicative of an increase in groundwater depth in Southeast, East, South and partly North of the study area. This increase of groundwater depth could be related to improper exploitation of groundwater resources considering given garden lands located on the parts of the study area

Two deterministic methods [Radial Basis Functions (RBF) and Inverse Distance Weighting (IDW)], and two stochastic interpolation methods [Kriging and Co-Kriging] have been evaluated to estimate the annual precipitation in Ardebil Province. For this purpose, we used data taken from various stations across the province [4 synoptic stations, 1 climatological station and 24 rain gauges], over a decade (2005-1995). The performance of the above model was examined using cross validation and the indices of Mean Bias Error (MBE), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE).Finally, to identify under-estimated and over-estimated areas of each method at elevations above the spatial distribution of stations, the output of each model was examined. The results suggested that Kriging model had lower errors than other methods and was more compatible with the elevation surfaces. Therefore, this method was identified as the best option for estimating f precipitation in areas without adequate data and intense topographic gradients in Ardebil Province.

Water crisis is one of the most important problems in arid and semi-arid regions, so snowfall occurring in upstream parts of mountainous basins has an enormous role in hydrological balance. In this paper, the spatial distribution of snow density in Sakhvid, Yazd has been studied using an artificial neural network. Snow density is an important parameter for assessment of water resources in mountain basins, and, with thecorresponding data and snow depth, snow water equivalent values can be calculated. For this purpose, 216 in-situ snow density data were measured using the Mt. Rose sampler. Then, using SGA-GIS software, 32 geo-morphometric parameters were calculated from DEM. The best network was 1-9-32 with a multilayer perceptron model, the back-propagation algorithm,the sigmoid activation function, and a linear output. In order to evaluatethe network, the ANN correlation coefficient and the root mean square error (RMSE) were used. The results showed that the correlation coefficient and RMSE of the observed and estimated data were 86 percent and 5.1 respectively. So, application of artificial intelligent can simulate the spatial distribution of snow density very well.